ToolTrust Directory
AgentSafe-AI/tooltrust-directory
Registro seguro de MCP servers com scoring A-F de risco
Ver no GitHubRegistro público e continuamente atualizado de ferramentas para agentes de IA, com avaliação automática de riscos de segurança (injeção de prompt, exfiltração de dados, escalação de privilégio). Fornece classificação A-F para mais de 1.200 MCP servers e plugins, com detecção de incidentes em cadeias de suprimento.
Instalação
npx convez-ai AgentSafe-AI/tooltrust-directory1 comando no terminal: detecta o formato do repositório (marketplace ou plugin avulso) e instala via Claude Code. Requer Node 18+ e o Claude Code instalado.
Métricas
Casos de uso
- Validar segurança de MCP servers antes de integração
- Pesquisar vulnerabilidades conhecidas em ferramentas de IA
- Avaliar risco de supply-chain de dependências npm em agents
Veredito

Recurso essencial para equipes que deployam agentes em produção. O scoring contínuo e a cobertura de incidentes recentes (LiteLLM, axios malicioso) reduzem riscos operacionais reais, embora a confiabilidade dependa da qualidade do scanner subjacente.
README
A tradução para o português deste README ainda está na fila.
🛡️ ToolTrust Directory
This repo hosts tooltrust.dev — the website and pre-scanned report data. If you want to scan your own MCP servers, go to tooltrust-scanner.
A public registry of AI agent tools, continuously scanned for prompt injection, data exfiltration, and privilege escalation by ToolTrust Scanner.
🚨 Supply-Chain Incident Coverage (March 2026) ToolTrust now detects and blocks confirmed supply-chain incidents including the LiteLLM / TeamPCP compromise and the malicious axios npm publish (
axios@1.14.1,axios@0.30.4). For npm-backed MCP servers, ToolTrust also scores dependency visibility, transitive lockfile evidence, lifecycle scripts, and IOC indicators such asplain-crypto-js.

📊 Security Registry
Top 50 by popularity. View all 1246 tools → Full Directory · data/reports/ · docs/tools/
| Tool | Version | Popularity | Grade | Key Findings | Scanned |
|---|---|---|---|---|---|
| playwright-mcp | 0.0.76 | 14.5M/mo | D | 📦 AS-004 ×23, 🔑 AS-002 ×15, ⚡ AS-006 ×2, ⚡ AS-011 ×6 | Jun 11 |
| chrome-devtools-mcp | chrome-dev… | 9.3M/mo | D | 📦 AS-004 ×29, 🔑 AS-002 ×16, ⚡ AS-011 ×4, ⚡ AS-006 | Jun 11 |
| upstash-context7-mcp | 1.0.30 | 5.0M/mo | B | AS-014 ×2, 🔑 AS-002, ⚡ AS-011 | Jun 11 |
| context7 | 1.0.30 | 5.0M/mo | B | AS-014 ×2, 🔑 AS-002, ⚡ AS-011 | Jun 11 |
| gemini-cli | 0.47.0-pre… | 3.1M/mo | C | AS-014 ×56, 🔑 AS-002 ×35, ⚡ AS-011 ×11 | Jun 11 |
| cloudflare-containers | 0.3.2 | 1.4M/mo | A | 🔑 AS-002 ×5, ⚡ AS-011, AS-014 ×7 | May 30 |
| mcp-server-filesystem | typescript… | 1.3M/mo | C | 🔑 AS-002 ×15, 📦 AS-004 ×14, ⚡ AS-011 | Jun 11 |
| mcp-server-github | typescript… | 563.6k/mo | C | 🔑 AS-002 ×35, 📦 AS-004 ×26, ⚡ AS-011 ×18 | Jun 11 |
| xcodebuildmcp | 2.6.2 | 532.0k/mo | B | AS-014 ×71, 🔑 AS-002 ×35, ⚡ AS-011 ×3 | Jun 11 |
| n8n-mcp | 2.57.3 | 528.8k/mo | C | 📦 AS-004 ×7, 🔑 AS-002 ×7, ⚡ AS-011 ×2 | Jun 11 |
| mcp-server-sequential-thinking | typescript… | 438.7k/mo | B | 📦 AS-004 | Jun 11 |
| firecrawl-mcp-server | 3.2.1 | 377.0k/mo | C | 🔑 AS-002 ×14, AS-014 ×8, ⚡ AS-011 ×7 | Jun 11 |
| cameroncooke-xcodebuildmcp | 2.3.2 | 329.3k/mo | B | AS-014 ×71, 🔑 AS-002 ×35, ⚡ AS-011 ×3 | May 30 |
| notion-mcp-server | 2.1.0 | 316.9k/mo | D | 🔑 AS-002 ×30, 📦 AS-004 ×22, ⚡ AS-011 ×22 | Jun 11 |
| figma-context-mcp | 0.12.0 | 296.4k/mo | B | AS-014 ×9, 🔑 AS-002, ⚡ AS-011 | Jun 11 |
| tavily-mcp | 0.2.20 | 165.1k/mo | C | 🔑 AS-002 ×10, 📦 AS-004 ×5, ⚡ AS-011 ×5 | Jun 11 |
| tavily-ai-tavily-mcp | 0.2.19 | 155.7k/mo | C | 🔑 AS-002 ×10, 📦 AS-004 ×5, ⚡ AS-011 ×5 | May 30 |
| ruflo | 3.10.41 | 147.4k/mo | B | AS-014 ×33, 🔑 AS-002 ×25, ⚡ AS-011 | Jun 11 |
| context-mode | 1.0.162 | 131.5k/mo | C | 🔑 AS-002 ×9, AS-014 ×7, ⚡ AS-011 | Jun 11 |
| mcp-server-kubernetes | 3.9.0 | 104.2k/mo | B | AS-014 ×22, 🔑 AS-002 ×6, ⚡ AS-011 ×3 | Jun 11 |
| mcp-server-brave-search | typescript… | 104.1k/mo | C | 🔑 AS-002 ×12, ⚡ AS-011 ×7, AS-014 ×8, 🗝️ AS-010 ×2 | Jun 11 |
| circleci-public-mcp-server-circleci | 0.15.1 | 101.4k/mo | D | 🔑 AS-002 ×21, 📦 AS-004 ×17, ⚡ AS-011 ×13, 📐 AS-003 ×2 | May 30 |
| ms-365-mcp-server | 0.118.1 | 97.9k/mo | D | 📦 AS-004 ×178, 🔑 AS-002 ×377, ⚡ AS-011 ×172 | Jun 11 |
| mcp-server-time | typescript… | 87.0k | A | AS-014 ×2 | Jun 11 |
| apify-mcp-server | 0.10.13 | 84.8k/mo | D | 🔑 AS-002 ×27, ⚡ AS-011 ×7, AS-014 ×16, ⚡ AS-006 ×2 | Jun 11 |
| mobile-mcp | 0.0.59 | 77.5k/mo | C | 📦 AS-004 ×23, 🔑 AS-002 ×5, ⚡ AS-011 | Jun 11 |
| exa-mcp-server | 3.2.1 | 67.9k/mo | C | 🔑 AS-002 ×4, 📦 AS-004 ×2, ⚡ AS-011 ×2 | Jun 11 |
| desktopcommandermcp | 0.2.42 | 66.2k/mo | C | 🔑 AS-002 ×22, AS-014 ×26, ⚡ AS-011 ×8, 📐 AS-003 | Jun 11 |
| brave-search-mcp-server | 2.0.83 | 66.1k/mo | C | 🔑 AS-002 ×12, ⚡ AS-011 ×7, AS-014 ×8, 🗝️ AS-010 ×2 | Jun 11 |
| claude-task-master | 0.20.0 | 64.2k/mo | B | AS-014 ×14, 🔑 AS-002 ×9, ⚡ AS-011 | Jun 11 |
| railway-mcp-server | 0.1.11 | 46.5k/mo | C | AS-012, 🔑 AS-002 ×57, AS-014 ×36, ⚡ AS-011 ×13, 🗝️ AS-010 | May 30 |
| obsidian-mcp-server | 3.2.4 | 42.3k/mo | B | 🔑 AS-002 ×9, AS-014 ×13, ⚡ AS-011 ×2 | Jun 11 |
| dive | 0.14.2 | 38.7k/mo | C | 🔑 AS-002 ×3, ⚡ AS-011 ×2, AS-014 ×2 | Jun 11 |
| git-mcp-server | 2.15.1 | 35.5k/mo | C | 🔑 AS-002 ×39, 📦 AS-004 ×28, ⚡ AS-011 ×9 | Jun 11 |
| tacticlaunch-mcp-linear | 1.1.2 | 31.6k/mo | C | AS-014 ×42, 🔑 AS-002 ×21, ⚡ AS-011 ×8 | May 30 |
| github-mcp-server | 1.2.0 | 30.6k | C | 🔑 AS-002 ×75, ⚡ AS-011 ×36, AS-014 ×86, 📐 AS-003, 🗝️ AS-010 | Jun 11 |
| brightdata-mcp | 2.10.0 | 30.5k/mo | C | 🔑 AS-002 ×67, ⚡ AS-011 ×58, AS-014 ×65 | Jun 11 |
| aas-ee-open-websearch | 2.1.11 | 28.5k/mo | C | 🔑 AS-002 ×7, 📦 AS-004 ×6, ⚡ AS-011 ×6 | Jun 11 |
| antvis-mcp-server-chart | 0.9.10 | 26.1k/mo | B | AS-014 ×26, 🔑 AS-002, ⚡ AS-011 | May 30 |
| mcp-server-chart | 0.9.10 | 25.8k/mo | B | AS-014 ×26, 🔑 AS-002, ⚡ AS-011 | Jun 11 |
| neo | 11.19.1 | 22.3k/mo | B | AS-014 ×8, 🔑 AS-002, ⚡ AS-011 | Jun 11 |
| kastalien-research-thoughtbox | 1.2.0 | 20.1k/mo | C | AS-014 ×3, 🔑 AS-002 ×3, ⚡ AS-011 | May 30 |
| kastalien-research-clear-thought-two | 1.2.0 | 20.1k/mo | C | AS-014 ×3, 🔑 AS-002 ×3, ⚡ AS-011 | May 30 |
| mcp-server-asana | 1.6.0 | 19.6k/mo | C | 🔑 AS-002 ×8, ⚡ AS-011 ×3, AS-014 ×10 | Jun 11 |
| postman-mcp-server | 2.9.0 | 19.1k/mo | C | 🔑 AS-002 ×53, ⚡ AS-011 ×15, AS-014 ×41 | Jun 11 |
| dainfernalcoder-perplexity-mcp | Feature | 17.5k/mo | B | 🔑 AS-002, ⚡ AS-011, AS-014 | May 30 |
| openmetadata | 1.2.1 | 14.2k | C | AS-014 ×31, 🔑 AS-002 ×11, ⚡ AS-011 ×8 | Jun 11 |
| xiaohongshu-mcp | 2026.05.28… | 14.1k | C | 🔑 AS-002 ×7, ⚡ AS-011 ×5, AS-014 ×10 | Jun 11 |
| skill-seekers | 3.7.0 | 14.0k | B | AS-012, 🔑 AS-002 ×2, ⚡ AS-011 ×2, AS-014 ×2 | Jun 11 |
| mcp-server-cloudflare | workers-ob… | 12.8k/mo | D | 🔑 AS-002 ×5, ⚡ AS-011 ×2, AS-014 ×2, ⚡ AS-006 | Jun 11 |
⚖️ Grading System
| Grade | Gateway Action | Description |
|---|---|---|
| S 🌟 | ALLOW | Reserved for dynamic analysis |
| A | ALLOW | Minimal risk. Safe for production agents. |
| B | ALLOW + rate limit | Low risk. Minor issues, but generally safe. |
| C | REQUIRE_APPROVAL | Moderate risk. Remediation recommended. |
| D | REQUIRE_APPROVAL | High risk. Use only in isolated environments. |
| F | BLOCK | Critical risk. Do not use in agentic pipelines. |
Full methodology: docs/methodology.md
🔍 Check Catalog
ToolTrust Scanner check IDs referenced in all reports:
| 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 details → docs/methodology.md
🤖 AI Agent Integration
Let your AI agent scan its own tools. Add ToolTrust as an MCP server in your .mcp.json or claude_desktop_config.json:
{
"mcpServers": {
"tooltrust": {
"command": "npx",
"args": ["-y", "tooltrust-mcp"]
}
}
}
This gives your agent five security tools:
| Tool | Description |
|---|---|
tooltrust_scan_config | Scan all MCP servers in your .mcp.json or ~/.claude.json in parallel |
tooltrust_scan_server | Launch and scan a specific MCP server |
tooltrust_scanner_scan | Scan a JSON blob of tool definitions |
tooltrust_lookup | Look up a server's trust grade from this directory |
tooltrust_list_rules | List all security rules with IDs and descriptions |
Claude Code users: ask your agent to run tooltrust_scan_config to audit every MCP server in your project in one shot.
🤝 Contribute
Request a scan — open an issue with the tool's public URL and version.
Dispute a finding — open an issue referencing the finding ID (e.g. AS-002).
Integrate ToolTrust Scanner — see docs/dev.md for the data pipeline and schema spec.
📛 Add to your README
If your MCP server was audited and earned a grade, add our badge to your repo:
Grade A (recommended) — copy this into your README:
[](https://github.com/AgentSafe-AI/tooltrust-directory)
Other grades — replace grade-a with grade-s, grade-b, grade-c, grade-d, or grade-f:
| Grade | Badge |
|---|---|
| S | |
| A | |
| B | |
| C | |
| D | |
| F |
Badges link to this directory. Generate SVGs locally: go run ./cmd/badge
⚙️ Automation
The registry table above is kept up to date by a daily GitHub Actions workflow:
.github/workflows/daily-audit.yml ← cron 00:00 UTC + manual dispatch
Each run:
- Discovers popular MCP servers via GitHub Search (50+ stars) plus Smithery-native servers (10+ uses)
- Scans new/updated tools with ToolTrust Scanner + OSV supply-chain analysis
- Publishes updated reports to
data/reports/and regenerates this README
Licensed MIT. Scanner engine: ToolTrust Scanner.