inspector

MCP Inspector A developer tool for inspecting Model Context Protocol MCP servers. It ships as a single package, @modelcontextprotocol/inspector, that provides four ways to inspect a server: Web — a Vite + React + Mantine single-page app with a Node backend. CLI — a scriptable command-line client...

agent-router: MCP session resume does not verify the embedded anti-hijacking subject; default Helm seed makes session IDs forgeable

Summary The MCP proxy's client-facing session ID embeds the authenticated caller's subject JWT sub claim specifically as an anti-hijacking discriminator — matching the Model Context Protocol specification's documented session-hijacking guidance...

CVE-2026-103091 Insecure Default Policy and Unrestricted OIDC Enrollment in Google OSS Agent Mesh (SAM)

Missing Authorization CWE-862 and Initialization of a Resource with an Insecure Default CWE-1188 in the MCP proxy HandleStreamPassThrough in mcpservice.go and OIDC registration flow GET /info and POST /register in internal/controlplane/server.go in Google OSS Agent Mesh SAM versions 0.1.0-alpha.1...

CVE-2026-103091 Insecure Default Policy and Unrestricted OIDC Enrollment in Google OSS Agent Mesh (SAM)

Missing Authorization CWE-862 and Initialization of a Resource with an Insecure Default CWE-1188 in the MCP proxy HandleStreamPassThrough in mcpservice.go and OIDC registration flow GET /info and POST /register in internal/controlplane/server.go in Google OSS Agent Mesh SAM versions 0.1.0-alpha.1...

CVE-2026-103091

Google OSS Agent Mesh (SAM) versions 0.1.0-alpha.1 through 0.1.0-alpha.8 are vulnerable to Missing Authorization (CWE-862) and Insecure Default (CWE-1188) . The issue originates in the MCP proxy (HandleStreamPassThrough in mcp_service.go) and the OIDC registration flow (GET /info and POST /regist...

CVE-2026-103091 Insecure Default Policy and Unrestricted OIDC Enrollment in Google OSS Agent Mesh (SAM)

Missing Authorization CWE-862 and Initialization of a Resource with an Insecure Default CWE-1188 in the MCP proxy HandleStreamPassThrough in mcpservice.go and OIDC registration flow GET /info and POST /register in internal/controlplane/server.go in Google OSS Agent Mesh SAM versions 0.1.0-alpha.1...

mcp-pwn

CVE-2026-23744 — MCPJam Unauthenticated Remote Code Execution Summary MCPJam is an open-source MCP Model Context Protocol inspector and proxy used to connect, debug, and manage MCP servers. Versions = 1.4.3 Attack Vector| Network — No Authentication Required Disclosure| 2026-01-15 Technical...

mcp-doorman

mcp-doorman The security gateway for MCP servers — every tool call gets checked at the door. CI npm License: Apache-2.0 PRs welcome mcp-doorman is a drop-in proxy that sits between your AI agent Claude Desktop, Claude Code, Cursor, VS Code, any MCP client and the MCP servers it uses. One command,...

Aegis-releases

Aegis Claude Code's sandbox lets an agent read your SSH keys and AWS credentials by default. Aegis doesn't. Two layers, both verified on real hardware. Kernel sandbox — the agent's own shell cannot reach a denied path: $ ! cat /.ssh/idrsa cat: /Users/you/.ssh/idrsa: Operation not permitted $ ! ca...

LiteLLM: MCP Proxy Has Improper Authentication

A weakness has been identified in BerriAI litellm up to 1.59.8. Affected is the function UserAPIKeyAuth of the file litellm/proxy/experimental/mcpserver/auth/userapikeyauthmcp.py of the component MCP Proxy. Executing a manipulation can lead to improper authentication. The attack may be launched...

PYSEC-2026-4067 LiteLLM: MCP Proxy Has Improper Authentication

A weakness has been identified in BerriAI litellm up to 1.59.8. Affected is the function UserAPIKeyAuth of the file litellm/proxy/experimental/mcpserver/auth/userapikeyauthmcp.py of the component MCP Proxy. Executing a manipulation can lead to improper authentication. The attack may be launched...

PT-2026-105823

A weakness has been identified in BerriAI litellm up to 1.59.8. Affected is the function UserAPIKeyAuth of the file litellm/proxy/ experimental/mcp server/auth/user api key auth mcp.py of the component MCP Proxy. Executing a manipulation can lead to improper authentication. The attack may be...

CVE-2026-79538

metatool-ai MetaMCP up to and including 2.4.22 is vulnerable to Code Execution in the internal MCP inspector proxy endpoint GET /mcp-proxy/server/stdio createTransport, STDIO branch, routers/mcp-proxy/server.ts...

CVE-2026-79538

metatool-ai MetaMCP up to and including 2.4.22 is vulnerable to Code Execution in the internal MCP inspector proxy endpoint GET /mcp-proxy/server/stdio createTransport, STDIO branch, routers/mcp-proxy/server.ts...

CVE-2026-79538

The metatool-ai MetaMCP software, specifically version 2.4.22 and below, is vulnerable to Code Execution . This vulnerability exists in the internal MCP inspector proxy endpoint at GET /mcp-proxy/server/stdio. The root cause is located within the createTransport function in the STDIO branch , spe...

PT-2026-102885

metatool-ai MetaMCP up to and including 2.4.22 is vulnerable to Code Execution in the internal MCP inspector proxy endpoint GET /mcp-proxy/server/stdio createTransport, STDIO branch, routers/mcp-proxy/server.ts...

CVE-2026-79538: Improper Control of Generation of Code

metatool-ai MetaMCP up to and including 2.4.22 is vulnerable to Code Execution in the internal MCP inspector proxy endpoint GET /mcp-proxy/server/stdio createTransport, STDIO branch, routers/mcp-proxy/server.ts...

CVE-2026-79538

metatool-ai MetaMCP up to and including 2.4.22 is vulnerable to Code Execution in the internal MCP inspector proxy endpoint GET /mcp-proxy/server/stdio createTransport, STDIO branch, routers/mcp-proxy/server.ts...

EUVD-2026-89360

metatool-ai MetaMCP up to and including 2.4.22 is vulnerable to Code Execution in the internal MCP inspector proxy endpoint GET /mcp-proxy/server/stdio createTransport, STDIO branch, routers/mcp-proxy/server.ts...

CVE-2026-58197

ToolHive is a utility designed to simplify the deployment and management of Model Context Protocol servers. Prior to ToolHive CLI 0.30.1 and ToolHive Studio 0.38.0, locally run MCP server containers use the default network permission profile without network isolation, permitting access to...