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.
934 results · page 10 of 19
Jul 12, 2026A security vulnerability has been detected in alioshr memory-bank-mcp up to 0.2.1/3.1.CVE-2026-15524 · Other software · alioshr · reported by VulDBLow 1.9
A security vulnerability has been detected in alioshr memory-bank-mcp up to 0.2.1/3.1. This affects an unknown part of the file list-project-files-validation-factory.ts. Such manipulation of the argument projectName leads to path traversal. Local access is required to approach this attack. The exploit has been disclosed publicly and may be used. The project was informed of the problem early through an issue report but has not responded yet.
- Product
- memory-bank-mcp
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Jul 12, 2026A security flaw has been discovered in tugcantopaloglu godot-mcp 2.0.0.CVE-2026-15522 · Other software · tugcantopaloglu · reported by VulDBLow 1.9
A security flaw has been discovered in tugcantopaloglu godot-mcp 2.0.0. Affected by this vulnerability is the function validatePath of the file build/index.js of the component run_project. The manipulation of the argument projectPath results in path traversal. Attacking locally is a requirement. The exploit has been released to the public and may be used for attacks. Upgrading to version 3.0.0 addresses this issue. The patch is identified as eb63add552aa4bd9205395cf91b40654654a3cf2. It is suggested to upgrade the affected component.
- Product
- godot-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.
Jul 9, 2026A security vulnerability has been detected in aerostackdev aerostack-mcp up to 6315dfde7df0a15aaf743f88d91347115e09ba23.CVE-2026-15189 · Other software · aerostackdev · reported by VulDBMedium 5.3
A security vulnerability has been detected in aerostackdev aerostack-mcp up to 6315dfde7df0a15aaf743f88d91347115e09ba23. Affected by this issue is the function upload_media of the component mcp-whatsapp. Such manipulation of the argument media_url leads to server-side request forgery. The attack may be launched remotely. This product operates on a rolling release basis, ensuring continuous delivery. Consequently, there are no version details for either affected or updated releases. The project was informed of the problem early through an issue report but has not responded yet.
- Product
- aerostack-mcp
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Jul 8, 2026A security vulnerability has been detected in tumf mcp-text-editor up to 1.0.2.CVE-2026-15138 · Other software · tumf · reported by VulDBLow 2.1
A security vulnerability has been detected in tumf mcp-text-editor up to 1.0.2. This issue affects the function _validate_file_path of the file mcp_text_editor/text_editor.py. Such manipulation of the argument file_path leads to path traversal. The attack can be launched remotely. The exploit has been disclosed publicly and may be used. The vendor closed the GitHub issue for this vulnerability without any explanation.
- Product
- mcp-text-editor
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Jul 7, 2026Serena is a powerful MCP toolkit for coding that provides semantic retrieval and editing capabilities.CVE-2026-49471 · Other software · oraios · reported by GitHubHigh 8.3
Serena is a powerful MCP toolkit for coding that provides semantic retrieval and editing capabilities. Prior to v1.5.2, Serena's built-in web dashboard exposes an unauthenticated Flask API on a fixed, predictable port, with no authentication, no CSRF protection, and no Host header validation. A DNS rebinding attack allows a malicious webpage to reach this API from any browser and write arbitrary content to the agent's persistent memory store, which the agent reads and acts on autonomously. Combined with execute_shell_command using shell=True, this creates a remote code execution chain requiring only that the victim visit a malicious webpage while Serena is running. This issue is fixed in version v1.5.2.
- Product
- serena
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Jul 6, 2026Improper Neutralization of Special Elements in the metrics-service retention policy management component in Amazon mcp-gateway-registry before 1.0.13 might alloCVE-2026-14471 · Other software · AWS · reported by ff89ba41-3aa1-4d27-914a-91399e9639e5High 8.6
Improper Neutralization of Special Elements in the metrics-service retention policy management component in Amazon mcp-gateway-registry before 1.0.13 might allow an authenticated remote user to execute arbitrary SQL queries via a crafted table_name value that is interpolated into SQL statements in identifier position. To remediate this issue, users should upgrade to version 1.0.13 or later.
- Product
- MCP Gateway & Registry
- 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 5, 2026A flaw has been found in AIAnytime Awesome-MCP-Server up to a884bb51bcd99e08e14fd712c749d55d9d9a13ab.CVE-2026-14748 · Other software · AIAnytime · reported by VulDBLow 2.1
A flaw has been found in AIAnytime Awesome-MCP-Server up to a884bb51bcd99e08e14fd712c749d55d9d9a13ab. Affected by this issue is some unknown functionality of the file mcp-wiki/src/mcp_wiki/server.py of the component mcp-wiki/wiki-summary. This manipulation of the argument url causes server-side request forgery. The attack may be initiated remotely. The exploit has been published and may be used. This product uses a rolling release model to deliver continuous updates. As a result, specific version information for affected or updated releases is not available. The project was informed of the problem early through an issue report but has not responded yet.
- Product
- Awesome-MCP-Server
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Jul 5, 2026A flaw has been found in zcaceres markdownify-mcp up to 1.1.0.CVE-2026-14702 · Other software · zcaceres · reported by VulDBLow 1.1
A flaw has been found in zcaceres markdownify-mcp up to 1.1.0. This impacts the function saveToTempFile of the file src/Markdownify.ts of the component webpage-to-markdown/youtube-to-markdown/bing-search-to-markdown. This manipulation causes insufficiently random values. The attack is restricted to local execution. A high degree of complexity is needed for the attack. The exploitability is said to be difficult. The exploit has been published and may be used. The pull request to fix this issue awaits acceptance.
- Product
- markdownify-mcp
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Jul 5, 2026A weakness has been identified in zcaceres markdownify-mcp up to 1.1.0.CVE-2026-14699 · Other software · zcaceres · reported by VulDBMedium 4.8
A weakness has been identified in zcaceres markdownify-mcp up to 1.1.0. The affected element is the function assertPathAllowed of the file src/Markdownify.ts. Executing a manipulation can lead to symlink following. The attack can only be executed locally. The pull request to fix this issue awaits acceptance.
- Product
- markdownify-mcp
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Jul 3, 2026A vulnerability exists in the Kong Konnect Model Context Protocol (MCP) server prior to version 1.0.0, which could allow a remote attacker to perform an indirecCVE-2026-13341 · Other software · KongHQ · reported by 02762ae7-200e-4b20-9b2b-a77d5b8fc4cbHigh 7.4
A vulnerability exists in the Kong Konnect Model Context Protocol (MCP) server prior to version 1.0.0, which could allow a remote attacker to perform an indirect prompt injection attack and execute unintended API requests.
- Product
- mcp-konnect
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Jul 2, 2026fast-mcp-telegram is a Telegram MCP Server.CVE-2026-52830 · Other software · leshchenko1979 · reported by GitHubCritical 9.4
fast-mcp-telegram is a Telegram MCP Server. Prior to 0.19.1, fast-mcp-telegram validates HTTP Bearer tokens by joining the raw token string into a session-file path. The verifier rejects the exact reserved token telegram, but it does not reject path separators or normalize the path before checking whether the session file exists. A remote HTTP client can therefore authenticate as the default legacy session with a token such as ../fast-mcp-telegram/telegram when the documented default session file ~/.config/fast-mcp-telegram/telegram.session exists. This bypasses the reserved session name control that is intended to prevent HTTP multi-user sessions from colliding with the default stdio or legacy account. With account-prefixed MCP tools enabled, the attacker still sees and calls the prefixed tools for the default account, so the prefix middleware does not stop the session selection bypass. This vulnerability is fixed in 0.19.1.
- Product
- fast-mcp-telegram
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Full record and what to do →NVD recordgithub.comweb.archive.org
Jul 1, 2026In the Linux kernel, the following vulnerability has been resolved: pinctrl: mcp23s08: Initialize mcp->dev and mcp->addr before regmap init Regmap initializatCVE-2026-53344 · Computers, phones & browsers · Linux · reported by 416baaa9-dc9f-4396-8d5f-8c081fb06d67Medium 5.5
In the Linux kernel, the following vulnerability has been resolved: pinctrl: mcp23s08: Initialize mcp->dev and mcp->addr before regmap init Regmap initialization triggers regcache_maple_populate() which attempts SPI read to populate cache. SPI read requires mcp->dev and mcp->addr to be set, without them, NULL pointer dereference occurs during probe. Move initialization before mcp23s08_spi_regmap_init() call.
- Product
- Linux
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Full record and what to do →NVD recordgit.kernel.orggit.kernel.org
Jul 1, 2026Royal MCP: Does not perform capability checks on the majority of its MCP tools after token authenticationCVE-2026-10750 · WordPress plugins & themes · reported by WPScanHigh 8.1
The Royal MCP WordPress plugin before 1.4.26 does not perform capability checks on the majority of its MCP tools after token authentication, allowing authenticated users with a low-privileged role such as Subscriber to read private content, enumerate all users and their roles, and create, modify, or delete content owned by other users.
- Product
- Royal MCP
- Fixed in
- 1.4.26
- What to do
- Update Royal MCP to 1.4.26 or newer.
Jun 30, 2026Presenton before 0.8.8-beta bundles an MCP server that, on server/Docker deployments configured with session authentication (AUTH_USERNAME/AUTH_PASSWORD), is reCVE-2026-58446 · Other software · presenton · reported by VulnCheckMedium 6.9
Presenton before 0.8.8-beta bundles an MCP server that, on server/Docker deployments configured with session authentication (AUTH_USERNAME/AUTH_PASSWORD), is reachable unauthenticated at /mcp because the nginx front-end does not apply the auth_request gate to that path and the MCP server auto-mints a valid internal session token for the configured user. A remote unauthenticated attacker can invoke MCP tools such as generate_presentation, performing authenticated application actions, consuming the operators configured LLM API keys, and creating presentations in the operators instance. The Electron desktop build is not affected (MCP disabled).
- Product
- presenton
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Jun 30, 2026IBM Langflow OSS 1.0.0 through 1.9.6 could allow unauthenticated attackers to access protected MCP project resources and execute MCP operations due to improper CVE-2026-7663 · Other software · IBM · reported by psirt@us.ibm.comCritical 9.1
IBM Langflow OSS 1.0.0 through 1.9.6 could allow unauthenticated attackers to access protected MCP project resources and execute MCP operations due to improper authorization enforcement in the Streamable MCP transport endpoint.
- Product
- Langflow OSS
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Jun 30, 2026DeepTutor before version 1.4.10 contains an authorization bypass vulnerability that allows low-privilege users to invoke unrestricted MCP tools due to the allowCVE-2026-58168 · Other software · HKUDS · reported by VulnCheckHigh 7.7
DeepTutor before version 1.4.10 contains an authorization bypass vulnerability that allows low-privilege users to invoke unrestricted MCP tools due to the allowed_mcp_tools function returning None instead of a denied result when mcp_tools is omitted from a user's grant in deeptutor/multi_user/tool_access.py. Attackers or prompt-injected content acting within a user session can enumerate and invoke any configured MCP tool, including filesystem, shell, and browser servers, gaining unauthorized access to sensitive deployment resources.
- Product
- DeepTutor
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Jun 29, 2026A path traversal vulnerability exists in the HTTP tool URL builder of googleapis/mcp-toolbox.CVE-2026-11720 · Computers, phones & browsers · Google · reported by cve-coordination@google.comCritical 9.3
A path traversal vulnerability exists in the HTTP tool URL builder of googleapis/mcp-toolbox. When constructing downstream API requests, the URL builder substitutes user-controlled pathParams into the configured tool path and parses the resulting string as a relative URL. While it checks that the input does not alter the scheme, host, or user info, it relies on ResolveReference for the final URL resolution. Because dot segments (../) are normalized during this resolution step, an attacker can supply path parameters containing directory traversal sequences to escape the operator-configured path scope. This allows the client to coerce the toolbox into making requests to unintended endpoints on the same target host while forwarding the toolbox's configured credentials (e.g., bypassing a restricted path like /api/v1/users/{{.id}} to reach /admin/secrets).
- Product
- MCP Toolbox for Databases (googleapis/mcp-toolbox)
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Jun 27, 2026Flowise before 3.1.3 validates Custom MCP stdio environment variables against a denylist using a case-sensitive comparison, so on Windows, where environment namCVE-2026-58057 · Other software · Flowise · reported by VulnCheckLow 2.3
Flowise before 3.1.3 validates Custom MCP stdio environment variables against a denylist using a case-sensitive comparison, so on Windows, where environment names are case-insensitive, supplying 'node_options' bypasses the NODE_OPTIONS denylist entry. An authenticated user who can configure a Custom MCP node can thereby inject NODE_OPTIONS --require and execute arbitrary code in the Flowise server context.
- Product
- Flowise
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Jun 26, 2026GitHub MCP Server is GitHub's official MCP Server.CVE-2026-48529 · Other software · github · reported by GitHubMedium 6
GitHub MCP Server is GitHub's official MCP Server. From 0.22.0 until 1.1.2, when running in HTTP mode with --lockdown-mode enabled, the RepoAccessCache is implemented as a process-global singleton initialized with the first authenticated user's GraphQL client. All subsequent requests from different users share this singleton and their lockdown-related GraphQL queries are executed using the first user's credentials. The singleton is never updated to reflect later users' tokens. This vulnerability is fixed in 1.1.2.
- Product
- github-mcp-server
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Jun 26, 2026In JetBrains YouTrack before 2026.2.16593 project settings disclosure via the MCP was possibleCVE-2026-57922 · Other software · JetBrains · reported by cve@jetbrains.comLow 3.1
In JetBrains YouTrack before 2026.2.16593 project settings disclosure via the MCP was possible
- Product
- YouTrack
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Jun 25, 2026Flowise before 3.0.6 (affected versions 2.2.7-patch.1 and earlier) contains an unsandboxed remote code execution vulnerability in the Custom MCP feature, which CVE-2025-71336 · Other software · Flowise · reported by VulnCheckCritical 9.3
Flowise before 3.0.6 (affected versions 2.2.7-patch.1 and earlier) contains an unsandboxed remote code execution vulnerability in the Custom MCP feature, which is designed to execute OS commands such as launching local MCP servers. Because Flowise's authentication and authorization model is minimal and lacks role-based access control, and the default installation runs without authentication unless FLOWISE_USERNAME and FLOWISE_PASSWORD are set, an attacker can send a crafted JSON payload with the header 'x-request-from: internal' to the /api/v1/node-load-method/customMCP endpoint to execute arbitrary OS commands, resulting in complete compromise of the platform container or server.
- Product
- Flowise
- 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
Jun 25, 2026Royal MCP: Missing AuthorizationCVE-2026-54842 · WordPress plugins & themes · reported by PatchstackHigh 8.1
Missing Authorization vulnerability in Royal Plugins Royal MCP allows Exploiting Incorrectly Configured Access Control Security Levels. This issue affects Royal MCP: from n/a through 1.4.25.
- Product
- Royal MCP
- Affected
- up to 1.4.25
- What to do
- Affects up to 1.4.25. Update Royal MCP to the newest version and check its changelog mentions this fix; if there isn’t one yet, deactivate it until there is.
Jun 25, 2026In the Linux kernel, the following vulnerability has been resolved: 6lowpan: fix off-by-one in multicast context address compression The second memcpy in lowpCVE-2026-53263 · Computers, phones & browsers · Linux · reported by 416baaa9-dc9f-4396-8d5f-8c081fb06d67Medium 5.5
In the Linux kernel, the following vulnerability has been resolved: 6lowpan: fix off-by-one in multicast context address compression The second memcpy in lowpan_iphc_mcast_ctx_addr_compress() uses &data[1] as destination and &ipaddr->s6_addr[11] as source, but both should be offset by one: &data[2] and &ipaddr->s6_addr[12] respectively. This off-by-one has two consequences: 1. data[1] is overwritten with s6_addr[11], corrupting the RIID field in the compressed multicast address 2. data[5] is never written, so uninitialized kernel stack memory is transmitted over the network via lowpan_push_hc_data(), leaking kernel stack contents The correct inline data layout must match what the decompression function lowpan_uncompress_multicast_ctx_daddr() expects: data[0..1] = s6_addr[1..2] (flags/scope + RIID) data[2..5] = s6_addr[12..15] (group ID) Also zero-initialize the data array as a defensive measure against similar bugs in the future.
- Product
- Linux
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Full record and what to do →NVD recordgit.kernel.orggit.kernel.org
Jun 24, 2026Chrome DevTools for agents (chrome-devtools-mcp) lets your coding agent control and inspect a live Chrome browser.CVE-2026-53766 · Other software · ChromeDevTools · reported by GitHubMedium 6.1
Chrome DevTools for agents (chrome-devtools-mcp) lets your coding agent control and inspect a live Chrome browser. From 0.24.0 until 1.1.0, McpContext.validatePath() enforces workspace roots by checking whether path.resolve(filePath) textually falls under one of the configured root paths. path.resolve() does not canonicalize symbolic links. As a result, a symlink inside a configured workspace root can point to a file outside that root, pass validation, and then be followed by downstream file read/write operations. This bypass applies even when the MCP client correctly declares the roots capability with a non-empty list. It is separate from the documented legacy behavior where missing roots capability allows all paths. The practical impact is a workspace-boundary bypass. In the write direction, filePath-writing tools can overwrite out-of-root files through an in-root symlink. In the read direction, upload_file can read through the symlink and send the file to the currently selected web page. This vulnerability is fixed in 1.1.0.
- Product
- chrome-devtools-mcp
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Jun 24, 2026Chrome DevTools for agents (chrome-devtools-mcp) lets your coding agent control and inspect a live Chrome browser.CVE-2026-53765 · Other software · ChromeDevTools · reported by GitHubMedium 6.1
Chrome DevTools for agents (chrome-devtools-mcp) lets your coding agent control and inspect a live Chrome browser. From 0.20.0 until 1.1.0, The chrome-devtools-mcp daemon writes its PID file with fs.writeFileSync() to a deterministic runtime path. On typical macOS environments, and on Linux sessions where $XDG_RUNTIME_DIR is unset, that runtime path falls back to /tmp/chrome-devtools-mcp-<uid>/daemon.pid. Because the write does not use O_NOFOLLOW, a local low-privilege user on the same POSIX host can pre-create /tmp/chrome-devtools-mcp-<victim_uid>/daemon.pid as a symlink to a file writable by the victim. When the victim later starts daemon mode, fs.writeFileSync() follows the symlink and truncates the target file to the daemon PID string. This vulnerability is fixed in 1.1.0.
- Product
- chrome-devtools-mcp
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Jun 24, 2026A missing permission check in Jenkins MCP Server Plugin 0.177.v629fdb_2557fe and earlier allows attackers with Item/Read permission to read the Pipeline replay CVE-2026-57300 · Websites & servers · Jenkins Project · reported by jenkinsci-cert@googlegroups.comMedium 4.3
A missing permission check in Jenkins MCP Server Plugin 0.177.v629fdb_2557fe and earlier allows attackers with Item/Read permission to read the Pipeline replay scripts of jobs they can access.
- Product
- Jenkins MCP Server Plugin
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Jun 23, 2026A flaw was found in foreman-mcp-server.CVE-2026-9073 · Other software · Red Hat · reported by Red HatMedium 6.2
A flaw was found in foreman-mcp-server. This component utilizes two distinct logging mechanisms that can expose sensitive session and authentication data. One mechanism logs session identifiers, which are treated as authentication credentials, at an informational level. The other, when debug logging is enabled, incompletely sanitizes HTTP request headers, leading to the cleartext logging of sensitive information such as authorization tokens and API keys. This vulnerability can result in a confidentiality breach, as sensitive authentication data is persisted in plain text within container logs, increasing the risk if logs are forwarded to a centralized platform.
- Product
- Red Hat Satellite 6.18
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Full record and what to do →NVD recordaccess.redhat.comaccess.redhat.com
Jun 23, 2026A flaw was found in the foreman-mcp-server.CVE-2026-12112 · Other software · Red Hat · reported by Red HatHigh 7.8
A flaw was found in the foreman-mcp-server. A session management vulnerability in the MCP Server allows unauthenticated attackers to hijack active administrative sessions due to an improper cache of authenticated client connections, by trusting a non-secret session ID without re-validating authentication tokens and by logging all newly created session IDs to standard logs. This issue can result in privilege escalation and infrastructure-wide code execution.
- Product
- Red Hat Satellite 6.18
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Full record and what to do →NVD recordaccess.redhat.comaccess.redhat.com
Jun 23, 2026Flowise before 3.1.2 contains multiple OS command injection vulnerabilities in the Custom MCP Server feature due to incomplete command-flag validation and a regCVE-2026-56274 · Other software · Flowise · reported by VulnCheckHigh 8.7
Flowise before 3.1.2 contains multiple OS command injection vulnerabilities in the Custom MCP Server feature due to incomplete command-flag validation and a regex bypass in local file access restrictions. An attacker with a Flowise account of any role, or API access with view/update permissions for chatflows, can configure a malicious MCP server to bypass the validateCommandFlags blocklist (for example, 'docker build' is not blocked, and 'npx --yes' is not blocked while only '-y' is) and the validateArgsForLocalFileAccess checks, resulting in execution of arbitrary commands on the Flowise host.
- Product
- Flowise
- 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
Jun 22, 2026A maliciously crafted webpage, when visited by a user with Autodesk Fusion Desktop running and the MCP extension enabled, can trigger a vulnerability in the MCPCVE-2026-10789 · Other software · Autodesk · reported by psirt@autodesk.comCritical 9.6
A maliciously crafted webpage, when visited by a user with Autodesk Fusion Desktop running and the MCP extension enabled, can trigger a vulnerability in the MCP extension that could allow arbitrary code execution. A successful exploit may allow code to execute with the privileges of the current user.
- Product
- Fusion
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Full record and what to do →NVD recorddl.appstreaming.autodesk.comdl.appstreaming.autodesk.com
Jun 22, 2026IBM Langflow OSS 1.0.0 through 1.8.4 could allow unauthenticated attackers to access protected MCP project resources and execute MCP operations due to improper CVE-2026-7664 · Other software · IBM · reported by psirt@us.ibm.comCritical 9.8
IBM Langflow OSS 1.0.0 through 1.8.4 could allow unauthenticated attackers to access protected MCP project resources and execute MCP operations due to improper authorization enforcement in the Streamable MCP transport endpoint.
- Product
- Langflow OSS
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Jun 22, 2026Apache Doris MCP Server contains a SQL injection vulnerability in a metadata query path.CVE-2025-66336 · Websites & servers · Apache Software Foundation · reported by security@apache.orgHigh 8.1
Apache Doris MCP Server contains a SQL injection vulnerability in a metadata query path. A user-controlled database name is directly interpolated into a SQL query, and the query is executed without passing the caller's authorization context. This may allow an authenticated attacker, or an anonymous attacker if authentication is disabled, to bypass SQL security validation and access metadata outside the intended database scope. Affected users are recommended to upgrade to Doris version 0.6.1 or later, which fixes the issue.
- Product
- Apache Doris MCP Server
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Full record and what to do →NVD recordlists.apache.orgopenwall.com
Jun 19, 2026mcp-memory-service is a semantic memory layer for AI applications.CVE-2026-49291 · Other software · doobidoo · reported by GitHubHigh 8.1
mcp-memory-service is a semantic memory layer for AI applications. Prior to version 10.65.3, the HTTP MCP JSON-RPC endpoint at `/mcp` requires only OAuth `read` scope for all requests, then dispatches `tools/call` directly to handlers that include mutating tools. A read-only OAuth client can call `store_memory` and `delete_memory` through MCP even though the corresponding REST endpoints require `write` scope. Version 10.65.3 patches the issue.
- Product
- mcp-memory-service
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Jun 19, 2026Line Desktop MCP is a project that, while unaffiliated with the official line-bot-mcp-server, allows users to directly operate the LINE Desktop application on WCVE-2026-49357 · Other software · dtwang · reported by GitHubHigh 8.8
Line Desktop MCP is a project that, while unaffiliated with the official line-bot-mcp-server, allows users to directly operate the LINE Desktop application on Windows or Mac via MCP. `line-desktop-mcp` supports a `--http-mode` Streamable HTTP transport for use with clients such as n8n. In this mode the server binds to `0.0.0.0` and exposes the MCP `/mcp` endpoint without an MCP-layer authentication check. Prior to version 1.1.2, any network client that can reach the port can initialize a session, list tools, and call tools that read LINE Desktop chat history or send LINE messages through the already logged-in desktop application. Version 1.1.2 fixes the issue.
- Product
- line-desktop-mcp
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Jun 18, 2026mcp-pinot is a Python-based Model Context Protocol (MCP) server for interacting with Apache Pinot.CVE-2026-49257 · Other software · startreedata · reported by GitHubCritical 10
mcp-pinot is a Python-based Model Context Protocol (MCP) server for interacting with Apache Pinot. In versions 3.0.1 and below, mcp-pinot defaults to running an HTTP MCP server bound to 0.0.0.0:8080 with no authentication enabled. All MCP tools, including SQL query execution, schema creation, and table-config mutation, are reachable by any network-adjacent caller. The server proxies these calls using server-side Pinot credentials, producing a confused-deputy condition that yields full read/write access to the configured Pinot cluster. This issue has been fixed in version 3.1.0
- Product
- mcp-pinot
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Jun 18, 2026An authenticated authorization bypass vulnerability exists in MCP Toolbox for Databases due to missing scope enforcement across older protocol handlers.CVE-2026-11719 · Computers, phones & browsers · Google · reported by cve-coordination@google.comHigh 8.6
An authenticated authorization bypass vulnerability exists in MCP Toolbox for Databases due to missing scope enforcement across older protocol handlers. While the 2025-11-25 protocol version handler correctly enforces per-tool restrictions defined by scopesRequired, older supported protocol versions (2025-06-18, 2025-03-26, and 2024-11-05) omit this check. An authenticated client with low-privilege tokens (e.g., read) can bypass the intended per-tool scope restrictions and execute high-privilege tools (e.g., admin) simply by specifying an older protocol version in the MCP-Protocol-Version header, or by omitting the header entirely (which causes the server to default to the vulnerable 2024-11-05 handler).
- Product
- MCP Toolbox for Databases (googleapis/mcp-toolbox)
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Jun 18, 2026An authentication bypass vulnerability exists in the generic opaque token validation path (validateOpaqueToken) of googleapis/mcp-toolbox.CVE-2026-11718 · Computers, phones & browsers · Google · reported by cve-coordination@google.comCritical 9.3
An authentication bypass vulnerability exists in the generic opaque token validation path (validateOpaqueToken) of googleapis/mcp-toolbox. When the toolbox validates an opaque token via an OAuth 2.0 introspection endpoint (RFC 7662), it decodes the response into an introspectResp struct. However, the subsequent claim-checking logic (validateClaims) evaluates the issuer condition as if a.issuer != "" && iss != "". If the external OAuth provider's introspection response omits the optional iss (issuer) field completely, the variable iss defaults to an empty string. This causes the conditional block to evaluate to false and be skipped silently. Consequently, the application accepts tokens issued by unauthorized or unintended third-party identity providers.
- Product
- MCP Toolbox for Databases (googleapis/mcp-toolbox)
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Jun 18, 2026An authentication bypass vulnerability exists in the generic opaque token validation path (validateOpaqueToken) of googleapis/mcp-toolbox.CVE-2026-11717 · Computers, phones & browsers · Google · reported by cve-coordination@google.comCritical 9.3
An authentication bypass vulnerability exists in the generic opaque token validation path (validateOpaqueToken) of googleapis/mcp-toolbox. When verifying an unparsed opaque token via an OAuth 2.0 introspection endpoint (RFC 7662), the toolbox decodes the response into an introspectResp struct where the Active field is declared as a pointer to a boolean (*bool). The code only explicitly rejects a token if the response contains a populated active field set to false (if introspectResp.Active != nil && !*introspectResp.Active). If an introspection endpoint responds with a payload that completely omits the mandatory active key, the internal variable remains nil, causing the conditional check to short-circuit. As a result, Toolbox accepts authorization tokens missing the "active" field, granting access to protected tools and underlying data sources.
- Product
- MCP Toolbox for Databases (googleapis/mcp-toolbox)
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Jun 17, 2026Windows-MCP is an open-source project that integrates AI agents with Windows.CVE-2026-48989 · Other software · CursorTouch · reported by GitHubHigh 8.9
Windows-MCP is an open-source project that integrates AI agents with Windows. In versions prior to 0.7.5, certain HTTP modes exposed the MCP control plane without authentication while enabling wildcard CORS (allow_origins=*, allow_methods=*, allow_headers=*). Because the same server also exposed a PowerShell tool that executes caller-controlled commands as the Windows user running Windows-MCP, attackers could reach the control plane from arbitrary origins or non-browser clients and achieve arbitrary PowerShell execution. This issue was fixed in version 0.7.5.
- Product
- Windows-MCP
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Jun 17, 2026Backpropagate is a Python library for fine-tuning large language models on a single GPU.CVE-2026-48797 · Other software · mcp-tool-shop-org · reported by GitHubCritical 9.3
Backpropagate is a Python library for fine-tuning large language models on a single GPU. In versions 1.1.0 and 1.1.1, the optional Reflex web UI exposes a training control plane without authentication: dataset upload, model load, training start/stop, multi-run orchestration, GGUF export, and HuggingFace Hub push. The CLI accepts two operator-facing flags intended as security controls: --auth user:pass — documented as "require HTTP Basic authentication on every request to the UI." and--share — documented as "expose the UI on a public address; requires --auth." When --auth user:pass is passed, the CLI prints Auth: enabled (user: <username>) to confirm to the operator that authentication is active, then exports BACKPROPAGATE_UI_AUTH=user:pass to the subprocess that launches the Reflex backend. The Reflex backend (backpropagate/ui_app/**) never reads BACKPROPAGATE_UI_AUTH. No authentication middleware is registered. No request-level guard runs. No WebSocket upgrade guard runs. Any client that reaches the bound port — local or remote, depending on whether --share is used — has full UI access. An inline comment at backpropagate/cli.py:1217-1218 in the v1.1.0 source documents the gap: "Fo
- Product
- backpropagate
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Jun 16, 2026OpenClaw before 2026.5.12 contains an information disclosure vulnerability in streamable-http MCP servers that forwards operator-configured custom headers durinCVE-2026-53840 · Other software · OpenClaw · reported by VulnCheckMedium 6
OpenClaw before 2026.5.12 contains an information disclosure vulnerability in streamable-http MCP servers that forwards operator-configured custom headers during cross-origin redirects. Attackers controlling or compromising an MCP endpoint can redirect requests to exfiltrate sensitive headers like API keys or tenant-routing credentials to attacker-controlled origins.
- Product
- OpenClaw
- 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
Jun 15, 2026Unauthenticated Broken Access Control in Royal MCP <= 1.4.2 versions.CVE-2026-40775 · WordPress plugins & themes · reported by PatchstackHigh 7.3
Unauthenticated Broken Access Control in Royal MCP <= 1.4.2 versions.
- Affected
- up to 1.4.2
- What to do
- Affects up to 1.4.2. Update the plugin to the newest version and check its changelog mentions this fix; if there isn’t one yet, deactivate it until there is.
Jun 13, 2026The Model Context Protocol has a security warning advising servers to validate the "Origin" header on all incoming connections to prevent DNS rebinding attacks.CVE-2026-11624 · Computers, phones & browsers · Google · reported by cve-coordination@google.comCritical 9.4
The Model Context Protocol has a security warning advising servers to validate the "Origin" header on all incoming connections to prevent DNS rebinding attacks. Prior to the v0.25.0 release, users had no way to validate the origin's host. In v0.25.0, a new "--allowed-hosts" flag was introduced alongside the existing "--allowed-origins" flag, enabling users to specify permitted hosts at server startup. Both flags default to "*", allowing users to implement strict access controls as needed without breaking existing setups. If either flag is set to "*", the server will output a startup warning about potential vulnerabilities. Documentation has also been updated to highlight these security considerations.
- Product
- MCP Toolbox for Databases
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Jun 12, 2026OpenClaw before 2026.5.12 contains an exec denylist bypass vulnerability in the bundle MCP loopback session-spawn path that allows authenticated callers to bypaCVE-2026-53820 · Other software · OpenClaw · reported by VulnCheckMedium 6.9
OpenClaw before 2026.5.12 contains an exec denylist bypass vulnerability in the bundle MCP loopback session-spawn path that allows authenticated callers to bypass intended command restrictions. Attackers can reach the affected bundled MCP session-spawn path to start sessions with broader command reach than intended.
- Product
- OpenClaw
- 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
Jun 11, 2026OpenClaw before 2026.4.24 contains an authorization bypass vulnerability in the MCP loopback feature that allows non-owner callers to skip owner-only tool policCVE-2026-53818 · Other software · OpenClaw · reported by VulnCheckMedium 6.9
OpenClaw before 2026.4.24 contains an authorization bypass vulnerability in the MCP loopback feature that allows non-owner callers to skip owner-only tool policies and before-tool-call hooks. Attackers can invoke owner-only behavior through the affected loopback path to execute restricted tools when the feature is enabled and reachable.
- Product
- OpenClaw
- 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
Jun 11, 2026OpenClaw before 2026.5.20 contains a privilege escalation vulnerability where hook-triggered agent runs incorrectly receive owner-scoped MCP loopback authority CVE-2026-53814 · Other software · OpenClaw · reported by VulnCheckHigh 8.7
OpenClaw before 2026.5.20 contains a privilege escalation vulnerability where hook-triggered agent runs incorrectly receive owner-scoped MCP loopback authority instead of hook-appropriate scope. Attackers with a valid hook token can exploit the /hooks/agent endpoint to cause spawned CLI runtimes to access or invoke owner-only MCP tools, potentially executing privileged actions like persistent cron state modifications.
- Product
- OpenClaw
- 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
Jun 11, 2026mcp-server-kubernetes is a Model Context Protocol server for Kubernetes cluster management.CVE-2026-47250 · Other software · Flux159 · reported by GitHubMedium 6.1
mcp-server-kubernetes is a Model Context Protocol server for Kubernetes cluster management. Prior to version 3.7.0, the kubectl_generic tool in mcp-server-kubernetes passes user-supplied flags directly to kubectl without any allowlist, enabling a privilege escalation attack within Kubernetes environments. An attacker who already has limited cluster or codebase access, for example, a developer with pod-deployment permissions but not cluster-admin credentials, can plant a single structured JSON line in an application's log output. When an operator with a privileged kubeconfig uses the MCP server to read those logs and their AI agent follows the injected instruction, kubectl_generic is called with --server=https://attacker.example.com and --insecure-skip-tls-verify=true. kubectl sends all API requests, including the Authorization: Bearer <token> header from the operator's kubeconfig to the attacker's endpoint. The captured token can then be replayed directly against the real Kubernetes API server, granting the attacker the full RBAC permissions of the operator's service account. This issue has been patched in version 3.7.0.
- Product
- mcp-server-kubernetes
- 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.