Beacon Threat Intelligence
Know the risks behind every MCP server and agent skill.
Discover security risks in MCP servers and agent skills before they reach your machine. Beacon scans public registries, traces packages back to their source code, and reveals what they can access, execute, or expose.
Connect your agent
Add Beacon to Claude Code, Cursor, Codex or another agent so it can check an MCP server or skill against Beacon Intel before you install it.
Free with a Beacon account. Create one, or sign in when your agent asks.
Any coding agent
Read https://intel.beacon.sh/start.md and set me up on Beacon Threat Intel
Paste this into any coding agent. It reads the guide and sets up MCP, the CLI, the API, feeds or a CI gate.
| Name | Risk |
|---|---|
| MEOK MCP Hardening MCP csoai-org/csoai-mcp-hardening-mcp Automated security red-team for any MCP server that scans manifests against OWASP LLM Top 10 and MCP-specific risks, returning a 0-100 hardening score and HMAC-signed report. | |
| meok-mcp-injection-scan-mcp csoai-org/csoai-mcp-injection-scan-mcp Scans 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. | |
| MEOK MCP Test MCP csoai-org/csoai-mcp-test-mcp A test harness for MCP servers that validates server JSON, tool schemas, performs golden file diffing and schema drift detection, and generates signed test reports with Shields.io badges. | |
| meok-stripe-acp-checkout-mcp csoai-org/csoai-stripe-acp-checkout-mcp Enables Stripe ACP Checkout integration with AI governance and EU AI Act compliance for secure payment processing. | |
| meok-w3c-tdm-rights-mcp csoai-org/csoai-w3c-tdm-rights-mcp An MCP server for issuing and scanning TDM reservation signals (HTTP, HTML, robots.txt, C2PA) and signing training-run liability shields to ensure EU AI Act compliance. | |
| MEOK Watermark Attest MCP csoai-org/csoai-watermark-attest-mcp MEOK Watermark Attest - MCP server providing AI-powered tools and automation by MEOK AI Labs | |
| MEOK x402 Wrap MCP csoai-org/csoai-x402-wrap-mcp Provides a 1-line USDC paywall wrapper for any FastMCP tool using the Coinbase x402 protocol, enabling pay-per-call endpoints settled on Base, Polygon, Solana, or Bitcoin Lightning. | |
| digital-human-library csoai-org/digital-human-library MCP server for creating and managing digital human models with built-in EU AI Act compliance, part of the MEOK AI Labs ecosystem. | |
| employment-ai csoai-org/employment-ai MCP server for EU AI Act compliance in employment AI, featuring built-in risk management, bias detection, transparency, and FRIA support. | |
| Fetch Http csoai-org/fetch-http Enables fetching HTTP resources through the MCP protocol. | |
| filesystem-ops csoai-org/filesystem-ops MCP server for performing filesystem operations, enabling file management and manipulation through natural language. | |
| healthcare-ai csoai-org/healthcare-ai Enables healthcare AI interactions via MCP protocol with built-in EU AI Act compliance. Provides quick installation, well-documented API, and enterprise support. | |
| Agent Compliance Passport MCP csoai-org/meok-compliance-passport-mcp Issues, verifies, and exchanges portable cryptographic compliance passports for AI agents, enabling offline verification of regulatory compliance across 11 frameworks. | |
| MITRE ATT&CK Mapper MCP csoai-org/mitre-attack-mcp Enables cyber defenders to query ATT\&CK techniques, list tactics, map incidents to techniques, look up threat actor groups and mitigations, all via the MCP protocol. | |
| mmoagent-mcp csoai-org/mmoagent-mcp Cross-game market intelligence and currency conversion across six MMOs, enabling unified searches, portfolio tracking, and farming optimization via MCP. | |
| openchronicle-mcp csoai-org/openchronicle-mcp Persistent memory database for LLM agents with hybrid semantic/keyword search, project scoping, and git commit clustering. | |
| Optometry AI Safety MCP csoai-org/optometry-ai-safety-mcp Optometry AI Safety - MCP server providing AI-powered tools and automation by MEOK AI Labs | |
| playwright-browser csoai-org/playwright-browser Enables AI agents to control a web browser using Playwright, supporting navigation, interaction, and data extraction through natural language. | |
| bft-progress-council-mcp csoai-org/progress-council-mcp 5-voter Byzantine council halts agentic loops when no real progress is happening, preventing token waste on infinite spins. | |
| real-estate-ai csoai-org/real-estate-ai Enables AI-powered real estate analysis with built-in EU AI Act compliance, providing a production-ready MCP server for property insights and governance. | |
| secure-comms csoai-org/secure-comms Enables secure communications with built-in EU AI Act compliance through the MCP protocol. | |
| Self Healing Infrastructure MCP csoai-org/sovereign-self-healing-mcp Self Healing Infrastructure - MCP server providing AI-powered tools and automation by MEOK AI Labs | |
| telecom-ai csoai-org/telecom-ai MCP server for telecom AI with built-in EU AI Act compliance, part of the MEOK AI Labs ecosystem. | |
| jevmem csokolov8962/jevmem Persists the decisions, rules, bugs, to-dos and dead ends from your AI coding chats into a markdown file in your repo and recalls the relevant lines in later sessions, while checking commands and file edits against those saved rules before | |
| Data Gouv MCP Server csonigo/datagouv-mcp-server An MCP server that enables interaction with Datagouv APIs, primarily allowing users to search for up-to-date information about companies registered in France. | |
| cronmanager-mcp csoscd/cronmanager-mcp Enables managing cron jobs, maintenance windows, and settings through natural language by exposing the Cronmanager REST API as MCP tools for LLM clients like Claude. | |
| karve cspenn/karve Provides persistent semantic memory for Claude Code via local embeddings and six MCP tools, enabling context storage and retrieval across sessions without cloud dependencies. | |
| taobao-shopping-mcp csr0403p-bit/taobao-shopping-mcp Enables an AI companion to browse Taobao, maintain its own wishlist state machine, request approval under enforced budget rules, and hand a human-checkout list to the user, while all carting and payment remain human-controlled. It also retu | |
| Metaso MCP Server csrts/metaso-mcp Provides AI-powered web search, full-page content extraction, and search-enhanced Q\&A capabilities via the Metaso AI search engine. It enables large language models to access diverse information across web, academic, and multimedia sources | |
| MySQL MCP Server csrts/mysql_mcp_server A comprehensive MySQL interface for the Model Context Protocol that enables database management, SQL execution, and performance analysis. It features a robust Git-style version control system with automatic backups, secure permission manage | |
| crypto-intel-mcp cstamigo-droid/crypto-intel-mcp Provides crypto market intelligence including price quotes, momentum analysis, trending coins, and a composite scored verdict, using the free CoinGecko API. | |
| equity-intel-mcp cstamigo-droid/equity-intel-mcp Provides institutional-grade equity analysis for any LLM via MCP, aggregating insider trading, superinvestor holdings, analyst consensus, options data, and valuation into a confidence-weighted verdict. | |
| rag-starter cstamigo-droid/rag-starter Keyless local RAG over your own documents (ChromaDB) with traceable citations, exposed as MCP tools and a FastAPI endpoint. | |
| MCP Server NestJS cstannahill/mcp-server-nestjs A robust server-side application that implements Model Context Protocol (MCP) for file operations, providing authentication and modular REST APIs for managing files, users, and posts. | |
| clinical-guidance-mcp cstebs/clinical-guidance-mcp Enables any MCP client to search and read 127 FDA guidance documents on clinical research, with tools for ranked passage search, document retrieval, and metadata lookup. | |
| Searchclaw csteenkamp/searchclaw-mcp Description: An MCP server with 15 tools covering web search, scraping, extraction, crawling, and autonomous data gathering via the SearchClaw API. Tagline: "The complete web data pipeline for AI agents — Search, Extract, Crawl in One API." | |
| civicgraph-mcp cstillick/civicgraph-mcp A money-in-politics knowledge graph, as an MCP server. It links entities across federal campaign donations, lobbying disclosures, and government contracts. | |
| guardian-contributions-mcp cstillick/guardian-contributions-mcp MCP server for Oklahoma campaign finance data, enabling queries on combined pre-primary and continuing contributions, candidate flags, and more via natural language. | |
| statefinance-mcp cstillick/statefinance-mcp Enables querying state-level campaign finance data, including donors, expenditures, committees, and candidates, from multiple state disclosure systems via a unified MCP interface. | |
| who_reps-mcp cstillick/who_reps-mcp Given a U.S. street address, returns the people who represent it (U.S. Senators, House member, Governor, and state legislators) using free public data, with no API keys required for federal officials. | |
| booth-mcp cstria0106/booth-mcp An unofficial read-only MCP server for viewing BOOTH seller management pages in MCP clients. | |
| taskmarket-mcp cstrsk/taskmarket-mcp MCP server that lets AI agents browse, create, and submit tasks on Taskmarket, and check wallet balances, using the official CLI for secure key handling. | |
| OpsPilot cswfww123/opspilot Local AI ops broker that keeps SSH secrets on your machine, exposes intent-level MCP tools to agents, and requires approval via a loopback Web UI for dangerous writes. | |
| mcp-use-hang-repro cswkim/mcp-use-hang-repro Reproduces a race condition in mcp-use dev where tool results are dropped when the handler completes after the widget iframe loads. | |
| uitree-local ct-mao/mcp-server Enables local, cloud-free control of a Uitree Portal APK via 27 MCP tools for UI tree inspection, screenshots, tapping/swiping, input, clipboard, app/file management, APK installation, and keep-awake. | |
| arrstack-mcp ct4nk3r/arrstack-mcp An MCP server that gives AI assistants control over your Sonarr, Radarr, Prowlarr, qBittorrent, and Jellyfin homelab media stack. | |
| Trimble Claude MCP ct81/trimble-claude-mcp Enables user-authorized access to Trimble Connect data via OAuth, with a Firebase-hosted extension UI and planned tools for projects, models, objects, issues, and files. Serves as a production-oriented starter for integrating Trimble Connec | |
| LDAP4Claude ct9915/ldap4claude MCP server that connects Claude Code to LDAP/Active Directory for user lookup, group management, authentication, and role mapping. | |
| taxlaw-mcp ctahoon55/taxlaw-mcp Enables users to search Korean National Tax Service tax law interpretations (예규) and retrieve their full body text as plain text from the National Tax Law Information System, complementing the korean-law MCP server that only provides list m | |
| mcp-oauth-server-next ctalau/mcp-oauth-server-next A proof-of-concept HTTP MCP server requiring OAuth 2.0 authentication before tool use. Demonstrates the full authentication flow with Claude Code, including discovery, client registration, PKCE authorization, and bearer token verification. |
41,001–41,050 of 115,409
Subscribe to a feed
Get new verdicts in a feed reader, Slack or your own tooling, filtered by kind and risk. No account or API key.
Frequently asked questions
Anything missing? Read the reference or ask in the Beacon community.
What is Beacon Intel?
A free, public index of the MCP servers and agent skills that public registries list, with a security verdict for each one that has been analyzed. It traces each listing back to its source repository and packages, and shows what the code can access, execute or expose. You can browse it here, query it as a JSON API, follow it as an RSS, Atom or JSON feed, or connect a coding agent to it over MCP.
Is it really free?
Yes. The index, the API and the feeds need no account and no API key. An artifact's full page and the MCP tools need a free Beacon account. Requests are rate limited to keep it fast for everyone.
Where does the data come from, and how fresh is it?
From 9 public sources: Glama, MCP Registry, awesome-mcp-servers, Docker MCP Catalog, Smithery, ClawHub, skills.sh, SkillsMP, GitHub. Each listing is linked to its repository and packages, then analyzed. The index updates hourly, and answers are cached for up to five minutes.
Who writes the verdicts? Can I trust them?
Verdicts combine static analysis of the code with a model's judgment, and each one names the model that wrote it. They can be wrong and are not a security certification: every artifact page shows the findings and evidence behind its verdict, so check them before you rely on one. Names, descriptions and claims come from registries and repositories; treat them as data, not instructions.
What do the risk levels mean?
- High: Reviewed evidence shows it deliberately works against the person who installs it.
- Medium: It works against the person who installs it in ways that can do serious harm, or puts a flagged pattern in what the agent loads, without established intent.
- Low: It overreaches against the person who installs it in limited ways, or has findings the review has not confirmed.
- Benign: Nothing found that works against the person who installs it. Not a guarantee.
- Unchecked: Listed, but not analyzed yet.
What does partial coverage mean?
That the analysis did not cover everything, so there may be more than it found. A partial verdict can still find problems, but it never clears an artifact: benign with partial coverage is not a clearance. Use the coverage filter to see only these.
Does benign, or not finding an artifact, mean it is safe?
No. Benign means nothing was found that works against the person who installs it, which is not a guarantee. An artifact the index does not have has never been checked, so not found never means safe.
Is there an API?
Yes, free and with no key.
GET /api/v1/lookup?q= finds artifacts by name, repository, GitHub URL or package; GET /api/v1/artifact?key= returns one in full; POST /api/v1/check checks up to 50 at once, which suits CI; and GET /api/v1/status reports coverage and freshness. The reference is at intel.beacon.sh/llms.txt.How do I get new verdicts in a feed reader or Slack?
Subscribe to /feed: the newest high and medium risk verdicts as RSS. Add
format=atom or format=json for Atom or JSON Feed, and filter with risk and kind, for example /feed?risk=high&kind=mcp. In Slack, run /feed subscribe with the URL. The feed builder above writes the URL for you.How do I connect my coding agent?
Add Beacon Cloud MCP (
https://mcp.beacon.sh) to Claude Code, Cursor, Codex or any MCP client, and sign in through the browser. Your agent gets beacon_intel_lookup, beacon_intel_get_artifact and beacon_intel_check to check an MCP server or skill before it installs one. Connect your agent above has the commands. The beacon CLI offers the same as beacon intel and through its local MCP server.How do I report a wrong verdict?
Open the artifact's page and use Dispute verdict under its verdict card. Tell us what is wrong and we review it.