Live · 98 sources · updated 14m ago
The Security Standard

A daily wire for defenders: vulnerabilities, advisories, research, standards.

Section

Vulnerabilities

CVE records from NVD, ZDI advisories and the CISA KEV catalog, with CVSS, EPSS, SSVC and exploitation state.

Clear

32 matching records.

  1. CVE NVD

    Langflow is a tool for building and deploying AI-powered agents and workflows.

    Langflow is a tool for building and deploying AI-powered agents and workflows. Prior to 1.9.0, any authenticated Langflow user can achieve Remote Code Execution (RCE) on the server by adding an MCP server with the "Stdio"…

    CVSS 9.9 Fix available CVE-2026-105740 Anthropic AI infrastructure
  2. CVE NVD

    NetLicensing MCP Server is a natural-language interface that enables agentic applications to manage the software-licensing lifecycle in Labs64…

    NetLicensing MCP Server is a natural-language interface that enables agentic applications to manage the software-licensing lifecycle in Labs64 NetLicensing. Prior to 0.1.8, netlicensing_get_product passes the caller-controlled…

    CVSS 9.6 CVE-2026-57496 Anthropic AI infrastructure
  3. CVE NVD

    obsidian-tc is a governed, agent-ready Model Context Protocol server for Obsidian vaults.

    obsidian-tc is a governed, agent-ready Model Context Protocol server for Obsidian vaults. Prior to 1.3.1, tool dispatch does not compare the caller-controlled input.vault value with the vault bound to the caller, the JSON Web…

    CVSS 9.9 CVE-2026-77366 Anthropic AI infrastructure
  4. CVE NVD

    Langflow is a tool for building and deploying AI-powered agents and workflows.

    Langflow is a tool for building and deploying AI-powered agents and workflows. Before Langflow 1.10.3, the MCP stdio transport launched whatever command / args a user put in an MCP server configuration, with no allowlist and…

    CVSS 9.9 CVE-2026-105697 Anthropic AI infrastructure
  5. CVE NVD

    MCP TypeScript SDK is the official TypeScript SDK for Model Context Protocol servers and clients.

    MCP TypeScript SDK is the official TypeScript SDK for Model Context Protocol servers and clients. From version 1.24.0 to before version 1.32.0, the experimental tasks feature (taskStore) did not check which session created a…

    CVSS 8.6 Fix available CVE-2026-111767 Node.js Anthropic Developer platform
  6. CVE NVD

    Langflow is a tool for building and deploying AI-powered agents and workflows.

    Langflow is a tool for building and deploying AI-powered agents and workflows. From 1.5.0 until 1.10.3, an IP spoofing vulnerability in the Model Context Protocol (MCP) configuration installation endpoint (POST…

    CVSS 7.1 Fix available CVE-2026-105741 Anthropic AI infrastructure
  7. CVE NVD

    In JetBrains Junie CLI before 26.8.3 code execution was possible via an untrusted project's MCP server configuration

    In JetBrains Junie CLI before 26.8.3 code execution was possible via an untrusted project's MCP server configuration

    CVSS 7.8 CVE-2026-111091 JetBrains Anthropic AI infrastructure
  8. CVE NVD

    The Model Context Protocol Python SDK is the official Python SDK for Model Context Protocol servers and clients.

    The Model Context Protocol Python SDK is the official Python SDK for Model Context Protocol servers and clients. In mcp versions before 1.29.1 and from 2.0.0a1 through 2.0.1, the Streamable HTTP session manager, SSE message…

    CVSS 7.5 CVE-2026-109527 Anthropic AI infrastructure
  9. CVE NVD

    obsidian-tc is a governed, agent-ready Model Context Protocol server for Obsidian vaults.

    obsidian-tc is a governed, agent-ready Model Context Protocol server for Obsidian vaults. Prior to 1.3.1, the Streamable HTTP transport does not validate the Host or Origin header or enable DNS-rebinding protection. When the…

    CVSS 8.8 CVE-2026-77363 Anthropic AI infrastructure
  10. CVE NVD

    MCP TypeScript SDK is the official TypeScript SDK for Model Context Protocol servers and clients.

    MCP TypeScript SDK is the official TypeScript SDK for Model Context Protocol servers and clients. Starting in version 1.12.0 and prior to versions 1.31.0 and 2.2.0, the SDK's OAuth client support let the MCP server a client…

    CVSS 7.5 CVE-2026-104850 Node.js Anthropic Developer platform
  11. CVE NVD

    NetBox MCP Server is a simple read-only Model Context Protocol server for NetBox.

    NetBox MCP Server is a simple read-only Model Context Protocol server for NetBox. Prior to version 1.2.1, when running with TRANSPORT=http, the MCP server has no authentication on the HTTP endpoint. Any client that can reach the…

    CVSS 5.9 Fix available CVE-2026-57207 Anthropic AI infrastructure
  12. CVE NVD

    Claude Agent SDK is a Python SDK for Claude Code.

    Claude Agent SDK is a Python SDK for Claude Code. Prior to 0.2.121, the resume option is passed to the Claude CLI as a separate token without validation, so a dash-leading value is parsed as an independent CLI flag. An attacker…

    Fix available CVE-2026-96620 Anthropic AI infrastructure
  13. CVE NVD

    x64dbg-MCP Server is a native Model Context Protocol (MCP) plugin for x64dbg that exposes the debugger's full functionality over HTTP.

    x64dbg-MCP Server is a native Model Context Protocol (MCP) plugin for x64dbg that exposes the debugger's full functionality over HTTP. Prior to 1.1, x64dbg-MCP Server exposes all MCP debugger tools over HTTP and SSE without…

    Fix available CVE-2026-107824 Anthropic AI infrastructure
  14. CVE NVD

    Next.js is a React framework for building full-stack web applications.

    Next.js is a React framework for building full-stack web applications. From 16.0.0 until 16.3.8, the next dev development server exposes a Model Context Protocol endpoint without reliably restricting cross-site requests. A…

    Fix available CVE-2026-94486 Node.js Anthropic Developer platform
  15. CVE NVD

    Next.js is a React framework for building full-stack web applications.

    Next.js is a React framework for building full-stack web applications. From 16.0.0 until 16.3.8, the `next dev` development server exposes a Model Context Protocol endpoint without reliably restricting cross-site requests. A…

    Fix available CVE-2026-94485 Node.js Anthropic Developer platform
  16. CVE NVD

    An incomplete list of disallowed inputs in the Python code validator of the run_script tool in AWS MCP Server might allow an authenticated remote…

    An incomplete list of disallowed inputs in the Python code validator of the run_script tool in AWS MCP Server might allow an authenticated remote user to execute arbitrary code within their own isolated session environment via a…

    CVSS 6.4 CVE-2026-115845 Anthropic AI infrastructure
  17. CVE NVD

    obsidian-tc is a governed, agent-ready Model Context Protocol server for Obsidian vaults.

    obsidian-tc is a governed, agent-ready Model Context Protocol server for Obsidian vaults. Prior to 1.3.1, bridge tools do not consistently apply the read access-control list (ACL) to every returned field. The tasks_filter tool…

    CVSS 4.3 CVE-2026-77362 Anthropic AI infrastructure
  18. CVE NVD

    obsidian-tc is a governed, agent-ready Model Context Protocol server for Obsidian vaults.

    obsidian-tc is a governed, agent-ready Model Context Protocol server for Obsidian vaults. Prior to 1.3.1, read access-control list (ACL) checks use a lexical vault-relative path while containment checks use the resolved path. An…

    CVSS 4.7 CVE-2026-77361 Anthropic AI infrastructure
  19. CVE NVD

    obsidian-tc is a governed, agent-ready Model Context Protocol server for Obsidian vaults.

    obsidian-tc is a governed, agent-ready Model Context Protocol server for Obsidian vaults. Prior to 1.3.1, undefined readPaths and writePaths settings allow all paths, strictReadDefault does not protect direct requests, and the…

    CVSS 6.5 CVE-2026-77364 Anthropic AI infrastructure
  20. CVE NVD

    UnicomAI Wanwu through 0.6.5 contains an authorization bypass vulnerability that allows authenticated users to mint AppKeys bound to other users' MCP…

    UnicomAI Wanwu through 0.6.5 contains an authorization bypass vulnerability that allows authenticated users to mint AppKeys bound to other users' MCP servers via POST /v1/appspace/app/key. Attackers supplying a victim's MCP…

    CVSS 4.2 CVE-2026-108856 Anthropic AI infrastructure
  21. CVE NVD

    JeecgBoot through 3.9.5 contains a missing authorization vulnerability that allows any authenticated user to read MCP server configurations because…

    JeecgBoot through 3.9.5 contains a missing authorization vulnerability that allows any authenticated user to read MCP server configurations because the queryById permission check is commented out. Attackers can obtain record ids…

    CVSS 6.5 CVE-2026-108671 Anthropic AI infrastructure
  22. CVE NVD

    1MCP Agent (@1mcp/agent) 0.20.0 through 0.39.0 contains an incorrect authorization vulnerability that allows authenticated clients to bypass OAuth…

    1MCP Agent (@1mcp/agent) 0.20.0 through 0.39.0 contains an incorrect authorization vulnerability that allows authenticated clients to bypass OAuth tag-scope enforcement using negated advanced tag-filter expressions. Attackers…

    CVSS 5.4 CVE-2026-108586 Anthropic AI infrastructure
  23. CVE NVD

    argocd-mcp (Argo CD MCP Server) through 0.9.0 contains a path traversal vulnerability in the delete_application tool that allows MCP clients to reach…

    argocd-mcp (Argo CD MCP Server) through 0.9.0 contains a path traversal vulnerability in the delete_application tool that allows MCP clients to reach unintended API endpoints via unvalidated applicationName values. Attackers or…

    CVSS 5.4 CVE-2026-108585 Argo Anthropic Developer platform
  24. CVE NVD

    x64dbg-MCP Server is a native Model Context Protocol (MCP) plugin for x64dbg that exposes the debugger's full functionality over HTTP.

    x64dbg-MCP Server is a native Model Context Protocol (MCP) plugin for x64dbg that exposes the debugger's full functionality over HTTP. Prior to 1.2, src/core/mcp_server.zig parses an unbounded Content-Length value in…

    CVSS 5.3 CVE-2026-107820 Anthropic AI infrastructure
  25. CVE NVD

    In Splunk MCP Server versions below 1.2.1, Splunk MCP Server could send the Splunk platform authentication token of a user who runs a custom…

    In Splunk MCP Server versions below 1.2.1, Splunk MCP Server could send the Splunk platform authentication token of a user who runs a custom Application Programming Interface (API) tool to the URL configured for that tool. If…

    CVSS 5.3 CVE-2026-76286 Splunk Anthropic Network management
  26. CVE NVD

    obsidian-tc is a governed, agent-ready Model Context Protocol server for Obsidian vaults.

    obsidian-tc is a governed, agent-ready Model Context Protocol server for Obsidian vaults. From 1.0.1 until 1.31.4, `create_entity`, `link_entities`, `rename_entity`, `unlink_entities` and `delete_entity` regenerate memory notes…

  27. CVE NVD

    obsidian-tc is a governed, agent-ready Model Context Protocol server for Obsidian vaults.

    obsidian-tc is a governed, agent-ready Model Context Protocol server for Obsidian vaults. From 1.13.0 until 1.31.4, on a Streamable HTTP deployment with `auth.jwtSecret` configured and a 2026-07-28-era client declaring…

    CVE-2026-115477 Anthropic AI infrastructure
  28. CVE NVD

    Z.ai ZCode v3.11.2.6792 was discovered to automatically establish connections with MCP servers declared inside a repository's workspace…

    Z.ai ZCode v3.11.2.6792 was discovered to automatically establish connections with MCP servers declared inside a repository's workspace configuration, possibly allowing attackers to execute arbitrary code via opening a crafted…

    CVE-2026-88755 Anthropic AI infrastructure
  29. CVE NVD

    The MCP Python SDK, called mcp on PyPI, is a Python implementation of the Model Context Protocol (MCP).

    The MCP Python SDK, called mcp on PyPI, is a Python implementation of the Model Context Protocol (MCP). From 1.8.0 until 1.30.0 and 2.2.0, stateful Streamable HTTP servers, including FastMCP, MCPServer…

    CVE-2026-59951 Anthropic Developer platform
  30. CVE NVD

    phpMyFAQ through 4.1.10 contains a missing authorization vulnerability in the MCP server faq_search tool that allows MCP clients to read restricted…

    phpMyFAQ through 4.1.10 contains a missing authorization vulnerability in the MCP server faq_search tool that allows MCP clients to read restricted FAQs because Search::searchDatabase() never applies user or group permission…

    CVSS 3.3 CVE-2026-108851 Anthropic AI infrastructure
  31. CVE NVD

    Docker Sandboxes could fail open while masking credentials in protected proxy responses.

    Docker Sandboxes could fail open while masking credentials in protected proxy responses. When a response-body read returned data together with an error, affected handlers could forward unmasked bytes. Code inside an authorized…

    CVE-2026-101998 Anthropic AI infrastructure
  32. CVE NVD

    Claude Code validated that a target file path resided within the project working directory at permission-check time, but re-resolved the path at…

    Claude Code validated that a target file path resided within the project working directory at permission-check time, but re-resolved the path at write time without repeating that validation. This time-of-check to time-of-use…

    CVE-2026-103435 Anthropic AI infrastructure

Reuse this view

Same filters as JSON: /api/items?category=vuln&window=30d&vendor=Anthropic&limit=100. RSS for this section: feed.xml.

Keyboard

j / k
Next / previous item
o or Enter
Open the original source
i
Open the item page
s
Save or unsave for later
/
Focus search
g then f v a r n s
Go to front, vulnerabilities, advisories, research, news, standards
t
Toggle theme
?
This help