Skip to content
Agentmart
Submit a tool

MCP Audit Server

Thin MCP and CLI proxy for AI agent and MCP security auditing via a hosted backend

Connector by joepangallo · GitHub account verified by the MCP Registry

IndexedMITLocal (stdio)
Write a review

Install

Works with Claude Code, Codex, VS Code, Cursor, Windsurf, Claude Desktop. Read the repository before you give any tool access to your data.

npx agentmarket install connector/joepangallo-mcp-audit-server

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Thin MCP and CLI proxy for AI agent and MCP security auditing via a hosted backend

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this server can do and what it asks for, from its tool list and install config. Checked Oct 25, 2026.

Tools
7 read · 0 write · 0 delete · 3 not yet classified
Secrets
1 (API keys, tokens or passwords)
Install scripts
Not scanned yet
Runs as
Node.js package

Tools by what they do 10

Read from the source code; the running server may list different tools.

Read 7 · Look things up without changing anything.

  • audit_agent_dataflow
  • audit_agent_trust
  • audit_mcp_config
  • audit_mcp_server
  • audit_prompt_injection
  • harden_system_prompt
  • scan_mcp_package

Not yet classified 3 · We could not tell from the name and description.

  • fix_mcp_config
  • generate_policy
  • generate_report

Secrets and settings it asks for

Secrets: values you paste in that let it act as you.

  • AGENT_SECURITY_API_KEY

Other settings (environment variables or headers).

  • AGENT_SECURITY_BASE_URL

Tools (10)

Read from the source code; the running server may differ. Descriptions are the server’s own words; hidden characters are shown as [U+…].

  • audit_agent_dataflow

    Infer tagged-data exposure and exfiltration paths from MCP config and observed tool capabilities.

  • audit_agent_trust

    Audit an MCP or agent deployment for tool-permission inventory, execution provenance coverage, secret exposure controls, policy drift, and an overall trust score.

  • audit_mcp_config

    Perform static analysis on raw MCP config JSON and identify privilege, auth, transport, and launch risks.

  • audit_mcp_server

    Launch a target MCP server over stdio, enumerate tools, and run active security probes against its exposed tools. Requires AGENT_SECURITY_ADMIN_MODE=1.

  • audit_prompt_injection

    Perform a static prompt-hardening review against a 30+ payload prompt-injection catalog.

  • fix_mcp_config

    Auto-remediate security issues in an MCP config: remove unsafe flags, strip shell wrappers, upgrade transport to TLS, redact inline secrets, add auth placeholders, and constrain filesystem scope.

  • generate_policy

    Generate a JSON security policy from an MCP config that can be enforced by a proxy or middleware.

  • generate_report

    Combine multiple stored audit jobs into a composite report with deduplicated findings and an executive summary.

  • harden_system_prompt

    Analyze a system prompt for injection vulnerabilities and return a hardened version with security guardrails appended.

  • scan_mcp_package

    Scan an npm MCP package for dependency vulnerabilities, dangerous patterns, and permission issues.

Signals

Stars
0
Forks
0
Open issues
0
Last commit
Aug 23, 2026 (2 months ago)
Last release
Aug 24, 2026 (2 months ago)

From GitHub (fetched Oct 24, 2026).

Details

Registry name
io.github.joepangallo/mcp-audit-server
Version
3.0.1
Auth
API key
License
MIT
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from joepangallo

Cite this page

MCP Audit Server. Agent Mart. https://agentmart.dev/connectors/joepangallo-mcp-audit-server (last updated 2026-10-24)