Vulnerability database

933 results · page 5 of 19

• Sep 15, 2026AI Engine – The Chatbot, AI Framework & MCP for: Insecure Direct Object ReferenceCVE-2026-89141 · WordPress plugins & themes · reported by WordfenceMedium 6.5

  The AI Engine – The Chatbot, AI Framework & MCP for WordPress plugin for WordPress is vulnerable to Insecure Direct Object Reference in all versions up to, and including, 3.7.7 via the 'mediaId' parameter due to missing validation on a user controlled key. This makes it possible for authenticated attackers, with subscriber-level access and above, to access and retrieve the transcribed contents of private audio attachments belonging to other users, including Administrators, via a supplied attachment ID. This vulnerability requires the Public API module to be enabled in the plugin settings; when disabled, the REST route is absent and the endpoint returns HTTP 404.

  Product

  AI Engine – The Chatbot, AI Framework & MCP for

  Affected

  up to 3.7.7

  What to do

  Affects up to 3.7.7. Update AI Engine – The Chatbot, AI Framework & MCP for to the newest version and check its changelog mentions this fix; if there isn’t one yet, deactivate it until there is.

  Full record and what to do →NVD recordplugins.trac.wordpress.orgplugins.trac.wordpress.org

• Sep 14, 2026IBM Langflow OSS 1.0.0 through 1.11.5 could allow an authenticated attacker to access another user's MCP server context due to improper cache key isolation in tCVE-2026-12763 · Other software · IBM · reported by psirt@us.ibm.comMedium 4.2

  IBM Langflow OSS 1.0.0 through 1.11.5 could allow an authenticated attacker to access another user's MCP server context due to improper cache key isolation in the MCP Tools component.

  Product

  Langflow OSS

  What to do

  Apply the vendor’s update. The NVD record links to the advisory.

  Full record and what to do →NVD recordibm.com

• Sep 14, 2026MCP Atlassian is a Model Context Protocol (MCP) server for Atlassian products (Confluence and Jira).CVE-2026-73497 · Other software · sooperset · reported by GitHubMedium 6.5

  MCP Atlassian is a Model Context Protocol (MCP) server for Atlassian products (Confluence and Jira). From 0.17.0 until 0.22.0, validate_url_for_ssrf resolves the attacker-controlled X-Atlassian-Jira-Url and X-Atlassian-Confluence-Url header host once at middleware time, but the outbound request is built with the raw hostname and resolves it again at connection time with no IP pinning. An attacker-controlled DNS-rebinding name can return a public IP during validation and 169.254.169.254 or another internal IP during connection, enabling unauthenticated server-side requests to cloud metadata or internal services. The flaw spans src/mcp_atlassian/utils/urls.py, src/mcp_atlassian/servers/main.py, and src/mcp_atlassian/servers/dependencies.py; validate_url_for_ssrf returns only a verdict rather than a pinned IP, UserTokenMiddleware processes the attacker-controlled headers before fetcher creation, and the Jira and Confluence fetchers use the raw hostname. This issue is fixed in version 0.22.0.

  Product

  mcp-atlassian

  What to do

  Apply the vendor’s update. The NVD record links to the advisory.

  Full record and what to do →NVD recordgithub.comgithub.com

• Sep 14, 2026MCP Atlassian is a Model Context Protocol (MCP) server for Atlassian products (Confluence and Jira).CVE-2026-73496 · Other software · sooperset · reported by GitHubHigh 7.7

  MCP Atlassian is a Model Context Protocol (MCP) server for Atlassian products (Confluence and Jira). Prior to 0.22.0, the confluence_upload_attachment and confluence_upload_attachments tools pass a client-controlled file_path through src/mcp_atlassian/confluence/attachments.py upload_attachment, and the jira_update_issue attachments parameter reaches src/mcp_atlassian/jira/attachments.py upload_attachment, without confining either path to an approved server workspace. In a remote HTTP, SSE, or multi-user deployment, absolute or traversing paths are resolved on the MCP server and uploaded to Atlassian, allowing a client with write-tool access to disclose server files, environment-held Atlassian credentials, or another tenant's data. A local single-user stdio deployment does not cross this trust boundary because the server runs in the caller's environment. This issue is fixed in version 0.22.0.

  Product

  mcp-atlassian

  What to do

  Apply the vendor’s update. The NVD record links to the advisory.

  Full record and what to do →NVD recordgithub.comgithub.com

• Sep 14, 2026dbt-mcp is a Model Context Protocol server for interacting with dbt.CVE-2026-55837 · Other software · dbt-labs · reported by GitHubMedium 6.8

  dbt-mcp is a Model Context Protocol server for interacting with dbt. Prior to 1.20.0, the local OAuth helper in src/dbt_mcp/oauth/fastapi_app.py exposes GET /dbt_platform_context without authentication or Host validation after a user completes the dbt Platform OAuth flow. The endpoint returns the full DbtPlatformContext, including access_token and refresh_token values persisted by the context manager, to any process that can reach 127.0.0.1:6785. The absence of TrustedHostMiddleware allows a remote attacker to use DNS rebinding against a victim's browser because the helper accepts arbitrary Host headers, while a co-located process can request the endpoint directly. The stolen tokens provide immediate dbt Platform API access as the victim and persistent access through the refresh token, allowing access to or modification of projects, jobs, environment secrets, and related account data. This issue is fixed in version 1.20.0.

  Product

  dbt-mcp

  What to do

  Apply the vendor’s update. The NVD record links to the advisory.

  Full record and what to do →NVD recordgithub.comgithub.com

• Sep 14, 2026ContextForge is an AI gateway, registry, and proxy that provides centralized discovery, guardrails, and management for MCP, A2A, and REST or gRPC APIs.CVE-2026-53708 · Other software · IBM · reported by GitHubMedium 6.6

  ContextForge is an AI gateway, registry, and proxy that provides centralized discovery, guardrails, and management for MCP, A2A, and REST or gRPC APIs. Prior to 1.0.3, the /admin/gateways/test call site in mcpgateway/admin.py calls validate_gateway_test_url() in mcpgateway/common/validators.py to resolve and reject private, loopback, link-local, and cloud-metadata addresses, but ResilientHttpClient later resolves the original hostname again without binding the validated address. When MCPGATEWAY_ADMIN_API_ENABLED is enabled, an attacker with a database-backed role containing explicit gateways.read permission can use DNS rebinding to return a public address during validation and a private or metadata address during connection, bypassing ssrf_blocked_networks and ssrf_dns_fail_closed because those controls apply only to the validation-time result. The endpoint's allow_admin_bypass=False setting means a bootstrap-only virtual platform-admin identity without a database role is not sufficient. Successful exploitation can reach internal services and cloud metadata, expose cloud credentials, access internal APIs, or probe internal network ports. This issue is fixed in version 1.0.3.

  Product

  mcp-context-forge

  What to do

  Apply the vendor’s update. The NVD record links to the advisory.

  Full record and what to do →NVD recordgithub.comgithub.com

• Sep 14, 2026Bifrost registers MCP clients through its management API.CVE-2026-90898 · Other software · maximhq · reported by reefs@jfrog.comCritical 9.8

  Bifrost registers MCP clients through its management API. A stdio client is a command plus args. Bifrost starts that program in the gateway the moment the client is added. No MCP handshake required. The default is governance.auth_config.is_enabled=false. Auth off means every caller is a local admin. One unauthenticated POST /api/mcp/client is enough to run a program as the Bifrost process user (appuser on the official image).  transports/v2.1.0 refuses an unauthenticated stdio registration with 403. transports/v2.0.0 still allows it.

  Product

  Bifrost

  What to do

  Apply the vendor’s update. The NVD record links to the advisory.

  Full record and what to do →NVD recordgithub.comgithub.com

• Sep 13, 2026In Oraios AI Serena before 1.0.0, the listen address of the MCP server in HTTP mode is 0.0.0.0.CVE-2026-38924 · Other software · Oraios AI · reported by MITRELow 2.9

  In Oraios AI Serena before 1.0.0, the listen address of the MCP server in HTTP mode is 0.0.0.0. NOTE: the Supplier observed that 0.0.0.0 was a "potential security hazard" but the Serena documentation, at the time of the issue report proposing 127.0.0.1 instead of 0.0.0.0, recommended "use a sandboxed environment for running Serena."

  Product

  Serena

  What to do

  Apply the vendor’s update. The NVD record links to the advisory.

  Full record and what to do →NVD recorddash.securitygithub.com

• Sep 12, 2026MCPHub before 1.0.32 contains an authentication bypass vulnerability in its embedded OAuth 2.0 authorization server where client authentication is disabled by dCVE-2026-90474 · Other software · samanhappy · reported by VulnCheckHigh 7.6

  MCPHub before 1.0.32 contains an authentication bypass vulnerability in its embedded OAuth 2.0 authorization server where client authentication is disabled by default and PKCE enforcement is optional. Attackers who obtain an authorization code through interception can redeem it for access tokens without providing a client secret or PKCE verifier, gaining access to victim accounts and their privileges.

  Product

  mcphub

  What to do

  Apply the vendor’s update. The NVD record links to the advisory.

  Full record and what to do →NVD recordgithub.comgithub.com

• Sep 11, 2026In the Linux kernel, the following vulnerability has been resolved: HID: mcp2221: stop device IO before hid_hw_stop Quiesce device IO at the start of the devmCVE-2026-89623 · Computers, phones & browsers · Linux · reported by 416baaa9-dc9f-4396-8d5f-8c081fb06d67

  In the Linux kernel, the following vulnerability has been resolved: HID: mcp2221: stop device IO before hid_hw_stop Quiesce device IO at the start of the devm cleanup callback mcp2221_hid_unregister() so that incoming HID reports cannot race with hardware teardown during probe failure or device removal, addressing a potential use-after-free. Guard the call to hid_device_io_stop() with io_started. On normal removal hid_device_remove() has already cleared io_started before the devres group is released, so an unconditional call would otherwise hit the !io_started path and emit a spurious "io already stopped" warning on every removal. The guard preserves the probe-failure balancing, where io_started is still set after hid_device_io_start(), while staying silent on the normal removal path.

  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

• Sep 11, 2026In the Linux kernel, the following vulnerability has been resolved: HID: mcp2221: clear rxbuf after I2C/SMBus transfer completes mcp_i2c_smbus_read() stores tCVE-2026-89622 · Computers, phones & browsers · Linux · reported by 416baaa9-dc9f-4396-8d5f-8c081fb06d67High 7.8

  In the Linux kernel, the following vulnerability has been resolved: HID: mcp2221: clear rxbuf after I2C/SMBus transfer completes mcp_i2c_smbus_read() stores the caller-supplied buffer pointer in mcp->rxbuf for the duration of a transfer but never clears it when the transfer finishes or times out. Once the caller frees or reuses the buffer, mcp->rxbuf becomes a dangling pointer. A delayed or spurious MCP2221_I2C_GET_DATA report can then drive mcp2221_raw_event() to memcpy device data into the freed memory, causing a write use-after-free. Route all return paths through a single exit point that clears mcp->rxbuf and mcp->rxbuf_size, so that the existing !mcp->rxbuf guard in the raw_event handler can reject any report arriving after the transfer has ended.

  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

• Sep 11, 2026In the Linux kernel, the following vulnerability has been resolved: HID: mcp2221: validate report size in mcp2221_raw_event() mcp2221_raw_event() never validaCVE-2026-89621 · Computers, phones & browsers · Linux · reported by 416baaa9-dc9f-4396-8d5f-8c081fb06d67

  In the Linux kernel, the following vulnerability has been resolved: HID: mcp2221: validate report size in mcp2221_raw_event() mcp2221_raw_event() never validates the size of incoming HID reports. In the MCP2221_I2C_GET_DATA path it trusts the device-supplied data[3] as the copy length without checking that 4 + data[3] bytes actually exist in the received report. A malicious or misbehaving USB device can send a short report with a large data[3], causing the memcpy to read past the valid report data in the HID transfer buffer and leak uninitialized kernel memory back to userspace through the I2C/SMBus read path. Add a minimum size check at entry and validate that the source range fits within the received report before the copy.

  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

• Sep 10, 2026IBM ContextForge MCP Gateway 1.0.0 through 1.0.7 could allow a remote attacker to gain administrative access due to the use of default credentials.CVE-2026-78573 · Other software · IBM · reported by psirt@us.ibm.comCritical 9.8

  IBM ContextForge MCP Gateway 1.0.0 through 1.0.7 could allow a remote attacker to gain administrative access due to the use of default credentials.

  Product

  ContextForge MCP Gateway

  What to do

  Apply the vendor’s update. The NVD record links to the advisory.

  Full record and what to do →NVD recordibm.com

• Sep 10, 2026knowns through 0.33.0 fails to confine the path argument of the code.find MCP tool to the project root, allowing AI agent sessions to read source files anywhereCVE-2026-88938 · Other software · knowns-dev · reported by VulnCheckHigh 7.1

  knowns through 0.33.0 fails to confine the path argument of the code.find MCP tool to the project root, allowing AI agent sessions to read source files anywhere on the host. Attackers can supply absolute paths or relative traversal sequences to the path argument and retrieve full file contents from outside the intended project directory.

  Product

  knowns

  What to do

  Apply the vendor’s update. The NVD record links to the advisory.

  Full record and what to do →NVD recordgithub.comgithub.com

• Sep 10, 2026A missing S3 bucket ownership verification in the AWS Security Agent MCP server before 0.2.0 version might allow remote attackers to obtain the private source aCVE-2026-87913 · Other software · AWS · reported by ff89ba41-3aa1-4d27-914a-91399e9639e5Medium 5.1

  A missing S3 bucket ownership verification in the AWS Security Agent MCP server before 0.2.0 version might allow remote attackers to obtain the private source archive of a scanned workspace, including credentials and infrastructure state contained in that archive, via a pre-registered storage bucket whose name is derived from a publicly known account identifier. To remediate this issue, users should upgrade to version 0.2.0. Users should also verify that the scan output bucket in their account is owned by their own account, because upgrading does not release a bucket name that a third party has already registered.

  Product

  AWS Security Agent 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

• Sep 9, 2026An OS command injection weakness in the read-only enforcement of the SQL validation component in Amazon awslabs postgres-mcp-server before 1.1.7 might allow an CVE-2026-87911 · Other software · AWS · reported by ff89ba41-3aa1-4d27-914a-91399e9639e5Critical 9

  An OS command injection weakness in the read-only enforcement of the SQL validation component in Amazon awslabs postgres-mcp-server before 1.1.7 might allow an unauthenticated actor to execute operating system commands on the host of a self-managed PostgreSQL server by placing a crafted COPY ... TO PROGRAM statement into content that is processed when an authenticated user interacts with the MCP server in its default read-only mode. To remediate this issue, users should upgrade to version 1.1.7 or later.

  Product

  AWS Labs postgres 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

• Sep 9, 2026Incomplete list of disallowed inputs in the mutable SQL detector component in Amazon awslabs mysql-mcp-server might allow context-dependent actors to bypass theCVE-2026-85788 · Other software · AWS · reported by ff89ba41-3aa1-4d27-914a-91399e9639e5Medium 5.7

  Incomplete list of disallowed inputs in the mutable SQL detector component in Amazon awslabs mysql-mcp-server might allow context-dependent actors to bypass the read-only enforcement gate and reach file-read and file-write SQL sinks via SQL inline comments that the regex engine does not treat as whitespace. To remediate this issue, users should upgrade to version 1.0.23.

  Product

  AWS Labs MySQL 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

• Sep 8, 2026Information leak in WebMCP in Google Chrome prior to 153.0.8010.36 allowed a remote attacker who had compromised the renderer process to obtain cross-origin datCVE-2026-87521 · Computers, phones & browsers · Google · reported by chrome-cve-admin@google.comLow 3.1

  Information leak in WebMCP in Google Chrome prior to 153.0.8010.36 allowed a remote attacker who had compromised the renderer process to obtain cross-origin data via a crafted HTML page. (Chromium security severity: Medium)

  Product

  Chrome

  What to do

  Apply the vendor’s update. The NVD record links to the advisory.

  Full record and what to do →NVD recordchromereleases.googleblog.comissues.chromium.org

• Sep 8, 2026MCP Kotlin SDK is the Kotlin Multiplatform software development kit for the Model Context Protocol.CVE-2026-53937 · Other software · modelcontextprotocol · reported by GitHubMedium 6.2

  MCP Kotlin SDK is the Kotlin Multiplatform software development kit for the Model Context Protocol. In versions 0.7.0 through 0.12.0, `ReadBuffer.append` in `kotlin-sdk-core/src/commonMain/kotlin/io/modelcontextprotocol/kotlin/sdk/shared/ReadBuffer.kt` writes every chunk of bytes received from the stdio transport into a `kotlinx.io.Buffer` with no size cap. Frames are extracted from that buffer only when a `\n` (0x0a) byte is observed. A peer that streams bytes without ever sending a newline causes the internal buffer to grow indefinitely until the JVM (or the surrounding host process) is OOM-killed. The leak is amplified by `StdioServerTransport` and `StdioClientTransport`, which both queue raw chunks through a `kotlinx.coroutines.channels.Channel<ByteArray>(Channel.UNLIMITED)` and then call `readBuffer.append(chunk)` without backpressure or size guard. This is a remote-pre-auth denial of service whenever an SDK stdio server's stdin is fed by an untrusted or attacker-controlled producer (for example: a host program that exec's the MCP server as a subprocess and pipes through bytes received from a network peer, or a sidecar wrapper that proxies bytes from an HTTP endpoint to the st

  Product

  io.modelcontextprotocol:kotlin-sdk

  What to do

  Apply the vendor’s update. The NVD record links to the advisory.

  Full record and what to do →NVD recordgithub.comgithub.com

• Sep 7, 2026knowns versions before 0.30.0 fail to validate filesystem paths in MCP tool arguments, allowing attackers to read, create, overwrite and delete files outside thCVE-2026-86439 · Other software · knowns-dev · reported by VulnCheckHigh 8.7

  knowns versions before 0.30.0 fail to validate filesystem paths in MCP tool arguments, allowing attackers to read, create, overwrite and delete files outside the project directory. Attackers can supply path arguments containing directory traversal sequences to access arbitrary Markdown files accessible to the server process.

  Product

  knowns

  What to do

  Apply the vendor’s update. The NVD record links to the advisory.

  Full record and what to do →NVD recordgithub.comgithub.com

• Sep 5, 2026Rowboat through 0.9.1 fails to validate custom MCP server and webhook URLs, allowing authenticated users to configure arbitrary destinations.CVE-2026-86122 · Other software · rowboatlabs · reported by VulnCheckMedium 5.3

  Rowboat through 0.9.1 fails to validate custom MCP server and webhook URLs, allowing authenticated users to configure arbitrary destinations. Attackers can point these URLs at internal services and cloud metadata endpoints to perform server-side request forgery and enumerate internal network topology.

  Product

  rowboat

  What to do

  Apply the vendor’s update. The NVD record links to the advisory.

  Full record and what to do →NVD recordgithub.comgithub.com

• Sep 4, 2026An incomplete list of disallowed inputs in the SQL validation component in Amazon awslabs postgres-mcp-server before version 1.1.7 might allow an unauthenticatCVE-2026-85787 · Other software · Amazon · reported by ff89ba41-3aa1-4d27-914a-91399e9639e5High 7.1

  An incomplete list of disallowed inputs in the SQL validation component in Amazon awslabs postgres-mcp-server before version 1.1.7 might allow an unauthenticated actor to modify data beyond the read-only scope by placing crafted SQL into the content that is submitted when an authenticated user interacts with the MCP server. To remediate this issue, users should upgrade to version 1.1.7 or above.

  Product

  postgres-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

• Sep 4, 2026Improper neutralization of special elements used in a template engine in the CDK generator in Amazon awslabs.dynamodb-mcp-server before 2.1.6 might allow a contCVE-2026-85654 · Other software · Amazon · reported by ff89ba41-3aa1-4d27-914a-91399e9639e5High 7.1

  Improper neutralization of special elements used in a template engine in the CDK generator in Amazon awslabs.dynamodb-mcp-server before 2.1.6 might allow a context-dependent actor to execute arbitrary code on the host that deploys the generated application via crafted table, index, or attribute names in a data model file.

  Product

  awslabs.dynamodb-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

• Sep 4, 2026IBM ContextForge MCP Gateway - Translate utility <= 1.0.8 MCP Context Forge could allow a remote attacker to obtain sensitive information from other sessions duCVE-2026-18489 · Other software · IBM · reported by psirt@us.ibm.comHigh 7.4

  IBM ContextForge MCP Gateway - Translate utility <= 1.0.8 MCP Context Forge could allow a remote attacker to obtain sensitive information from other sessions due to exposure of data elements to the wrong session.

  Product

  ContextForge MCP Gateway - Translate utility

  What to do

  Apply the vendor’s update. The NVD record links to the advisory.

  Full record and what to do →NVD recordibm.com

• Sep 4, 2026IBM ContextForge MCP Gateway <= v1.0.7 MCP Context Forge could allow a remote authenticated attacker to obtain sensitive credentials and escalate privileges dueCVE-2026-18486 · Other software · IBM · reported by psirt@us.ibm.comHigh 8.8

  IBM ContextForge MCP Gateway <= v1.0.7 MCP Context Forge could allow a remote authenticated attacker to obtain sensitive credentials and escalate privileges due to improper validation of jq filters.

  Product

  ContextForge MCP Gateway

  What to do

  Apply the vendor’s update. The NVD record links to the advisory.

  Full record and what to do →NVD recordibm.com

• Sep 4, 2026IBM ContextForge MCP Gateway could allow a remote authenticated attacker to obtain sensitive information due to server-side request forgery via DNS rebinding.CVE-2026-77822 · Other software · IBM · reported by psirt@us.ibm.comHigh 8.2

  IBM ContextForge MCP Gateway could allow a remote authenticated attacker to obtain sensitive information due to server-side request forgery via DNS rebinding.

  Product

  ContextForge MCP Gateway

  What to do

  Apply the vendor’s update. The NVD record links to the advisory.

  Full record and what to do →NVD recordibm.com

• Sep 4, 2026IBM ContextForge MCP Gateway (`mcp-contextforge-gateway`) <= v1.0.6 MCP Context Forge could allow a remote authenticated attacker to obtain sensitive informatioCVE-2026-18905 · Other software · IBM · reported by psirt@us.ibm.comHigh 7.7

  IBM ContextForge MCP Gateway (`mcp-contextforge-gateway`) <= v1.0.6 MCP Context Forge could allow a remote authenticated attacker to obtain sensitive information due to a DNS rebinding vulnerability during tool invocation.

  Product

  ContextForge MCP Gateway (`mcp-contextforge-gateway`)

  What to do

  Apply the vendor’s update. The NVD record links to the advisory.

  Full record and what to do →NVD recordibm.com

• Sep 4, 2026IBM Langflow OSS 1.0.0 through 1.11.2 allows remote authenticated attackers to bypass localhost-only MCP configuration installation by spoofing X-Forwarded-For:CVE-2026-9186 · Other software · IBM · reported by psirt@us.ibm.comMedium 6.5

  IBM Langflow OSS 1.0.0 through 1.11.2 allows remote authenticated attackers to bypass localhost-only MCP configuration installation by spoofing X-Forwarded-For: 127.0.0.1 header, enabling arbitrary writes to IDE config files (~/.cursor/mcp.json, etc.).

  Product

  Langflow OSS

  What to do

  Apply the vendor’s update. The NVD record links to the advisory.

  Full record and what to do →NVD recordibm.com

• Sep 4, 2026excel-mcp-server 0.1.8 fails to enforce path confinement in stdio mode when EXCEL_FILES_PATH is unset, allowing attackers to read and write arbitrary files.CVE-2026-85661 · Other software · haris-musa · reported by VulnCheckCritical 9.3

  excel-mcp-server 0.1.8 fails to enforce path confinement in stdio mode when EXCEL_FILES_PATH is unset, allowing attackers to read and write arbitrary files. Attackers can supply unchecked file paths to read and write tools to access any file accessible to the process.

  Product

  excel-mcp-server

  What to do

  Apply the vendor’s update. The NVD record links to the advisory.

  Full record and what to do →NVD recordgithub.comgithub.com

• Sep 4, 2026cli-mcp-server 0.2.5 contains a command allowlist bypass vulnerability in the _validate_command_with_operators function when ALLOW_SHELL_OPERATORS is enabled.CVE-2026-85660 · Other software · MladenSU · reported by VulnCheckCritical 9.2

  cli-mcp-server 0.2.5 contains a command allowlist bypass vulnerability in the _validate_command_with_operators function when ALLOW_SHELL_OPERATORS is enabled. Attackers can use shell command substitution syntax like $(...) or backticks to execute non-allowlisted commands that bypass the ALLOWED_COMMANDS validation check.

  Product

  cli-mcp-server

  What to do

  Apply the vendor’s update. The NVD record links to the advisory.

  Full record and what to do →NVD recordgithub.comgithub.com

• Sep 4, 2026git-mcp-server 2.15.1 contains an argument injection vulnerability in the ref and object parameters of git_log, git_diff, and git_show tools that lack leading-dCVE-2026-85626 · Other software · cyanheads · reported by VulnCheckHigh 8.7

  git-mcp-server 2.15.1 contains an argument injection vulnerability in the ref and object parameters of git_log, git_diff, and git_show tools that lack leading-dash validation. Attackers can inject git command-line options like --output= to write files outside the repository to arbitrary paths accessible by the process.

  Product

  git-mcp-server

  What to do

  Apply the vendor’s update. The NVD record links to the advisory.

  Full record and what to do →NVD recordgithub.comgithub.com

• Sep 4, 2026Postgres MCP Pro 0.3.0 contains a restricted-mode bypass vulnerability where function-name validation is not applied to RangeFunction nodes in FROM clauses.CVE-2026-85620 · Other software · crystaldba · reported by VulnCheckCritical 9.2

  Postgres MCP Pro 0.3.0 contains a restricted-mode bypass vulnerability where function-name validation is not applied to RangeFunction nodes in FROM clauses. Attackers can execute file-reading functions like pg_read_file through FROM-clause syntax to read arbitrary files despite restricted-mode protections.

  Product

  postgres-mcp

  What to do

  Apply the vendor’s update. The NVD record links to the advisory.

  Full record and what to do →NVD recordgithub.comgithub.com

• Sep 4, 2026firecrawl-mcp-server 3.20.2 contains an arbitrary local file read vulnerability in the firecrawl_parse tool that accepts unconstrained filePath arguments withouCVE-2026-85606 · Other software · firecrawl · reported by VulnCheckHigh 8.7

  firecrawl-mcp-server 3.20.2 contains an arbitrary local file read vulnerability in the firecrawl_parse tool that accepts unconstrained filePath arguments without directory containment validation. Attackers can supply absolute paths or directory traversal sequences to read sensitive files like credentials and environment variables, which are then uploaded and returned to the model context.

  Product

  firecrawl-mcp-server

  What to do

  Apply the vendor’s update. The NVD record links to the advisory.

  Full record and what to do →NVD recordgithub.comgithub.com

• Sep 4, 2026SiYuan versions before v3.8.2 contain a path guard bypass vulnerability in the MCP file-access handler that uses case-sensitive matching on Linux filesystems.CVE-2026-85580 · Other software · siyuan-note · reported by VulnCheckHigh 7.1

  SiYuan versions before v3.8.2 contain a path guard bypass vulnerability in the MCP file-access handler that uses case-sensitive matching on Linux filesystems. Attackers can read the protected publishAccess.json file by requesting case-variant paths like PublishAccess.json to disclose sensitive publish-access configuration and metadata.

  Product

  siyuan

  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

• Sep 3, 2026MountDev AI MCP Connector for: Missing AuthorizationCVE-2026-85306 · WordPress plugins & themes · reported by PatchstackMedium 6.5

  Missing Authorization vulnerability in Cascadia Web Services MountDev AI MCP Connector for WordPress allows Exploiting Incorrectly Configured Access Control Security Levels. This issue affects MountDev AI MCP Connector for WordPress: from n/a through 1.6.5.

  Product

  MountDev AI MCP Connector for

  Affected

  up to 1.6.5

  What to do

  Affects up to 1.6.5. Update MountDev AI MCP Connector for to the newest version and check its changelog mentions this fix; if there isn’t one yet, deactivate it until there is.

  Full record and what to do →NVD recordpatchstack.com

• Sep 3, 2026Subscriber Broken Access Control in Agentimus – AI SEO, llms.txt & MCP for AI Agents <= 1.51.0 versions.CVE-2026-84779 · WordPress plugins & themes · reported by PatchstackHigh 8.1

  Subscriber Broken Access Control in Agentimus – AI SEO, llms.txt & MCP for AI Agents <= 1.51.0 versions.

  Affected

  up to 1.51.0

  What to do

  Affects up to 1.51.0. 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.

  Full record and what to do →NVD recordpatchstack.com

• Sep 1, 2026An authorization bypass in the runZero Platform MCP service has been resolved in version 5.1.260826.0.CVE-2026-81846 · Other software · runZero · reported by 44488dab-36db-4358-99f9-bc116477f914Low 3.5

  An authorization bypass in the runZero Platform MCP service has been resolved in version 5.1.260826.0. This issue is an instance of CWE-639: Authorization Bypass Through User-Controlled Key and has an estimated CVSS score of CVSS:3.1/AV:N/AC:H/PR:L/UI:N/S:C/C:L/I:N/A:N (3.5 Low).

  Product

  Platform

  What to do

  Apply the vendor’s update. The NVD record links to the advisory.

  Full record and what to do →NVD recordhelp.runzero.comrunzero.com

• Sep 1, 2026appium-mcp-server through 0.1.61 fails to validate or normalize file paths in the write_file and write_files_batch tools, allowing attackers to write files outsCVE-2026-84201 · Other software · argneshu · reported by VulnCheckMedium 6.9

  appium-mcp-server through 0.1.61 fails to validate or normalize file paths in the write_file and write_files_batch tools, allowing attackers to write files outside the intended PROJECT_ROOT directory. Attackers can supply absolute paths or relative paths with parent directory segments to overwrite arbitrary files with the server user's privileges, including shell profiles and configuration files in the home directory.

  Product

  appium-mcp-server

  What to do

  Apply the vendor’s update. The NVD record links to the advisory.

  Full record and what to do →NVD recordgithub.comgithub.com

• 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-2026-79750 · Other software · samanhappy · reported by GitHubHigh 7.7

  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 1.0.30, MCPHub scopes non-admin users to servers they own (list views and config edits enforce ownership), but the tool-execution API does not. Any authenticated non-admin user can invoke tools on MCP servers owned by other users — servers they cannot even see in GET /api/servers. Because connected MCP servers carry real capability (filesystem, HTTP fetch, cloud APIs with the owner's keys), this is cross-tenant compromise: demonstrated arbitrary host file read (/etc/passwd, another user's secrets) and SSRF. This issue has been patched in version 1.0.30.

  Product

  mcphub

  What to do

  Apply the vendor’s update. The NVD record links to the advisory.

  Full record and what to do →NVD recordgithub.comgithub.com

• 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-2026-79749 · Other software · samanhappy · reported by GitHubHigh 7.6

  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, MCPHub's SSRF guard in src/utils/ssrf.ts uses a custom isBlockedIpv6 function that only checks for loopback, link-local, unique-local, IPv4-mapped, and IPv4-compatible IPv6 addresses. IPv6 transition address families -- NAT64 (64:ff9b::/96), 6to4 (2002::/16), and Teredo (2001::/32) -- are not checked. An attacker who can specify a URL for an MCP server connection can encode a private IPv4 address inside one of these IPv6 forms to bypass the SSRF guard and reach internal infrastructure. 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.

  Full record and what to do →NVD recordgithub.comgithub.com

• 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.

  Full record and what to do →NVD recordgithub.comgithub.com

• 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.

  Full record and what to do →NVD recordgithub.comgithub.com

• 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.

  Full record and what to do →NVD recordgithub.comgithub.com

• 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.

  Full record and what to do →NVD recordgithub.comgithub.com

• 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.

  Full record and what to do →NVD recordgithub.comgithub.com

• 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.

  Full record and what to do →NVD recordgithub.comgithub.com

• 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 29, 2026argocd-mcp 0.8.0 binds its HTTP transport to every network interface and accepts MCP sessions without requiring caller credentials when ARGOCD_API_TOKEN is confCVE-2026-82456 · Other software · argoproj-labs · reported by VulnCheckCritical 10

  argocd-mcp 0.8.0 binds its HTTP transport to every network interface and accepts MCP sessions without requiring caller credentials when ARGOCD_API_TOKEN is configured. Attackers who can reach the listener can invoke the full tool surface using the operator's stored token to create applications, request syncs, and modify Argo CD resources.

  Product

  argocd-mcp

  What to do

  Apply the vendor’s update. The NVD record links to the advisory.

  Full record and what to do →NVD recordgithub.comgithub.com

• Aug 28, 2026Hermes Agent 0.18.2 prior to 0.19.0 contains a supply chain vulnerability in its bundled MCP catalog that allows a remote attacker to execute arbitrary code by CVE-2026-82021 · Other software · NousResearch · reported by VulnCheckCritical 9

  Hermes Agent 0.18.2 prior to 0.19.0 contains a supply chain vulnerability in its bundled MCP catalog that allows a remote attacker to execute arbitrary code by compromising a third-party upstream repository referenced via a mutable branch rather than a pinned commit SHA. An attacker who compromises the upstream repository can propagate malicious code to every host that installs the affected catalog entry, with no further action required by the operator.

  Product

  hermes-agent

  What to do

  Apply the vendor’s update. The NVD record links to the advisory.

  Full record and what to do →NVD recordgithub.comgithub.com

• Aug 28, 2026SiYuan before v3.8.1 contains a path traversal vulnerability in the asset.upload MCP tool that accepts arbitrary absolute file paths without workspace boundary CVE-2026-82233 · Other software · siyuan-note · reported by VulnCheckMedium 6.9

  SiYuan before v3.8.1 contains a path traversal vulnerability in the asset.upload MCP tool that accepts arbitrary absolute file paths without workspace boundary validation. Attackers can induce the AI Agent to upload sensitive files such as SSH keys or credentials from outside the workspace into the asset directory through prompt injection.

  Product

  siyuan

  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

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.