375 matches found
scopeblind-gateway
⚠️ This repository has moved. Active development continues at ScopeBlind/scopeblind-gateway. This personal fork may be behind the canonical repository. Please use the org repo for issues, pull requests, and the latest code. protect-mcp Security gateway for MCP servers. Shadow-mode logs by default,...
mcp-stdio-shellguard
Part of theStudioMeyer MCP Stack — Built in Mallorca 🌴 · ⭐ if you use it mcp-stdio-shellguard Defense-in-depth bundle for MCP stdio servers. Wraps childprocess.exec/spawn with allowlist + sandbox + replay-detection, plus an AST audit CLI mcp-shellguard-audit that scans MCP server sources for...
Bifrost < 2.1.0 - Unauthenticated MCP Stdio Command Execution
When dashboard authentication is disabled, Bifrost accepts an unauthenticated stdio MCP client registration and starts its configured command before the MCP handshake completes. This template runs a benign outbound HTTP request from the target and requires an out-of-band callback to confirm comma...
mcpshield
mcpshield A drop-in fix for the unpatched MCP STDIO command-injection flaw the CVE-2026-30623 family, disclosed by OX Security in April 2026 as "by design" -- no SDK patch is coming. Import one line, and every stdio MCP server your Python app launches gets its command/args/env validated before th...
Langflow 1.8.3 and 1.9.0 - Authenticated MCP Stdio Command Execution
An authenticated user can register an MCP stdio server command that executes when Langflow lists server actions. The 1.9.0 REST validation can be bypassed by placing arguments in the command field. This probe runs a short Python callback, verifies an out-of-band DNS lookup, and removes its server...
CVE-2026-42271-PoC
CVE-2026-42271 — LiteLLM Authenticated Command Injection via MCP stdio Test Endpoints LiteLLM POST /mcp-rest/test/connection & POST /mcp-rest/test/tools/list — Authenticated command injection via MCP stdio transport. Any valid API key can execute arbitrary OS commands as root in default Docker...
CVE-2025-6514
mcp-remote Connect an MCP Client that only supports local stdio servers to a Remote MCP Server, with auth support: Note: this is a working proof-of-concept but should be considered experimental. Why is this necessary? So far, the majority of MCP servers in the wild are installed locally, using th...
CVE-2026-12940-Langflow-Unauth-RCE
CVE-2026-12940 — Langflow OSS ≤ 1.10.1 Unauthenticated RCE MCP stdio env-var injection Unauthenticated remote code execution in Langflow OSS through 1.10.1. The environment-variable blocklist that guards MCP stdio server configuration DANGEROUSENVVARS omits SHELLOPTS, BASHOPTS and PS4. Because th...
LiteLLM - Command Injection
A critical unauthenticated remote code execution vulnerability exists in LiteLLM due to improper input handling in the MCP stdio test endpoint. An attacker can send a specially crafted request to the /mcp-rest/test/connection endpoint with controlled parameters, resulting in arbitrary command...
CVE-2026-67546
Heym builds and runs agentic systems and business-process automations on self-hosted infrastructure. Prior to version 0.0.75, the same POST /api/mcp/fetch-tools endpoint any authenticated user, lowest role also accepts the stdio transport, which spawns the attacker-supplied command with...
EUVD-2026-124047
Heym builds and runs agentic systems and business-process automations on self-hosted infrastructure. Prior to version 0.0.75, the same POST /api/mcp/fetch-tools endpoint any authenticated user, lowest role also accepts the stdio transport, which spawns the attacker-supplied command with...
CVE-2026-67546
Heym builds and runs agentic systems and business-process automations on self-hosted infrastructure. Prior to version 0.0.75, the same POST /api/mcp/fetch-tools endpoint any authenticated user, lowest role also accepts the stdio transport, which spawns the attacker-supplied command with...
CVE-2026-67546 Heym: Command execution via POST /api/mcp/fetch-tools stdio transport: supplied command is spawned before MCP validation
Heym builds and runs agentic systems and business-process automations on self-hosted infrastructure. Prior to version 0.0.75, the same POST /api/mcp/fetch-tools endpoint any authenticated user, lowest role also accepts the stdio transport, which spawns the attacker-supplied command with...
CVE-2026-67546
The Heym agentic systems and business-process automation platform is vulnerable to arbitrary command execution via the POST /api/mcp/fetch-tools endpoint in versions prior to 0.0.75 . An authenticated user with the lowest role can exploit this by providing a stdio transport , which causes the sys...
CVE-2026-67546 Heym: Command execution via POST /api/mcp/fetch-tools stdio transport: supplied command is spawned before MCP validation
Heym builds and runs agentic systems and business-process automations on self-hosted infrastructure. Prior to version 0.0.75, the same POST /api/mcp/fetch-tools endpoint any authenticated user, lowest role also accepts the stdio transport, which spawns the attacker-supplied command with...
CVE-2026-67546: heymrun heym: Heym builds and runs agentic systems and business-process automations on self-hosted infrastructure
Heym builds and runs agentic systems and business-process automations on self-hosted infrastructure. Prior to version 0.0.75, the same POST /api/mcp/fetch-tools endpoint any authenticated user, lowest role also accepts the stdio transport, which spawns the attacker-supplied command with...
PT-2026-145533
Heym builds and runs agentic systems and business-process automations on self-hosted infrastructure. Prior to version 0.0.75, the same POST /api/mcp/fetch-tools endpoint any authenticated user, lowest role also accepts the stdio transport, which spawns the attacker-supplied command with...
EUVD-2026-117780
Code Graph RAG: MCP paginated readfile path traversal / arbitrary file read...
CVE-2026-77604
Code Graph RAG is an AI-powered knowledge graph and retrieval system for querying, understanding, and editing multi-language codebases. Prior to 0.0.345, the MCPToolsRegistry.readfile implementation in codebaserag/mcp/tools.py joins attacker-controlled filepath input to projectroot without...
CVE-2026-77604
Prior to version 0.0.345 , Code Graph RAG is vulnerable to arbitrary file read via a path traversal flaw in the MCPToolsRegistry.read_file implementation located in codebase_rag/mcp/tools.py. The root cause is that the paginated branch of the code joins attacker-controlled file_path input to proj...