ToolTrust Scanner

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.

---

Every MCP tool your agent calls is an attack surface — prompt injection, data exfiltration, privilege escalation, supply-chain backdoors. ToolTrust scans tool definitions before your agent trusts them and assigns a trust grade (A–F) so you know the risk. ToolTrust is an MCP Server and a CLI/CI tool — not a host, gateway, or runtime proxy. Coverage is expanding beyond today’s MCP-focused workflows; skills and additional agent tool formats are on the roadmap.

Browse the live ToolTrust Directory — trust grades and scan-backed reports before you install.

MCP demo: run a full config scan from your agent.

Scan your setup in 30 seconds

Add ToolTrust as an MCP server and let your agent audit its own tools (stdio transport — no network listener; your host launches it as a subprocess):

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

Then ask your agent: "Run tooltrust_scan_config"

It reads your MCP config, connects to each server in parallel, scans every tool, and returns a risk report with grades and enforcement decisions — all in seconds.

Or use the CLI:

curl -sfL https://raw.githubusercontent.com/AgentSafe-AI/tooltrust-scanner/main/install.sh | bash
tooltrust-scanner scan --server "npx -y @modelcontextprotocol/server-filesystem /tmp"

Example snapshot (research cohort)

The public ToolTrust Directory holds current grades and aggregates as scanning scales. One published research pass illustrates the shape of the problem — 207 MCP servers, 3,235 tools — not an exhaustive count of everything we scan today:

Metric	Count
MCP servers in cohort	207
Individual tools analyzed	3,235
Total security findings	3,613
Servers with at least one finding	145 (70%)
Servers with a clean Grade A	22 (10%)
Servers with arbitrary code execution	16

Only 10% of servers in that cohort had a clean Grade A. See tooltrust.dev for up-to-date directory-wide results (and use this table only as a labeled snapshot).

🔍 What it catches

ToolTrust runs 16 static tool-definition rules in this repo (AS-001–AS-011, AS-013–AS-017) plus 2 source-scan rules for embedded MCP implementations (AS-018, AS-019). AS-012 (tool drift) is evaluated in the ToolTrust Directory when new scan results are compared to previous runs.

ID	Severity	Detects
🛡️ AS‑001	Critical	Tool Poisoning — Adversarial prompts hidden in tool descriptions (ignore previous instructions, <INST>)
🔑 AS‑002	High/Low	Permission Surface — exec, network, db, fs beyond stated purpose; over-broad input schema
📐 AS‑003	High	Scope Mismatch — Tool name contradicts its permissions (e.g. read_config with exec)
📦 AS‑004	High/Critical	Supply Chain CVEs — Known CVEs in bundled dependencies via OSV
🔓 AS‑005	High	Privilege Escalation — admin/:write OAuth scopes; sudo/impersonate in descriptions
⚡ AS‑006	Critical	Arbitrary Code Execution — evaluate_script, _evaluate suffix, execute javascript, page.evaluate() patterns
ℹ️ AS‑007	Info	Insufficient Tool Data — Tool lacks a valid description or schema
🚨 AS‑008	Critical	Known Compromised Package — Offline embedded blacklist of confirmed supply-chain attacks (LiteLLM 1.82.7/1.82.8, Trivy v0.69.4-v0.69.6, Langflow <1.9.0, Axios 1.14.1/0.30.4). Zero-latency, no network required.
🔤 AS‑009	Medium	Typosquatting — Tool name within edit-distance 2 of a well-known MCP tool, suggesting impersonation
🗝️ AS‑010	Medium	Secret Handling — Input params accepting API keys/passwords; credentials logged insecurely
⚡ AS‑011	Low	DoS Resilience — No rate-limit, timeout, or retry config on network/exec tools
🔄 AS‑012	High	Rug-Pull — Tool set changed between scans of the same version without a version bump (directory pipeline only)
👥 AS‑013	High/Medium	Tool Shadowing — Duplicate or near-duplicate tool name hijacks calls intended for a trusted tool
ℹ️ AS‑014	Info	Dependency Inventory Unavailable — MCP server exposed neither metadata.dependencies nor a repo_url, so supply-chain coverage is limited and must be treated as incomplete
⚠️ AS‑015	Medium/High	Suspicious NPM Lifecycle Script — npm dependency publishes preinstall / postinstall / similar install-time scripts; severity rises for remote-fetch or inline-execution patterns
🚨 AS‑016	Critical	Suspicious NPM IOC Dependency — published npm metadata or install-time scripts reference a known malicious IOC package, domain, URL, or reviewed script pattern such as plain-crypto-js, even if the top-level package name is new
⚠️ AS‑017	Medium	Suspicious Data Exfiltration Description — tool description explicitly suggests sending user data, content, or conversation history to external / remote endpoints, without classifying it as prompt injection
ℹ️ AS‑018	Info	Embedded MCP Server Detected — source-level MCP SDK usage was found, but tools could not be enumerated from a manifest or live handshake, so manual review is still required
🔓 AS‑019	High	Unauthenticated MCP Route Exposure — embedded MCP HTTP routes expose the same handler without equivalent authentication middleware

Full rule details: docs/RULES.md

How it works

1. Parse — Connects to a live MCP server (or reads a JSON file) and extracts every tool definition
2. Analyze — Runs tool-definition rules against each tool's name, description, schema, and permissions; source scans add embedded MCP implementation checks
3. Grade — Assigns a numeric risk score and letter grade (A–F) per tool
4. Enforce — Maps each grade to a gateway policy: ALLOW, REQUIRE_APPROVAL, or BLOCK

Pure static analysis. No LLM calls. No data leaves your machine (except optional CVE lookups). Runs in milliseconds. Deterministic and reproducible.

Install

# One-line install (macOS / Linux)
curl -sfL https://raw.githubusercontent.com/AgentSafe-AI/tooltrust-scanner/main/install.sh | bash

# Go
go install github.com/AgentSafe-AI/tooltrust-scanner/cmd/tooltrust-scanner@latest

# npx (no install needed)
npx -y tooltrust-mcp

MCP tools

When running as an MCP server, ToolTrust exposes these tools to your agent:

Tool	What it does	Data access
tooltrust_scan_config	Scan all MCP servers in your .mcp.json or ~/.claude.json	Reads local config; spawns each server as subprocess
tooltrust_scan_server	Launch and scan a specific MCP server by command	Runs user-supplied command as subprocess (stdio)
tooltrust_scanner_scan	Scan a raw JSON blob of tool definitions	In-memory only; no subprocess or network
tooltrust_lookup	Look up a server's trust grade from the ToolTrust Directory	Network request to ToolTrust Directory API
tooltrust_list_rules	List all built-in security rules	Local catalog only

CI / GitHub Actions

Block risky MCP servers in your pipeline:

- name: Audit MCP Server
  uses: AgentSafe-AI/tooltrust-scanner@main
  with:
    server: "npx -y @modelcontextprotocol/server-filesystem /tmp"
    fail-on: "approval"

Deployment and security

For deployment, use the install paths in Install or the workflow example in CI / GitHub Actions. For vulnerability reporting and disclosure policy, see docs/SECURITY.md.

Scan-before-install gate

Never add an untrusted MCP server to your config again:

# Scans the server, then auto-installs if Grade A/B, prompts on C/D, blocks on F
tooltrust-scanner gate @modelcontextprotocol/server-memory -- /tmp

# Replace `claude mcp add` with a scanned install
alias mcp-add='tooltrust-scanner gate'

Full gate options and pre-commit hook setup: docs/USAGE.md

Add a trust badge to your project

If your MCP server passes ToolTrust, let people know:

[![ToolTrust Grade A](https://img.shields.io/badge/ToolTrust-Grade%20A-brightgreen)](https://www.tooltrust.dev/)

---

Supply-chain alert: ToolTrust detects and blocks confirmed compromised packages including LiteLLM v1.82.7/8 (TeamPCP backdoor), Trivy v0.69.4–v0.69.6, and Langflow < 1.9.0. If you encounter a Grade F with rule AS-008, remove the package immediately and rotate all credentials.

---

Usage guide · Developer guide · Contributing · Deployment & security · Changelog · Security · License: MIT

Vulnerability lookup completeness

If an OSV lookup fails (including rate limiting, service errors, malformed responses or timeouts), the scan fails with scan incomplete instead of issuing a success report or security grade. Partial lookup failure also fails the scan. CLI exits nonzero, MCP scan calls return tool errors, and gate does not install the server. This deliberately favors explicit incomplete results over availability; an OSV outage can prevent scans of tools with declared dependencies.

TOOLTRUST_OSV_URL optionally selects an OSV-compatible query endpoint (default: https://api.osv.dev/v1/query). Use only a trusted service: declared dependency names and versions are sent there. HTTPS is required, except numeric loopback HTTP for local integration fixtures; embedded credentials and fragments are rejected. There is no fallback to the public API when an override fails.

The project-local verification skill runs in GitHub Actions as CLI and MCP Verification, covering baseline paths, discovery regressions, and an owned loopback OSV fixture. Reports and command transcripts are uploaded even on failure. Live public OSV availability and MCP HTTP transport are not part of this job.