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 |
|---|---|
| Excel MCP Server f-sammarco/excel_mcp_server Enables reading and writing MS Excel files, including cell values, formulas, sheet creation, copying, formatting, and on Windows, live editing and screen captures. | |
| agiscorecard f-tiger/agiscorecard-mcp Auditable AGI-2027 evidence: eight graded Situational Awareness predictions with pre-registered flip conditions, a 0-100 Thesis Tracker with full score history, and a public market-call ledger where misses stay published. Free, no auth, CC | |
| verified-ai-free-tiers f-tiger/verified-ai-free-tiers Verified AI free-tier limits, quota comparisons, commercial-use verdicts and zero-cost workflows. Every entry carries a human-checked verification date and is re-checked by a daily link patrol. | |
| Weather MCP Server with GitHub OAuth & Location Management f/komunite-mcp-bootcamp-weather-mcp Enables users to check weather conditions using Open-Meteo's free API with GitHub OAuth authentication and personalized location management. Users can save custom location labels (like 'home' or 'office') and query weather using these conve | |
| MCP Startup Framework f/mcp-startup-framework A comprehensive framework for building remote MCP servers on Cloudflare Workers featuring OAuth 2.1 authentication, PostgreSQL integration, and Stripe-powered paid tools. It enables developers to create scalable, platform-agnostic MCP tools | |
| Poke Gate f/poke-gate An MCP server that lets your Poke AI assistant access your macOS machine, enabling shell commands, file operations, and screenshots through natural language. | |
| llms-audit f0rextasy/llms-audit Enables auditing any website for AI-answer readiness, returning a score and actionable fix list based on llms.txt, schema, sitemap, and related checks. | |
| omp-laya-judge f0rextasy/omp-laya-judge Enables local, token-free typed decisions (choice/bool/score) in milliseconds for oh-my-pi sessions, with per-request language routing and confidence-based escalation. | |
| x-mcp f1l1ph/x_mcp Enables publishing to X (Twitter) — new posts, replies, quote-posts, and reposts — through a saved logged-in browser session with no API keys or developer account, verifying each target and confirming success from X's own responses. Also ch | |
| agent-notify f1lt3r/agent-notify Enables AI agents and applications to send audio notifications with text-to-speech, message streaming, agent-to-agent conversations, and web push notifications through a persistent message store and MCP integration. | |
| google-contacts-mcp-server f1nthelad/google-contacts-mcp-server Serverless connector to access Google Contacts via MCP, enabling AI agents to securely interact with contacts without storing data. | |
| douban-mcp f1sh-yu/douban-mcp MCP server for querying Douban books, movies, TV shows, and group topics, with tools for searching, retrieving details, and listing reviews. | |
| tieba-mcp f25h-233/tieba-mcp Enables reading public Baidu Tieba content through a persistent real-browser session, supporting forum searches, post details, and user public post lists with optional login-state injection. | |
| f2b-mcp-gateway f2b-dev/f2b-mcp-gateway Exposes f2b-sandbox capabilities as MCP tools for creating, managing, and running commands in sandboxes, enabling AI agents to execute code and manipulate files in isolated environments. | |
| f2c-mcp-server f2c-ai/f2c-mcp f2c-mcp-server | |
| GLOBAL Hybrid MCP v2 f2f54866sh-afk/global-hybrid-mcp-v2 Enables deterministic task routing, contract enforcement, and effect authorization across domain owners while exposing a minimal MCP interface and read-only observability. | |
| filialsucher-mcp f43nris/filialsucher-mcp An MCP server for searching Sparkasse bank branches and ATMs by location, with filtering by type, facilities, and open status. Currently uses mock data but designed for easy integration with the real Sparkasse API. | |
| n8n-MCP f4bse-94/lai-n8n-mcp-smithery Provides AI assistants with comprehensive access to n8n workflow automation platform, including 543 node documentation, 2,709 workflow templates, validation tools, and optional workflow management capabilities for creating and deploying aut | |
| Polyforge MCP Server f4cte/polyforge-mcp Enables AI assistants to interact with the Polyforge prediction market platform for market browsing, strategy management, order execution, and portfolio tracking. | |
| F6 Threat Intelligence MCP Server f6-security/ti-mcp Enables AI assistants to search and retrieve threat-intelligence collections—including leaks, malware, attacks, suspicious IPs, threats, and group profiles—through indicator queries, filtered pagination, update tracking, and WHOIS enrichmen | |
| F6 XDR MCP Server f6-security/xdr-mcp Gives AI assistants access to F6 XDR alerts, incidents, emails, files, hosts, and audit logs via query-language search, with tools for counting records, inspecting available fields and filters, and marking events. | |
| Personal Knowledge-Base MCP Server f6-zeppelinfellowship/knowledge_base-mcp_server A FastMCP server and web app for multi-tenant semantic search over personal document corpora, backed by Qdrant vector search and supporting MCP clients and a React dashboard. | |
| cybersec-mcp fa1829/cybersec-mcp Enables AI assistants to perform cybersecurity tasks including hash analysis, CVE lookup, HTTP header auditing, WHOIS/OSINT, payload decoding, password strength evaluation, and threat report generation. | |
| Postgres-Neo4j MCP Server faaizshah/postgres-neo4j-mcp Enables natural language queries to a Neo4j knowledge graph built from PostgreSQL data, integrating with Claude Desktop and REST API. | |
| Agent Identity Protocol (AIP) faalantir/mcp-agent-identity Provides cryptographic identity and signing capabilities for AI agents, enabling them to create persistent identities, sign actions with private keys, and allow external systems to verify the authenticity and provenance of agent-initiated o | |
| agent-risk-ai faanogueira/agent-risk-ai Enables AI agents to assess credit default risk, run what-if scenarios, and evaluate portfolios through natural language, backed by an explainable XGBoost model. | |
| Companies-House-MCP-Server fab-ai-up/companies-house-test-mcp-server MCP server exposing the full UK Companies House Public Data API, enabling natural language queries for company profiles, search, officers, filing history, charges, insolvency, and persons with significant control, as well as downloading and | |
| MCP SSH Server fabber-bot/mcp-ssh-server Enables AI assistants to execute commands and transfer files on remote servers over SSH connections. | |
| dagster-mcp fabdendev/dagster-mcp An MCP server that gives AI agents full visibility and control over your Dagster instance, enabling autonomous monitoring, diagnosis, and remediation of data pipelines. | |
| Ferret MCP fabdendev/ferret-mcp An MCP server that extracts complete knowledge from any codebase — architecture, patterns, dependencies, API surface. Combines static analysis with AI-powered deep interpretation. | |
| Ghost Writer MCP fabdendev/ghost-writer-mcp Scans Git repositories, identifies interesting engineering work, and generates LinkedIn post drafts with built-in confidentiality sanitisation. | |
| mcp-server fabg/mcp-server Provides instructions and code to set up an MCP server using FastMCP, enabling tool creation for LLM interaction, with an example project for extracting product information from Amazon links. | |
| kontist-mcp fabi-spl/kontist-mcp MCP server that reads and annotates Kontist business banking data, including balances, transactions, and tax reserves. | |
| uiverse-mcp fabi-spl/uiverse-mcp MCP server for Uiverse.io that lets AI agents browse, search, and fetch open-source UI components (HTML + CSS) directly in their editor. No API key required, it indexes 3,800+ components locally. | |
| MCP Intercom Server fabian1710/mcp-intercom Provides access to Intercom conversations and chats through the Model Context Protocol, allowing LLMs to query and analyze Intercom conversations with various filtering options. | |
| sap-sd-mcp-validation fabianacevedo9006/sap-sd-mcp-validation Validates SAP SD sales orders (material, pricing, credit) before creation using the MCP protocol, enabling clean-core order-to-cash automation. | |
| Sozio Business fabianbartschdatenanalyse/sozio-business Sozio Business is a standalone local MCP server for combining private company data with 22,635 profiled Swiss open-data resources. | |
| Sozio Thin fabianbartschdatenanalyse/sozio-thin Enables reproducible analysis of 100 curated Swiss open-data resources by searching profiles, materializing PXWeb data, validating and executing SQL, and formatting reproduction details, with reasoning delegated to the MCP client. | |
| My Awesome MCP Server fabiancasta/odoo-mcp-governed Enables AI agents to interact with an Odoo ERP through tool calls that are allowlist-policy-checked, risk-scored and throttled before touching the ERP, covering record reads, writes, deletes and method execution. Every request and decision | |
| MCP Wiki Server fabiandistler/mcp-wiki-server Enables AI agents to access a markdown wiki or knowledge base through per-topic tools that expose available domains and retrieve tables of contents, matching lines, or full pages on demand. | |
| warehouse-mcp-server fabianguiliani/warehouse-mcp-server An MCP server that provides safe, read-only access to a PostgreSQL warehouse, enabling schema introspection, guarded SQL queries, and truncated result reporting for LLMs. | |
| Aliado Libre fabiangulla-pixel/aliado-libre Connects AI assistants via MCP to Colombian legislation and jurisprudence with verifiable citations. Enables hybrid search over a local index of over 44,000 legal documents, returning exact, sourced quotes without generating text. | |
| local-memo fabianharmikstelzer/local-memo Local-only MCP server for saving and restoring conversation context across AI agent sessions using JSON files on disk. | |
| oasa-mcp fabianhogger/oasa_mcp Enables AI assistants to query live arrivals, vehicle positions, routes, stops, and timetables across the Athens public transport network, with stop lookups by name or coordinate in Greek or Latin script. Results cover OASA buses, trolleys, | |
| AnkiConnect MCP Server fabianissam/ankiconnectmcp Enables users to review Anki decks card by card, identify gaps such as missing verb forms or declensions, and apply approved edits through natural language conversation. | |
| Firewalla MCP Server fabiano-personal/mcp-firewalla-server Provides real-time access to Firewalla firewall data through 28 specialized tools for network monitoring, security analysis, bandwidth tracking, and firewall rule management. Enables users to query security alerts, analyze network flows, mo | |
| anvisa-mcp fabianofilho/anvisa-mcp Enables querying Anvisa's open data for drug registration status and recent medical devices, with heuristic AI-use classification using a locally hosted LLM. | |
| iamed-mcp fabianofilho/iamed-mcp Enables read-only consultation of the latest published content on AI applied to medicine—articles, news, podcasts, lessons, events, conferences and repositories—through tools to list recent items, search by topic, and open item summaries wi | |
| protocolos-pcdt-mcp fabianofilho/protocolos-pcdt-mcp Enables querying Brazilian PCDT clinical protocols from Conitec and generating concise, context-specific treatment summaries using a local LLM, with verified literal citations and links to official PDFs. | |
| radar-cfm-mcp fabianofilho/radar-cfm-mcp Enables querying and monitoring Brazilian Federal Council of Medicine resolutions on AI, telemedicine, and electronic medical records, with a local searchable copy and official document links. |
49,301–49,350 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.