mcp-audit
Server Details
Security audit for MCP servers: command injection, unsafe file access, secrets, prompt injection.
- Status
- Healthy
- Uptime
- 100.0% over the last 24 hours
- Last Tested
- Transport
- Streamable HTTP · MCP 2025-11-25
- URL
- ChatGPT
- –
- Claude
- –
TDQS
Scored across 1 tool
There is only one tool, so an agent cannot misselect between competing options. Its purpose (security audit of a local MCP server project) is stated unambiguously.
The single name scan_mcp_server follows a clear verb_noun snake_case convention that matches the server's domain. No mixed conventions exist to trip up an agent.
A one-tool surface is thin even for a focused audit utility; there is no way to scope, configure, or follow up on a scan. The tool itself is non-trivial and earns its place, but the surface feels under-built.
The core operation (scan a path, return a structured risk list) exists, but there are no companion operations such as listing available rules, filtering by severity, or fetching/exporting detailed findings. Agents can complete the primary workflow but hit dead ends for anything beyond a single fire-and-forget scan.
Available Tools
1 toolscan_mcp_serverCInspect
审计一个 MCP server 项目(本地路径)的安全风险,返回结构化风险清单
Inputs: path (required), include_tests. Returns: result
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Related MCP Connectors
Security scanner for MCP servers. Detect vulnerabilities, prompt injection, and tool poisoning.
Audit your MCP servers for poisoned tools and leaked secrets, and check AI-generated code for flaws.
Security scanner for AI agents and MCP servers: injection, jailbreak, tool abuse.
MCP server: static security scanner for MCP servers, agent skills & plugins. 17 attack patterns.
Related MCP Servers
- AlicenseNot gradedqualityCmaintenanceSecurity scanner for MCP servers. Detects prompt injection, command injection, auth bypass, and excessive permissions across tools, resources, and prompts.24 npm3MIT
- AlicenseNot gradedqualityDmaintenanceAudit any MCP server for tool-poisoning, prompt-injection, and data-exfiltration risk before connecting an agent.MIT
- AlicenseAqualityDmaintenanceScans MCP servers for prompt-injection, tool-poisoning, and SSRF vulnerabilities using 30+ canonical rules across 5 severity tiers, with optional signed safety reports for procurement.5MIT
- AlicenseNot gradedqualityDmaintenanceScans MCP servers for security vulnerabilities, prompt injection, and tool poisoning, providing risk scores and protection.4MIT
Glama MCP Gateway
Add one secure layer between your agents and this server.