Vulnerability database
Every flaw the U.S. government’s cybersecurity agency (CISA) has confirmed attackers are using, plus the new WordPress plugin and theme bugs published each day, sorted by what they mean for a small business. We refresh it twice a day. If you see something your website or office runs, tell us.
183 results · page 2 of 4
Aug 31, 2026MCPHub is a unified hub for centrally managing and dynamically orchestrating multiple MCP servers/APIs into separate endpoints with flexible routing strategies.CVE-2026-79748 · Other software · samanhappy · reported by GitHubCritical 9.9
MCPHub is a unified hub for centrally managing and dynamically orchestrating multiple MCP servers/APIs into separate endpoints with flexible routing strategies. Prior to version 0.12.15, the POST /api/servers and PUT /api/servers/:name endpoints in MCPHub create/update MCP server configurations and then immediately spawn the configured stdio process via child_process.spawn. Authentication is required, but there is no authorization check restricting these endpoints to admins, and there is no allowlist/sanitization on the command and args fields. As a result, any authenticated non-admin user can submit a server configuration with command:"/bin/sh" (or any other binary) and arbitrary args, causing MCPHub to execute the attacker-controlled process as the MCPHub server's OS user (commonly root in the published Docker image and in npx/systemd deployments). This issue has been patched in version 0.12.15.
- Product
- mcphub
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Aug 31, 2026MCPHub is a unified hub for centrally managing and dynamically orchestrating multiple MCP servers/APIs into separate endpoints with flexible routing strategies.CVE-2026-79747 · Other software · samanhappy · reported by GitHubHigh 7.1
MCPHub is a unified hub for centrally managing and dynamically orchestrating multiple MCP servers/APIs into separate endpoints with flexible routing strategies. Prior to version 1.0.32, an authenticated non-admin user can register a server pointing at an arbitrary URL and make the hub issue server-side requests to it, with no egress filtering (no block of loopback / RFC1918 / link-local 169.254.0.0/16). Via the OpenAPI proxy path the response body is returned to the caller (full, reflected SSRF); via the SSE/streamable-http transport the request is sent blind. This issue has been patched in version 1.0.32.
- Product
- mcphub
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Aug 31, 2026MCPHub is a unified hub for centrally managing and dynamically orchestrating multiple MCP servers/APIs into separate endpoints with flexible routing strategies.CVE-2026-79746 · Other software · samanhappy · reported by GitHubHigh 8.1
MCPHub is a unified hub for centrally managing and dynamically orchestrating multiple MCP servers/APIs into separate endpoints with flexible routing strategies. Prior to version 1.0.31, when a bearer key with accessType: 'servers' (or 'custom') is used against a group route, isBearerKeyAllowedForRequest grants access to the entire group as long as any single server in that group appears in the key's allowedServers list — not only when every server the key is scoped to matches, and critically, without ever re-checking allowedServers again once the group-level connection is authorized. A key explicitly scoped to one specific server therefore also grants full access to every other server that happens to share a group with it, including servers the key was never authorized for. This issue has been patched in version 1.0.31.
- Product
- mcphub
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Aug 31, 2026MCPHub is a unified hub for centrally managing and dynamically orchestrating multiple MCP servers/APIs into separate endpoints with flexible routing strategies.CVE-2026-79745 · Other software · samanhappy · reported by GitHubHigh 7.1
MCPHub is a unified hub for centrally managing and dynamically orchestrating multiple MCP servers/APIs into separate endpoints with flexible routing strategies. Prior to version 1.0.32, the built-in prompt and resource controllers perform no role checking. The mutating POST/PUT /api/prompts* and POST/PUT /api/resources* routes are attached to the authenticated router with no admin gate, and the handlers never read req.user. The DAO singletons they write are consulted first — ahead of any connected MCP server — for every session in handleGetPromptRequest / handleReadResourceRequest. A non-admin can therefore create, overwrite, and shadow global prompt templates and resources that all other users are served. The scored impact is the unauthorized integrity violation (creation/tampering/shadowing of globally-served records); stored prompt injection into other users' LLM sessions is a downstream consequence of that tampering. This issue has been patched in version 1.0.32.
- Product
- mcphub
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Aug 31, 2026MCPHub is a unified hub for centrally managing and dynamically orchestrating multiple MCP servers/APIs into separate endpoints with flexible routing strategies.CVE-2026-79744 · Other software · samanhappy · reported by GitHubHigh 8.8
MCPHub is a unified hub for centrally managing and dynamically orchestrating multiple MCP servers/APIs into separate endpoints with flexible routing strategies. Prior to version 1.0.29, MCPHub's PUT /api/system-config endpoint (handler updateSystemConfig) performs no authorization check. It is protected only by the app-wide authentication middleware and a rate limiter — it never inspects req.user.isAdmin. This issue has been patched in version 1.0.29.
- Product
- mcphub
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Aug 31, 2026MCPHub is a unified hub for centrally managing and dynamically orchestrating multiple MCP servers/APIs into separate endpoints with flexible routing strategies.CVE-2026-79743 · Other software · samanhappy · reported by GitHubMedium 6.9
MCPHub is a unified hub for centrally managing and dynamically orchestrating multiple MCP servers/APIs into separate endpoints with flexible routing strategies. Prior to version 0.12.13, MCPB File Upload Handler extracts a ZIP file and reads manifest.json from it. The name field in the manifest is directly concatenated into a file path (line 107) without any sanitization or path traversal character validation. An attacker can craft a malicious MCPB file where manifest.name is set to something like ../../../etc/malicious, causing the file to be extracted to an arbitrary location on the file system. The cleanupOldMcpbServer function (line 110) also uses the unsanitized name, potentially allowing deletion of arbitrary directories. This issue has been patched in version 0.12.13.
- Product
- mcphub
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Aug 30, 2026Origin Validation Error vulnerability in ash-project ash_ai allows a malicious web page to bypass the MCP server's DNS-rebinding protection and issue cross-siteCVE-2026-81315 · Other software · ash-project · reported by 6b3ad84c-e1a6-4bf7-a703-f496b71e49dbHigh 7.4
Origin Validation Error vulnerability in ash-project ash_ai allows a malicious web page to bypass the MCP server's DNS-rebinding protection and issue cross-site requests to a user's local MCP server with that user's actor. In AshAi.Mcp.Server, with the default allowed_origins: nil, origin_allowed?/3 accepts an origin when uri.host == conn.host and the forwarded scheme is https. Both values are attacker-controlled: conn.host comes from the Host header and the scheme is read from the raw x-forwarded-proto header with no trusted-proxy check. Under DNS rebinding the browser sends the attacker's origin and a matching host, and page JavaScript may set X-Forwarded-Proto: https, so the check passes with no TLS or proxy involved. The fix trusts only localhost origins by default; other origins require an explicit allowed_origins allowlist. This issue affects ash_ai: from 0.8.0 before 1.0.0.
- Product
- ash_ai
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Full record and what to do →NVD recordcna.erlef.orggithub.com
Aug 27, 2026The Dash MCP server bound its listener to the loopback address but never checked the host a request named.CVE-2026-81102 · Other software · dropbox · reported by VulnCheckLow 2.3
The Dash MCP server bound its listener to the loopback address but never checked the host a request named. src/mcp_server_dash.py constructed the server for its network mode with the interface restricted to loopback and no transport-security settings, so a name that had been pointed at the loopback address still reached the listener while carrying the attacker's host name. A page in a visitor's browser could therefore drive the local server and invoke its company-search and file-detail tools under the Dropbox credential the server holds. Only the network mode was reachable this way; the standard input mode was not. The fix supplies transport-security settings that enable host checking and allow only the loopback name and port, rejecting other hosts before a tool runs. The repository publishes no versions, so the affected boundary is the commit preceding the fix.
- Product
- mcp-server-dash
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Aug 27, 2026The Telnyx MCP server exposed its HTTP transport on every interface and did not require a caller credential.CVE-2026-81098 · Other software · team-telnyx · reported by VulnCheckCritical 9.3
The Telnyx MCP server exposed its HTTP transport on every interface and did not require a caller credential. packages/mcp-server/src/http.ts served MCP on the root path with a listener bound to all interfaces and parsed the caller's authentication headers in a mode that did not fail when they were absent, so a request without any credential completed initialisation and dispatched tools. Dispatch forwarded the server's own stored credentials, the Telnyx API key and client secret together with the code-execution key, to the upstream endpoint, so an unauthenticated caller able to reach the port acted with them. The current code defaults the host to loopback, requires a server API key, and enforces it in middleware.
- Product
- telnyx-mcp
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Aug 25, 2026genieacs-mcp is an MCP server for GenieACS written in Go.CVE-2026-55637 · Other software · GeiserX · reported by GitHubHigh 8.8
genieacs-mcp is an MCP server for GenieACS written in Go. Prior to 0.3.2, the Streamable HTTP transport in cmd/server/main.go creates an unauthenticated /mcp listener on the default MCP_LISTEN_ADDR value 127.0.0.1:8080 when MCP_AUTH_TOKEN is unset and the httpSrv.Start(addr) branch does not validate the Host or Origin headers. A malicious website can use DNS rebinding to send browser requests with attacker-controlled Host and Origin values to the loopback listener, initialize an MCP session, list tools, and invoke operations against the GenieACS NBI configured by ACS_URL. Successful exploitation can expose or modify CPE management state, including device reboots, firmware tasks, TR-069 parameter changes, presets, provisions, tags, connection requests, and task operations. The npm wrapper is not affected because it forces TRANSPORT=stdio and does not expose an HTTP listener. This issue is fixed in version 0.3.2.
- Product
- genieacs-mcp
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Aug 25, 2026browse-mcp is a Playwright-based headless-browser MCP server for MCP-capable agents.CVE-2026-55557 · Other software · That1Drifter · reported by GitHubHigh 8.6
browse-mcp is a Playwright-based headless-browser MCP server for MCP-capable agents. Prior to 0.8.2, browser_download writes a fetched response body to join(save_dir, filename) without validating the caller-controlled save_dir, while browser_save_state and browser_load_state honor a caller-controlled path unchanged. A malicious MCP client, or an autonomous agent steered by indirect prompt injection on a visited page, can choose an arbitrary save_dir or state path and a URL whose response body becomes attacker-controlled file contents, allowing writes to any path the process can reach, including ~/.bashrc, autostart entries, or cron files, and potentially leading to host code execution. The force_fetch fallback also uses a raw fetch() that bypasses the BROWSE_MCP_ALLOWED_ORIGINS origin fence. This issue is fixed in version 0.8.2.
- Product
- browse-mcp
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Aug 25, 2026Nextcloud MCP Server is a production-ready MCP server that connects AI assistants to a Nextcloud instance.CVE-2026-55640 · Other software · cbcoutinho · reported by GitHubCritical 9.1
Nextcloud MCP Server is a production-ready MCP server that connects AI assistants to a Nextcloud instance. Prior to 0.117.2, the POST /webhooks/nextcloud endpoint in nextcloud_mcp_server/vector/webhook_receiver.py has no authentication by default because WEBHOOK_SECRET defaults to None and startup validation does not require it. When WEBHOOK_SECRET is unset, handle_nextcloud_webhook() accepts unauthenticated requests. The payload["user"]["uid"] field parsed in nextcloud_mcp_server/vector/webhook_parser.py is attacker-controlled and is used without an authenticated-session cross-check for Qdrant operations, allowing a network attacker to delete or trigger re-indexing of vector embeddings for any user and to destroy the semantic search index by sending forged deletion events. This issue is fixed in version 0.117.2.
- Product
- nextcloud-mcp-server
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Aug 25, 2026mcp-shell is an MCP server for running shell commands securely, auditably, and on demand.CVE-2026-55582 · Other software · sonirico · reported by GitHubHigh 8.4
mcp-shell is an MCP server for running shell commands securely, auditably, and on demand. Prior to 0.6.0, the default security.yaml allows /usr/bin/git, while security.go omits ! from containsShellMetacharacters and containsDangerousShellConstructs and applies no per-executable argument policy. A caller of the shell_exec MCP tool can provide the command argument /usr/bin/git -c alias.pwn=!<arbitrary-command>, causing Git to create a shell alias and execute arbitrary OS commands as the mcp-shell process user. The default Docker image runs as mcpuser with Git installed and secure mode enabled, so the bypass is exploitable in the default deployment without additional authentication beyond MCP connectivity. This issue is fixed in version 0.6.0.
- Product
- mcp-shell
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Aug 25, 2026mcp-shell is an MCP server for running shell commands securely, auditably, and on demand.CVE-2026-55581 · Other software · sonirico · reported by GitHubHigh 8.4
mcp-shell is an MCP server for running shell commands securely, auditably, and on demand. Prior to 0.6.0, the default Docker security.yaml includes /bin/bash in allowed_executables, while security.go validates only the first token and checkBlockedPatternsAndCommands does not reject the shell command-mode flag -c. A caller of the shell_exec MCP tool can provide the command argument `/bin/bash -c <arbitrary-command>`, which passes validation and reaches executor.go, where parseCommand and exec.CommandContext execute the arbitrary command as mcpuser outside the intended allowlist. This issue is fixed in version 0.6.0.
- Product
- mcp-shell
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Aug 25, 2026mcp-shell is an MCP server for running shell commands securely, auditably, and on demand.CVE-2026-55580 · Other software · sonirico · reported by GitHubHigh 8.6
mcp-shell is an MCP server for running shell commands securely, auditably, and on demand. Prior to 0.6.0, config.go initializes Security.Enabled to false, and when MCP_SHELL_SEC_CONFIG_FILE is unset, main.go starts the documented bare-binary deployment without a security policy. SecurityValidator.validateCommand in security.go then short-circuits and allows every command supplied to the shell_exec MCP tool, so an LLM connected over stdio can execute unrestricted OS commands as the mcp-shell process user. The README from-source installation and MCP client configuration omit MCP_SHELL_SEC_CONFIG_FILE, making the insecure state the documented default. This issue is fixed in version 0.6.0.
- Product
- mcp-shell
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Aug 21, 2026CKAN MCP Server is a tool for querying CKAN open data portals.CVE-2026-53509 · Other software · ondata · reported by GitHubMedium 5.7
CKAN MCP Server is a tool for querying CKAN open data portals. A known vulnerability CVE-2026-33060 indicated tools including ckan_package_search and sparql_query that accept a base_url parameter had the risk of making HTTP requests to arbitrary endpoints without restriction. A fix was applied to filter out ip addresses. However, a method to bypass exists prior to version 0.4.106. CKAN MCP Server validates caller-supplied CKAN server URLs by inspecting only the parsed hostname string before issuing outbound HTTP requests. In `src/utils/http.ts`, hostname aliases such as `ip6-localhost` are not equal to `localhost`, are not dotted IPv4 literals, and are not bracketed IPv6 literals, so they pass the SSRF filter but can resolve to loopback when the server performs the request. A remote MCP caller that can invoke CKAN tools with a `server_url` can therefore make the server connect to local or private addresses and, for CKAN-shaped responses, receive response-derived data. The updated fix in version 0.4.106 replaced the single `hostname === 'localhost'` check with a blocked-hostname `Set` covering `ip6-localhost` and `ip6-loopback`.
- Product
- ckan-mcp-server
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Aug 20, 2026Neo.mjs contains a command injection vulnerability within the FileSystemService.mjs component of the ai/mcp/server/file-system MCP server, where the checkSyntaxCVE-2026-18482 · Other software · Klarso GmbH · reported by cret@cert.orgCritical 9.8
Neo.mjs contains a command injection vulnerability within the FileSystemService.mjs component of the ai/mcp/server/file-system MCP server, where the checkSyntax() and runPlaywrightTest() functions unsafely interpolate caller-controlled absolutePath values into shell commands, enabling arbitrary OS command execution when an AI agent is induced to invoke these tools. Commit 88c77fc fixes these vulnerabilities.
- Product
- neo-mjs
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Aug 19, 2026In Splunk MCP Server app versions below 1.2.1, a user who holds the "admin" Splunk role could execute arbitrary commands on the underlying operating system.CVE-2026-76404 · Other software · Splunk · reported by psirt@cisco.comCritical 9.1
In Splunk MCP Server app versions below 1.2.1, a user who holds the "admin" Splunk role could execute arbitrary commands on the underlying operating system. The vulnerability is possible because of missing input validation in the app's credential management component, which deserializes stored data without checking whether the content is of the expected type.
- Product
- Splunk MCP Server app
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Aug 18, 2026The Apify MCP server enables AI agents to extract data from websites using ready-made scrapers, crawlers, and automation tools available on the Apify Store.CVE-2026-50143 · Other software · apify · reported by GitHubHigh 8.1
The Apify MCP server enables AI agents to extract data from websites using ready-made scrapers, crawlers, and automation tools available on the Apify Store. Prior to 0.10.11, getActorMCPServerURL in src/mcp/actors.ts concatenates the trusted Actor standby URL with the attacker-controlled webServerMcpPath from an Actor definition without verifying the resulting origin, allowing a malicious Actor publisher to use a userinfo-style authority value to redirect connectMCPClient to a third-party host. The call-actor, fetch-actor-details, and actor-mcp tool-loading paths pass this URL to transports in src/mcp/client.ts that attach the victim Authorization bearer token, exposing the Apify API token and enabling access to Actors, stored data, and billable compute. A victim must invoke or inspect the attacker-controlled Actor. This issue is fixed in version 0.10.11.
- Product
- apify-mcp-server
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Aug 18, 2026ArcadeDB versions 26.4.2 through 26.7.3 contain an authorization bypass vulnerability in the set_server_setting MCP server-level tool.CVE-2026-75845 · Other software · ArcadeData · reported by VulnCheckMedium 5.3
ArcadeDB versions 26.4.2 through 26.7.3 contain an authorization bypass vulnerability in the set_server_setting MCP server-level tool. SetServerSettingTool.execute() gates only on the global allowAdmin flag and never checks the caller's role, so in an MCP deployment with allowAdmin=true and a non-root allowedUsers set, any authenticated read-only user can invoke set_server_setting to modify server GlobalConfiguration, enabling configuration tampering or denial of service. The issue is fixed in 26.8.1.
- Product
- arcadedb
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Full record and what to do →NVD recordgithub.comvulncheck.com
Aug 14, 2026CKAN MCP Server is a tool for querying CKAN open data portals.CVE-2026-73846 · Other software · ondata · reported by GitHubMedium 6.5
CKAN MCP Server is a tool for querying CKAN open data portals. Prior to 0.4.112, canonicalizeParams in src/utils/cache.ts serializes request parameters with unescaped ampersand, equals-sign, and vertical-bar delimiters, allowing different logical parameter sets used by buildCacheKey to collide and an attacker to prime a shared cache with a response for a victim's distinct query. This issue is fixed in version 0.4.112.
- Product
- ckan-mcp-server
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Aug 14, 2026CKAN MCP Server is a tool for querying CKAN open data portals.CVE-2026-73845 · Other software · ondata · reported by GitHubMedium 5.3
CKAN MCP Server is a tool for querying CKAN open data portals. Prior to 0.4.112, the ckan_get_mqa_quality and ckan_get_mqa_quality_details tools in src/tools/quality.ts use isValidMqaServer to validate the server_url parameter with a prefix-only regular expression for dati.gov.it, allowing suffix-host and URL-userinfo values to target an attacker-controlled host and return a spoofed response. This issue is fixed in version 0.4.112.
- Product
- ckan-mcp-server
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Aug 14, 2026CKAN MCP Server is a tool for querying CKAN open data portals.CVE-2026-73844 · Other software · ondata · reported by GitHubLow 3.7
CKAN MCP Server is a tool for querying CKAN open data portals. Prior to 0.4.112, error paths reflect raw upstream response bodies and internal exception messages back to the caller instead of a sanitized, generic message. When the server is pointed at (or redirected/SSRF'd to) a host that returns a non-CKAN response, or when an internal exception occurs, the caller receives verbatim upstream content and internal detail (hostnames, internal IPs, DB errors, stack fragments). This vulnerability is fixed in 0.4.112.
- Product
- ckan-mcp-server
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Aug 14, 2026The Cortex MCP server (`neuro-cortex-memory`), a cross-platform persistent memory MCP, prior to version 3.17.1 treats the `CLAUDE_PROJECT_DIR` environment variaCVE-2026-49986 · Other software · cdeust · reported by GitHubHigh 7.1
The Cortex MCP server (`neuro-cortex-memory`), a cross-platform persistent memory MCP, prior to version 3.17.1 treats the `CLAUDE_PROJECT_DIR` environment variable — automatically set by Claude Code to the currently open project directory — as a trusted Cortex developer checkout. When the `open_visualization` tool is invoked, `_find_dev_source()` resolves the user's active project directory as a candidate Cortex source root. The only validation performed by `_is_cortex_root()` is a check for the presence of an `mcp_server/` subdirectory and a `ui/unified-viz.html` file. An attacker who places these two marker files in a malicious repository can cause Cortex to execute an arbitrary `mcp_server/server/visualize_bootstrap.py` from that directory via `subprocess.run([sys.executable, ...])`, achieving code execution with the privileges of the victim's local user process. Version 3.17.1 fixes the issue.
- Product
- Cortex
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Aug 13, 2026auth-fetch-mcp is an MCP server that lets AI assistants fetch content from authenticated web pages.CVE-2026-49857 · Other software · ymw0407 · reported by GitHubHigh 7.4
auth-fetch-mcp is an MCP server that lets AI assistants fetch content from authenticated web pages. Version 3.0.1 implements SSRF protection in `assertSafeUrl()` (`src/security.ts`) to block requests to private and loopback addresses. However, the `isPrivateV6()` function fails to detect IPv4-mapped IPv6 loopback addresses in their hex-normalized form. When an attacker supplies a URL such as `http://[::ffff:127.0.0.1]:PORT/`, the Node.js WHATWG URL parser silently normalizes the host to `[::ffff:7f00:1]`. Because `net.isIPv4('7f00:1')` returns `false`, the private-IP check is bypassed and the URL is passed to the browser or HTTP client, allowing the MCP tool to reach loopback services that are supposed to be blocked. The issue is exploitable under default configuration without any special environment variable. Version 3.0.1 patches the issue.
- Product
- auth-fetch-mcp
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Aug 13, 2026@jshookmcp/jshook is an MCP server that gives AI agents tools for JavaScript analysis and security research.CVE-2026-49856 · Other software · vmoranv · reported by GitHubMedium 4.3
@jshookmcp/jshook is an MCP server that gives AI agents tools for JavaScript analysis and security research. In version 0.3.1, he network domain has a central SSRF authorization policy that blocks private, loopback, link-local, and reserved targets unless an explicit authorization object allows private network access. The policy is enforced by raw HTTP/TCP/TLS RTT tools, but the ICMP probe and traceroute tools resolve the target and invoke the native ICMP/traceroute sink directly. An MCP client with access to an active network domain can therefore ask the jshookmcp server to probe internal addresses even when local SSRF access is disabled for the other raw network tools. This exposes an internal reachability and route mapping primitive from the server network position. Version 0.3.2 fixes the issue.
- Product
- jshookmcp
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Aug 11, 2026A caller-supplied X-Grafana-URL request header controls the destination of mcp-grafana's outbound requests, and the grafana_api_request tool lets the caller alsCVE-2026-19516 · Other software · Grafana · reported by security@grafana.comCritical 9.1
A caller-supplied X-Grafana-URL request header controls the destination of mcp-grafana's outbound requests, and the grafana_api_request tool lets the caller also choose the HTTP method, path, and body. Because the destination is not restricted to the configured Grafana instance, a caller can direct requests at internal, loopback, and link-local network services (including metadata endpoints) and read the responses, resulting in server-side request forgery. The fix for CVE-2026-15583 prevented the configured service-account token from being sent to unintended destinations but did not restrict the destinations themselves.
- Product
- Grafana MCP Server
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Aug 5, 2026Incorrect authorization in the aggregation pipeline tool in Amazon AWS Labs DocumentDB MCP Server before 1.0.12 might allow an authenticated MCP client to perfoCVE-2026-18954 · Other software · AWS · reported by ff89ba41-3aa1-4d27-914a-91399e9639e5Medium 5.7
Incorrect authorization in the aggregation pipeline tool in Amazon AWS Labs DocumentDB MCP Server before 1.0.12 might allow an authenticated MCP client to perform inappropriate write operations on the connected database via write-capable aggregation pipeline stages that bypass the read-only mode enforcement logic. To remediate this issue, users should upgrade to version 1.0.12 or later.
- Product
- documentdb-mcp-server
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Full record and what to do →NVD recordaws.amazon.comgithub.com
Aug 5, 2026IBM Langflow OSS 1.0.0 through 1.10.3 Langflow allows remote authenticated attackers to bypass localhost-only restrictions and write arbitrary MCP server configCVE-2026-9077 · Other software · IBM · reported by psirt@us.ibm.comHigh 8.5
IBM Langflow OSS 1.0.0 through 1.10.3 Langflow allows remote authenticated attackers to bypass localhost-only restrictions and write arbitrary MCP server configurations to IDE configuration files on the host system.
- Product
- Langflow OSS
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Aug 5, 2026IBM Langflow OSS 1.0.0 through 1.10.3 Langflow could allow an authenticated attacker to read, modify, or expose sensitive host files via Docker-based MCP serverCVE-2026-17626 · Other software · IBM · reported by psirt@us.ibm.comHigh 8.8
IBM Langflow OSS 1.0.0 through 1.10.3 Langflow could allow an authenticated attacker to read, modify, or expose sensitive host files via Docker-based MCP servers due to incomplete filtering of dangerous Docker volume-mount and device-mapping arguments.
- Product
- Langflow OSS
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Aug 3, 2026Improper restriction of intended endpoints in the RabbitMQ broker connection tools of the Amazon MQ MCP Server (awslabs.amazon-mq-mcp-server) before 2.0.24 may CVE-2026-18655 · Other software · AWS · reported by ff89ba41-3aa1-4d27-914a-91399e9639e5High 7.1
Improper restriction of intended endpoints in the RabbitMQ broker connection tools of the Amazon MQ MCP Server (awslabs.amazon-mq-mcp-server) before 2.0.24 may allow a remote unauthenticated actor (via prompt injection) to obtain Amazon MQ for RabbitMQ broker credentials or OAuth access tokens sent to a crafted endpoint controlled through a broker hostname introduced in the MCP client context. To remediate this issue, users should upgrade to version 2.0.24.
- Product
- amazon-mq-mcp-server
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Full record and what to do →NVD recordaws.amazon.comgithub.com
Jul 31, 2026gemini-bridge is a lightweight MCP server bridging AI agents to Google's Gemini AI via the official CLI.CVE-2026-54785 · Other software · eLyiN · reported by GitHubMedium 6.2
gemini-bridge is a lightweight MCP server bridging AI agents to Google's Gemini AI via the official CLI. From 1.0.0 until 1.3.1, consult_gemini_with_files in inline mode read any file path supplied in the files argument without confining it to the working directory, then forwarded the contents to the Gemini CLI. Because the caller also controls query, the file contents are echoed back through the Gemini round-trip (and sent to Google), making this an arbitrary local file read. This issue is fixed in version 1.3.1.
- Product
- gemini-bridge
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Jul 28, 2026GitHub MCP Server is GitHub's official MCP Server.CVE-2026-47427 · Other software · github · reported by GitHubHigh 7.5
GitHub MCP Server is GitHub's official MCP Server. Prior to 1.1.0, the CompletionsHandler function in pkg/github/server.go accesses params.Ref without first checking whether it is nil, so a completion/complete request with a missing or empty ref field triggers a nil pointer dereference and a Go runtime panic; because the crash occurs before any authentication or token validation, any unauthenticated client able to send JSON-RPC messages can crash the server, resulting in a complete denial of service. This issue is fixed in version 1.1.0.
- Product
- github-mcp-server
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Jul 28, 2026Improper exposure of the MCP server in alibabacloud-rds-openapi-mcp-server allows remote attackers to invoke exposed MCP tools via network access to an MCP endpCVE-2026-9680 · Other software · Alibaba · reported by alibaba-cna@list.alibaba-inc.comMedium 5.8
Improper exposure of the MCP server in alibabacloud-rds-openapi-mcp-server allows remote attackers to invoke exposed MCP tools via network access to an MCP endpoint listening on all network interfaces by default.
- Product
- Alibaba Cloud RDS OpenAPI MCP Server
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Jul 23, 2026APIFold reads an OpenAPI 3.x or Swagger 2.x specification and generates a live, production-ready MCP server endpoint.CVE-2026-47769 · Other software · Work90210 · reported by GitHubMedium 5.3
APIFold reads an OpenAPI 3.x or Swagger 2.x specification and generates a live, production-ready MCP server endpoint. Prior to commit 7f19b52280f414f57af2b79a95333d1c8fbeece5, the `/webhooks/:serverSlug/:eventName` endpoint accepts arbitrary unauthenticated JSON and stores it in Redis and the `webhook_events` PostgreSQL table without any signature check or authentication requirement. The root cause is that `createWebhookRouter` is called at `server.ts:188` without a `validators` map, so `receivers.ts:80`'s optional-chaining guard evaluates to `undefined` and the signature-validation block (`receiver.ts:81–95`) is unconditionally skipped. Any unauthenticated network client that knows a valid server slug can inject arbitrary payloads, which are subsequently served as trusted resource state to legitimate MCP clients. Commit 7f19b52280f414f57af2b79a95333d1c8fbeece5 patches the issue.
- Product
- APIFold
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Jul 23, 2026Improper handling of an initialization failure in AWS API MCP Server from 0.2.13 through 1.3.46 might allow an actor to bypass the user-configured security poliCVE-2026-16584 · Other software · AWS · reported by ff89ba41-3aa1-4d27-914a-91399e9639e5High 7.3
Improper handling of an initialization failure in AWS API MCP Server from 0.2.13 through 1.3.46 might allow an actor to bypass the user-configured security policy and execute AWS API operations that the policy was set to deny or gate. When initialization of the security policy enforcement data fails at server startup, the policy check is skipped for the lifetime of the process. IAM permissions on the configured credentials remain in effect and are unaffected. To remediate this issue, users should upgrade to version 1.3.47.
- Product
- aws-api-mcp-server
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Full record and what to do →NVD recordaws.amazon.comgithub.com
Jul 21, 2026MCP-for-Stata is an MCP server for Stata to integrate Stata into an agent.CVE-2026-47708 · Other software · SepineTam · reported by GitHubCritical 9.3
MCP-for-Stata is an MCP server for Stata to integrate Stata into an agent. Prior to version 1.17.3, the `log_file_name` parameter in the `stata_do` API and CLI is directly interpolated into a Stata command string without sanitization. The security guard (`GuardValidator`) only scans the do-file content but does not validate this parameter. An attacker can inject arbitrary Stata commands (including `shell`, `python`, `erase`, etc.) by crafting a malicious `log_file_name` containing quotes, newlines, or Stata command separators. Version 1.17.3 contains a patch for the issue.
- Product
- stata-mcp
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Jul 20, 2026WhatsApp MCP Server is a Model Context Protocol (MCP) server for WhatsApp, enabling Claude to read and send WhatsApp messages.CVE-2026-46555 · Other software · verygoodplugins · reported by GitHubHigh 7.7
WhatsApp MCP Server is a Model Context Protocol (MCP) server for WhatsApp, enabling Claude to read and send WhatsApp messages. Prior to version 0.2.1, the `whatsapp-bridge` HTTP API listens on `127.0.0.1:8080` without authentication and without Host header validation, and the `/api/send` endpoint accepts an absolute `media_path` parameter without confining it to a safe directory. Combined, these issues allow any local process running as the same user as the bridge to send WhatsApp messages from the paired account without authorization; the same caller to read arbitrary files readable by the user (e.g. SSH private keys, browser session data, source code, dotfiles) and exfiltrate them as WhatsApp document attachments; and/or a remote attacker to trigger the same operations via DNS rebinding from a webpage the user visits, since no Host header validation is performed. In MCP environments, "local caller" extends beyond processes the user explicitly launched — sibling MCP servers, IDE extensions, and tool-triggered flows running in the user's session can act as the effective caller. This issue is fixed in whatsapp-mcp v0.2.1 and corresponding Docker images / release artifacts. Users sho
- Product
- whatsapp-mcp
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Jul 17, 2026IBM Langflow OSS 1.0.0 through 1.10.0 Langflow could allow remote code execution due to incomplete validation enforcement on MCP server configuration files.CVE-2026-7755 · Other software · IBM · reported by psirt@us.ibm.comHigh 8.8
IBM Langflow OSS 1.0.0 through 1.10.0 Langflow could allow remote code execution due to incomplete validation enforcement on MCP server configuration files.
- Product
- Langflow OSS
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Jul 17, 2026ForgeCode (tailcallhq/forgecode), an AI pair-programming CLI, automatically loads and executes the MCP servers defined in a repository's .mcp.json file on startCVE-2026-57860 · Other software · tailcallhq · reported by VulnCheckHigh 8.4
ForgeCode (tailcallhq/forgecode), an AI pair-programming CLI, automatically loads and executes the MCP servers defined in a repository's .mcp.json file on startup without user confirmation. A malicious repository can supply a crafted .mcp.json whose mcpServers entries specify arbitrary command and args values (for example, command: bash with args: ['-c', 'touch /tmp/pwned']). When a user runs the forge CLI inside a cloned untrusted repository, the specified commands are spawned with the invoking user's privileges, resulting in arbitrary code execution. This provides a reliable initial-access and persistence primitive against developers who evaluate untrusted repositories with ForgeCode.
- Product
- forgecode
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Jul 16, 2026The Apify MCP server enables AI agents to extract data from websites using ready-made scrapers, crawlers, and automation tools available on the Apify Store.CVE-2026-46341 · Other software · apify · reported by GitHubMedium 6.1
The Apify MCP server enables AI agents to extract data from websites using ready-made scrapers, crawlers, and automation tools available on the Apify Store. Prior to 0.9.21, the fetch-apify-docs tool in src/tools/common/fetch_apify_docs.ts validates allowlisted documentation domains with String.startsWith() rather than URL hostname comparison, allowing attacker-controlled URLs such as `https://docs.apify.com.evil.com/` and `https://docs.apify.com@evil.com/` to pass the ALLOWED_DOC_DOMAINS check and return arbitrary fetched content to the LLM. This issue is fixed in version 0.9.21.
- Product
- apify-mcp-server
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Jul 15, 2026LiteLLM 1.18.10 contains a remote code execution vulnerability in its MCP server creation functionality.CVE-2026-30623 · Other software · reported by MITRECritical 9.8
LiteLLM 1.18.10 contains a remote code execution vulnerability in its MCP server creation functionality. The application allows users to add MCP servers via a JSON configuration specifying arbitrary command and args values. LiteLLM executes these values on the host without validation, enabling attackers to run arbitrary operating system commands. Successful exploitation may result in remote code execution with the privileges of the LiteLLM process.
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Full record and what to do →NVD recorddocs.litellm.aigithub.com
Jul 15, 2026n8n-MCP is an MCP server that provides AI assistants access to n8n node documentation, properties, and operations.CVE-2026-55608 · Other software · czlonkowski · reported by GitHubMedium 4.2
n8n-MCP is an MCP server that provides AI assistants access to n8n node documentation, properties, and operations. Prior to 2.57.4, multi-tenant HTTP mode with ENABLE_MULTI_TENANT=true could allow an authenticated tenant to access default-scope workflow_versions backups instead of being confined to the tenant scope, exposing or deleting workflow-version backups from prior single-tenant deployments or migrations. This issue is fixed in version 2.57.4.
- Product
- n8n-mcp
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Jul 15, 2026n8n-MCP is an MCP server that provides AI assistants access to n8n node documentation, properties, and operations.CVE-2026-54052 · Other software · czlonkowski · reported by GitHubCritical 9.9
n8n-MCP is an MCP server that provides AI assistants access to n8n node documentation, properties, and operations. Prior to 2.56.1, in HTTP mode with multi-tenancy enabled through ENABLE_MULTI_TENANT=true, n8n-mcp's local workflow version history backups were not isolated per tenant, allowing an authenticated tenant to read workflow version snapshots belonging to other tenants and delete or destroy other tenants' stored backups, including full node definitions, credential references, and authorization headers. This issue is fixed in version 2.56.1.
- Product
- n8n-mcp
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Jul 15, 2026A confused-deputy flaw in Grafana MCP Server allows an unauthenticated remote attacker to exfiltrate the server's environment-configured Grafana service-accountCVE-2026-15583 · Other software · Grafana · reported by security@grafana.comHigh 8.6
A confused-deputy flaw in Grafana MCP Server allows an unauthenticated remote attacker to exfiltrate the server's environment-configured Grafana service-account token by supplying a crafted X-Grafana-URL request header. This also enables SSRF against arbitrary internal services, including cloud metadata endpoints.
- Product
- Grafana MCP Server
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Jul 14, 2026AWS HealthLake MCP Server (awslabs.healthlake-mcp-server) is a Model Context Protocol server that enables AI assistants to interact with AWS HealthLake FHIR datCVE-2026-15643 · Other software · AWS · reported by ff89ba41-3aa1-4d27-914a-91399e9639e5Critical 9.2
AWS HealthLake MCP Server (awslabs.healthlake-mcp-server) is a Model Context Protocol server that enables AI assistants to interact with AWS HealthLake FHIR datastores. A server-side request forgery in the pagination handling component in AWS awslabs.healthlake-mcp-server before 0.0.14 on all platforms might allow a remote authenticated user to exfiltrate AWS temporary security credentials to an arbitrary endpoint via a crafted next_token parameter. The server does not validate that pagination URLs point back to the expected HealthLake endpoint, allowing an actor to redirect subsequent requests to an actor-controlled server. Its recommended to upgrade to version 0.0.14 or later.
- Product
- awslabs.healthlake-mcp-server
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Full record and what to do →NVD recordaws.amazon.compypi.org
Jul 13, 2026MCP Appium is an MCP server that provides AI assistants with tools to automate mobile app testing on Android and iOS.CVE-2026-58500 · Other software · appium · reported by GitHubHigh 8.2
MCP Appium is an MCP server that provides AI assistants with tools to automate mobile app testing on Android and iOS. In versions prior to 1.85.10, the createLocatorGeneratorUI function interpolates attacker-controlled element attributes — text, content-desc, resource-id, and locator selector values — directly into an HTML template literal without any HTML or JavaScript context escaping. An attacker who controls the UI of the app under test can inject arbitrary HTML and JavaScript into the MCP UI resource returned by the generate_locators tool. When a victim's MCP client renders this resource, the injected script executes and can invoke arbitrary MCP tools via window.parent.postMessage, leading to unauthorized MCP tool execution such as taking screenshots, reading page source, or any other registered capability. This issue has been fixed in version 1.85.10.
- Product
- appium-mcp
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Jul 10, 2026MCP Server Kubernetes before 3.9.0 contains an argument injection vulnerability in structured tools (kubectl_get, kubectl_describe, kubectl_delete) that allows CVE-2026-61459 · Other software · Flux159 · reported by VulnCheckCritical 9.3
MCP Server Kubernetes before 3.9.0 contains an argument injection vulnerability in structured tools (kubectl_get, kubectl_describe, kubectl_delete) that allows attackers to bypass the assertNoDangerousFlags security check by supplying resourceType and name parameters with leading dashes. Attackers can inject the --server flag to redirect kubectl commands to an attacker-controlled API server, causing the operator's bearer token to be transmitted externally and enabling full cluster compromise.
- Product
- mcp-server-kubernetes
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Jul 9, 2026DeepSeek MCP Server is an MCP server for DeepSeek V4.CVE-2026-55605 · Other software · arikusi · reported by GitHubMedium 5.3
DeepSeek MCP Server is an MCP server for DeepSeek V4. Starting in version 1.4.2 and prior to version 1.8.0, the self-hosted HTTP transport of `@arikusi/deepseek-mcp-server` exposes `POST /mcp` without any authentication: `createMcpExpressApp` is called without an `authProvider` and no middleware guards the route, so any network-reachable client can issue an unauthenticated `initialize` request and obtain a valid MCP session identifier. In reproduced testing against commit `5e1302171e99`, an unauthenticated client was able to initialize a session, enumerate tools, and invoke the local `deepseek_sessions` tool with no credentials. The same unauthenticated session also exposes `deepseek_chat`, whose handler uses the server-side `DEEPSEEK_API_KEY` when self-hosted deployments configure one. This issue applies to self-hosted HTTP mode, not the separately documented hosted BYOK endpoint in `README.md`, which expects an `Authorization: Bearer ...` header. Upstream self-hosted container assets enable HTTP mode by default (`Dockerfile`) and publish port `3000` (`docker-compose.yml`). Version 1.8.0 contains a patch for this issue.
- Product
- deepseek-mcp-server
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Jul 9, 2026DeepSeek MCP Server is an MCP server for DeepSeek V4.CVE-2026-55604 · Other software · arikusi · reported by GitHubHigh 8.6
DeepSeek MCP Server is an MCP server for DeepSeek V4. Starting in version 1.4.2 and prior to version 1.7.0, the process-global `SessionStore` accepts caller-supplied `session_id` values without binding them to any authenticated principal or transport session. An attacker can enumerate active session IDs via `deepseek_sessions`, then reuse a victim-controlled `session_id` in `deepseek_chat` to retrieve and continue the victim's conversation context. Version 1.7.0 contains a patch.
- Product
- deepseek-mcp-server
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Where this comes from: the exploited list is CISA’s Known Exploited Vulnerabilities catalog. Everything else is the whole National Vulnerability Database, where each record is published by the team that found the bug (Wordfence, Patchstack, WPScan, the vendors themselves and others); we show who. Exploit odds are FIRST’s EPSS, updated daily. Titles and categories are ours, so check the linked record before acting on a detail. For a write-up of the big ones, see our advisories. Every vendor, and every WordPress plugin and theme with a recorded flaw, also has its own page. All of it is free to reuse as JSON, CSV or RSS.
Weekly security brief
The flaws that hit local websites, every Friday.
One short email: what got exploited this week, which WordPress plugins broke, and what to check. Unsubscribe in one click.
Tell us what you're building.
A website, your marketing, a security check, an app, or the thing you've been running out of a spreadsheet for three years. A few lines is plenty.
Not ready to talk yet? Run the free website check and see what Google sees.