ToolTrust Scanner MCP Server

Static security scanner for MCP tool definitions Trust grades (A–F) before your agent calls a tool - run as an MCP server , CLI , or CI check. It runs locally over stdio via the published package.

People connecting security tools to Claude, Cursor, VS Code, or another MCP client. The project is written in Go.

VERIFIED ACTIVE

LAST COMMIT 2026-08-20 · ★ 19 · #38 OF 182 MAINTAINED SECURITY · VERIFIED 2026-08-25

MIT · Go servers · how we verify → /methodology

01 · Install ToolTrust Scanner

Claude Code

claude mcp add agentsafe-ai-tooltrust-scanner -- npx -y tooltrust-mcp

Claude Desktop / Cursor / VS Code - add to config

{
  "mcpServers": {
    "agentsafe-ai-tooltrust-scanner": {
      "command": "npx",
      "args": [
        "-y",
        "tooltrust-mcp"
      ]
    }
  }
}

Same JSON for Cursor. For VS Code, rename the top-level key from `mcpServers` to `servers`.

Using another client? Same JSON, different key

Claude Desktop · mcpServers

Cursor · mcpServers

VS Code · servers

Windsurf · mcpServers

Zed · context_servers

Cline · mcpServers

Roo Code · mcpServers

Continue · mcpServers

LibreChat · mcpServers

Gemini CLI · mcpServers

Codex CLI · mcp_servers

Full setup guides: every client.

02 · Evidence

Security posture

What to check before giving this server access to your agent - from the registry, GitHub, and our own probes. We don't score safety; we show what's verifiable.

runs as local process (stdio) - runs on your machine with your user's permissions

license MIT - declared in the repository

npm package tooltrust-mcp - unscoped; check the name against the project README before installing

registry namespace io.github.AgentSafe-AI is GitHub-verified and matches the repo owner

03 · What ToolTrust Scanner can do

Prose above is summarized from the project's README and registry record - no invented capabilities.

Latest releases

v0.3.19 · 2026-06-21

Update Homebrew formula for v0.3.18 · blacklist 9 MCP/AI malicious npm packages (AS-008, 0.3.19)

v0.3.18 · 2026-06-16

bump npm wrapper to v0.3.17 binary (1.1.12) · Update Homebrew formula for v0.3.17 · blacklist claudechor (npm) - Claude typosquat (AS-008, 0.3.18)

v0.3.17 · 2026-06-15

bump npm wrapper to v0.3.16 binary (1.1.11) · AS-002 capability-disclosure summary + AS-006 expression FP (0.3.17)

04 · Who maintains ToolTrust Scanner

ToolTrust Scanner is maintained by agentsafe-ai. It's the only MCP server we track from this author; the repo dates to Mar 2026.

05 · Facts

repository: github.com/agentsafe-ai/tooltrust-scanner
category: security - ranked #38 of 182 actively-maintained security servers as of 2026-08-25.
release cadence: 6 releases in the last 90 days (latest 2026-06-21)
registry: io.github.AgentSafe-AI/tooltrust-scanner (active, first published 2026-03-31)
packages: npm:tooltrust-mcp

06 · ToolTrust Scanner FAQ

What is ToolTrust Scanner?

Static security scanner for MCP tool definitions Trust grades (A–F) before your agent calls a tool - run as an MCP server , CLI , or CI check. It runs locally over stdio via the published package.

Is ToolTrust Scanner still maintained?

Yes - as of 2026-08-25, its last commit was 2026-08-20 and it shipped 6 releases in the last 90 days. We re-verify nightly.

How do I install ToolTrust Scanner?

Run `npx -y tooltrust-mcp`. You can also paste the ready-made client config above.

Does ToolTrust Scanner run locally?

Yes - it's a stdio server: it runs on your machine (via npx) with your user's permissions. Your data stays local unless the server itself calls external APIs.

07 · Alternatives to ToolTrust Scanner

Alternatives to ToolTrust Scanner

Maintained security servers if ToolTrust Scanner isn't the fit.

Pairs well with

Servers that cover what ToolTrust Scanner doesn't - only shown when the pairing reason fits the companion.

More security MCP servers · Enigmagent MCP · Prism Scanner · AIGEN - Open Bounty Protocol for AI Agents · Healthclaw Guardrails · Linkedctl

More Go MCP servers · Dibs · Dir MCP · Git Courer · Spotdb · Argon · see all