CVE-2026-34884

Apache SkyWalking MCP version 0.1.0 is affected by two vulnerabilities: an SSRF via the set_skywalking_url tool and a GraphQL expression injection in the MCP Server. Both are exploitable over the network with no privileges and no user interaction required, carrying a CVSS 3.1 score of 9.8 (Critic...

CVE-2026-34884 Apache SkyWalking MCP: SSRF via set_skywalking_url Tool and GraphQL Expression Injection in MCP Server

SSRF via setskywalkingurl Tool and GraphQL expression injection vulnerability in Apache SkyWalking MCP. This issue affects Apache SkyWalking MCP: 0.1.0. Users are recommended to upgrade to version 0.2.0, which fixes this issue...

CVE-2026-53766

creationtimestamp| type| source ---|---|--- 2026-08-17 22:35:16+00:00| published-proof-of-concept| https://github.com/ChromeDevTools/chrome-devtools-mcp/security/advisories/GHSA-8qf9-62x2-82pp 2026-08-18 02:33:46+00:00| seen| https://gist.github.com/alon710/259d2014ae004d0972fa015a9b341f1e...

chrome-devtools-mcp: validatePath() does not canonicalize symlinks before enforcing roots

Summary I originally reported this through Google Bug Hunters. The Google Bug Hunters team said this is in OSS VRP scope but not reward-eligible due to the project tier, and asked me to file an issue or PR directly with this repository. I am reporting it privately here first because it is an...

atomic-agents-stack: HTTP MCP catalog accepts cleartext http and spawns catalog-supplied commands (MITM to RCE)

The HTTP MCP server-registry backend factory atomicagents/mcpregistry/http.py, makehttpmcpserverregistrybackendfromurl accepts both http and https schemes. Catalog entries carry command/args that are type-validated but content-unrestricted, and are later spawned as local stdio subprocesses by...

CVE-2026-71424 Onyx: Cross-user OAuth-token leak via /api/mcp/servers* for per-user MCP servers

Onyx is an open-source AI platform. Prior to 3.1.10, 3.2.14, and 4.0.0, Onyx's GET /api/mcp/servers and GET /api/mcp/servers/persona/personaid endpoints expose another user's OAuth Authorization header because OnyxTokenStorage.settokens and OnyxTokenStorage.setclientinfo in...

EUVD-2026-60479

Onyx is an open-source AI platform. Prior to 3.1.10, 3.2.14, and 4.0.0, Onyx's GET /api/mcp/servers and GET /api/mcp/servers/persona/personaid endpoints expose another user's OAuth Authorization header because OnyxTokenStorage.settokens and OnyxTokenStorage.setclientinfo in...

CVE-2026-71424

Onyx is an open-source AI platform. Prior to 3.1.10, 3.2.14, and 4.0.0, Onyx's GET /api/mcp/servers and GET /api/mcp/servers/persona/personaid endpoints expose another user's OAuth Authorization header because OnyxTokenStorage.settokens and OnyxTokenStorage.setclientinfo in...

CVE-2026-71424 Onyx: Cross-user OAuth-token leak via /api/mcp/servers* for per-user MCP servers

Onyx is an open-source AI platform. Prior to 3.1.10, 3.2.14, and 4.0.0, Onyx's GET /api/mcp/servers and GET /api/mcp/servers/persona/personaid endpoints expose another user's OAuth Authorization header because OnyxTokenStorage.settokens and OnyxTokenStorage.setclientinfo in...

CVE-2026-71424

CVE-2026-71424 is a critical cross-user OAuth token leak in Onyx , an open-source AI platform. The GET /api/mcp/servers and GET /api/mcp/servers/persona/{persona_id} endpoints expose another user's OAuth Authorization header. The root cause is that OnyxTokenStorage.set_tokens and OnyxTokenStorage...

CVE-2026-75060

In JetBrains PyCharm before 2026.2.1 code execution was possible via unauthenticated Jupyter MCP tools...

CVE-2026-74858

A vulnerability has been found in jae-jae fetcher-mcp up to 0.3.9. Impacted is the function fetchurl/fetchurls of the file /latest/meta-data/iam/security-credentials/ of the component URL Validation. Such manipulation leads to server-side request forgery. It is possible to launch the attack...

CVE-2026-75060

In JetBrains PyCharm before 2026.2.1 code execution was possible via unauthenticated Jupyter MCP tools...

CVE-2026-75060

JetBrains PyCharm versions prior to 2026.2.1 are vulnerable to unauthenticated remote code execution through Jupyter MCP (Model Context Protocol) tools. MCP is a standard that allows AI models to access data and tools from external sources; in this case, the Jupyter MCP tools in PyCharm could be ...

CVE-2026-75060

In JetBrains PyCharm before 2026.2.1 code execution was possible via unauthenticated Jupyter MCP tools...

EUVD-2026-60259

In JetBrains PyCharm before 2026.2.1 code execution was possible via unauthenticated Jupyter MCP tools...

CVE-2026-75060

In JetBrains PyCharm before 2026.2.1 code execution was possible via unauthenticated Jupyter MCP tools...

EUVD-2026-60234

A vulnerability has been found in jae-jae fetcher-mcp up to 0.3.9. Impacted is the function fetchurl/fetchurls of the file /latest/meta-data/iam/security-credentials/ of the component URL Validation. Such manipulation leads to server-side request forgery. It is possible to launch the attack...

CVE-2026-74858 jae-jae fetcher-mcp URL Validation security-credentials fetch_urls server-side request forgery

A vulnerability has been found in jae-jae fetcher-mcp up to 0.3.9. Impacted is the function fetchurl/fetchurls of the file /latest/meta-data/iam/security-credentials/ of the component URL Validation. Such manipulation leads to server-side request forgery. It is possible to launch the attack...

CVE-2026-74858

A vulnerability has been found in jae-jae fetcher-mcp up to 0.3.9. Impacted is the function fetchurl/fetchurls of the file /latest/meta-data/iam/security-credentials/ of the component URL Validation. Such manipulation leads to server-side request forgery. It is possible to launch the attack...