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 |
|---|---|
| Academic Paper Search MCP Server andrean01951/academic-search-mcp-server Enables Claude Desktop and other MCP-compatible clients to search academic papers across Semantic Scholar and Crossref, retrieve detailed metadata and abstracts, and access full-text content when available, including topic searches with opt | |
| patreonmcp andreanjos/patreonmcp Enables interaction with Patreon through the official API v2 for reading identity, campaigns, tiers, members, posts, webhooks, and early-access Lives, with cursor pagination, field selection, and optional OAuth token refresh. It also lets c | |
| Hegelion andreao32/hegelion Enables LLMs to reason dialectically by forcing thesis, antithesis, and synthesis passes, and to implement code through an iterative player-coach loop where a separate agent independently verifies requirements. Exposes tools for dialectical | |
| dev.augments/mcp andreaokada67/augments-mcp-server Enables Claude Code and other compatible clients to retrieve real-time, context-aware documentation, TypeScript types, examples, migration guides, error diagnoses, package comparisons, and dependency scans for any npm package. | |
| Scryfall MCP Server andreapede/mcp_scryfall MCP server for searching and retrieving Magic: The Gathering card information via the Scryfall API, with support for field presets, multiple output formats, and automatic rate limiting. | |
| MCP GitHub Project Manager andreaperry95/mcp-github-project-manager Enables AI coding agents and teams to turn GitHub Projects v2 into an autonomous task substrate for registering, claiming, tracking, reviewing, and completing work, while also supporting AI-powered PRD generation, sprint planning, issue tri | |
| Machine 2 Machine Protocol andrearettaroli/m2m Enables AI agents to autonomously request services from other specialized agents and compensate them via x402 micropayments. Demonstrates a Machine-to-Machine economy using A2A protocol for agent communication, MCP for context management, a | |
| mcp-governance-proxy andreas-altamirano/mcp-governance-proxy An MCP server that acts as a governance proxy for AI agents, evaluating each tool call against policies before execution, enabling secure and controlled access to systems like Slack, GitHub, and AWS without exposing credentials to the agent | |
| Vectorize MCP Server andreas2986/vectorize-mcp-server Enables vector search and document retrieval from Vectorize pipelines, conversion of any file into chunked Markdown text, and generation of private deep-research reports with optional web search. | |
| Canvas MCP Server andreas87808/mcp-canvas-lms Enables interaction with the Canvas LMS API to manage courses, assignments, submissions, enrollments, grades, discussions, and account-level administration. Supports student, instructor, and account admin workflows with stdio and streamable | |
| S&P 500 MCP Server andreas9036/sp500-mcp-server Enables querying S&P 500 company data from Supabase through tools covering company fundamentals, annual financial metrics, historical daily price rows, news with sentiment filtering, officers and compensation, and SEC filing history. Includ | |
| mcptube-vision andreasaito407/mcptube Enables users to ingest YouTube videos and query a persistent, compounding wiki built from transcripts and visual scene analysis, with agentic search over merged entities, topics, and concepts. It exposes this knowledge base as an MCP serve | |
| pubmed-mcp-server andreasd601/pubmed-mcp-server Enables agents to search PubMed, PubMed Central, and Europe PMC, fetch article metadata and full text with multi-tier fallbacks, resolve partial citations and identifiers, format references, find related or citing work, and ground queries i | |
| mcp-document-intelligence andreasdietzel/mcp-document-intelligence Enables AI assistants to analyze, rename, categorize, and organize local documents using OCR, metadata extraction, and batch processing, with preview mode and undo support. | |
| docs-rag-mcp andreaselmi/docs-rag-mcp Enables MCP clients to semantically search a local folder of markdown documents via a single search_notes tool, with embeddings generated locally by Ollama and support for excluding superseded or archived material. | |
| threads-mcp andreaselmi/threads-mcp Enables MCP clients to publish text posts to Threads, read your own posts, retrieve post insights, and check the publishing quota using the Threads API. | |
| PlayCanvas Editor MCP Server andreasford778/editor-mcp-server Lets AI agents automate the PlayCanvas Editor directly, creating and editing projects, entities, scripts, assets, templates, animation, scenes, builds and store content through natural language. It also launches projects at runtime to captu | |
| Agent Harness Kit andreashart3607/agent-harness-kit Enables AI coding providers to run structured multi-agent workflows with shared documents, tracked tasks, handoffs, and health-gated completion evidence. It integrates with multiple coding tools while keeping task state, actions, and health | |
| cli-mcp andreasheine/cli-mcp Exposes existing command-line applications as MCP tools by discovering their commands and arguments, generating JSON Schemas, and executing them with argument validation, allowlists, read-only rules, approvals, and container sandboxing. Wor | |
| MCP Server Template for Cursor IDE andreashornqvist/mcp A template for creating and connecting custom tools to Cursor IDE using Model Context Protocol with support for cheerful server responses. | |
| AKIMCP andreasjimenez57915/aki-mcp-sv An OAuth-gated MCP endpoint that lets web-based AI chat clients such as Claude, ChatGPT, Grok, and Postman operate a local machine through a governed suite of 38 tools covering files, shell, search, Git, SQLite, browser automation, DevTools | |
| baby-mcp andreasorel/baby-mcp Enables AI assistants to answer questions about pregnancy, infancy, and the first year of life using live content exclusively from Norwegian health authorities: Helsedirektoratet, FHI, and Helsenorge. It provides source URLs, rejects non-ap | |
| Piia Engram andreasp7450/piia-engram Enables multiple MCP-compatible coding tools to share one local, user-owned store of your identity, preferences, quality bar, decisions, lessons, and project context, so each agent starts from the same understanding of you instead of from s | |
| FastMCP-Harness andreasredjack/fastmcp-harnes Enables read-only governance and security checks for local FastMCP environments, including code security review and Trivy vulnerability scanning via MCP tools. | |
| ptc-fs-mcp andreasronge/ptc-fs-mcp A small filesystem MCP server that reads and writes files under one confined root over stdio, with paginated tools and strict change-detection. It enables safe, deterministic file access for agentic runtimes and MCP clients. | |
| ptc-web andreasronge/ptc-web Enables compatible MCP clients to read JavaScript-rendered web pages as bounded Markdown or structured records, with URL policy and resource limits for safe, inspectable access. | |
| Pare andreass15/pare Wraps developer tools like git, npm, Docker, and test runners to return clean, schema-validated JSON instead of raw terminal text. This lets agents use typed, token-efficient results directly without brittle string parsing. | |
| moneyflow MCP Server andreassigloch/moneyflow-mcp Query money flows between state, citizens, and enterprises. Simulate policy changes, compare cohorts, and check data confidence directly from MCP-compatible tools. | |
| Jokes MCP Server andreasvolkmann/mcp An MCP server that fetches jokes from various APIs (Chuck Norris, Dad jokes, and Yo Mama jokes) for use in Microsoft Copilot Studio. | |
| FRED MCP Server andreaszimmermann511/fred-mcp-server Enables users to browse, search, and retrieve over 800,000 Federal Reserve Economic Data time series through category, release, and source exploration, keyword/tag search, and series data retrieval with date ranges and transformations. | |
| AgentQL MCP Server andreat788/agentql-mcp Enables users to extract structured data from a given web page URL by describing the desired data and its fields in a natural language prompt. It returns the requested fields as clean, structured output for use directly within MCP-compatibl | |
| tradingview-chart-mcp andreavisser171/tradingview-chart-mcp Enables users to request chart images for specified tickers and timeframes via MCP, with optimized concurrent fetching and optional authenticated clipboard/base64 capture. | |
| otp-mcp-server andreax79/otp-mcp The server provides secure OTP (One-Time Password) generation. Supports TOTP (Time-based) and HOTP (HMAC-based) algorithms | |
| Screenshot Website Fast andreayoshida0531/mcp-screenshot-website-fast Enables fast capture of web page screenshots optimized for AI vision workflows, with automatic tiling into 1072x1072 chunks and support for capturing specific DOM elements and screencasts. | |
| spotify-mcp andreazero/spotify-mcp Enables AI agents to search Spotify tracks and control playback (play, pause, skip, queue, volume) through the Spotify Web API. | |
| Local Data Engineering MCP andrebarrocas/data-engineering-mcp-demo Enables AI agents to inspect a mock data platform locally via SQLite, using read-only tools for schemas, row counts, freshness, queries, and pipeline status without cloud credentials. | |
| CarClever Find My Car andrebro007/carclever-find-my-car An MCP server for used-vehicle matching, offering tools to find matching vehicles, fetch photos, and resolve dealer URLs using Auto.dev endpoints. Currently a scaffold with stubs for search logic. | |
| Hermes andrebuilds/hermes Hermes is a boilerplate for building agent-ready tools with a shared TypeScript core, enabling a single operation to be used as a CLI command, local MCP tool, remote MCP server, and Skill instructions. It currently demonstrates sending Tele | |
| cortex andrecavalcantii/cortex Lets Claude read, search, create, update, and connect notes kept as plain local Markdown files, turning ideas, plans, and projects into an organized personal knowledge network. It can list and search notes, add new ones to the right area, c | |
| intervals-mcp andrecccruz/garmin_smart_trainer_mcp Enables Claude Code to publish, update, and delete planned workouts on Intervals.icu, which syncs them to athletes' Garmin Connect calendars and watches. Also lets users list authorized athletes, review recent activities and scheduled worko | |
| juris-br-mcp andrecccruz/juris-br-mcp Enables natural-language queries of Brazilian court cases through the public DataJud and DJEN APIs, retrieving case details, movements, publications, and parties across 92 tribunals, and calculating procedural deadlines in business days. It | |
| Bring! MCP Server andreclaassen1/bring-mcp-server Enables Claude to manage Bring! shopping lists by reading lists, adding items, checking them off, and sorting items into the correct store automatically. | |
| vserver-monitoring-mcp andreclaassen1/vserver-monitoring-mcp Enables SSH-based read-only monitoring of Linux vServers via Claude, allowing queries for system metrics, logs, network info, and health check reports. | |
| blocksign-mcp andrecolin/blocksign-mcp Blockchain-anchored e-signatures. Create, send, negotiate, and verify legally binding agreements — every signature anchored to XRPL + Bitcoin with public verification. Agents can pay autonomously. | |
| deep-directory-tree-mcp andredezzy/deep-directory-tree-mcp Deep directory tree visualization tool enabling efficient visualization of complex directory structures with AI-powered analysis capabilities. | |
| mcptube-vision andree18010/mcptube Enables users to turn YouTube videos into a compounding knowledge base by extracting transcripts, detecting scene changes, generating vision-based frame descriptions, and building a searchable wiki. It supports agentic natural-language quer | |
| rag-server andreeagheorghe/rag-mcp Local MCP server that provides a search_documents tool to query a RAG pipeline built with Ollama embeddings and ChromaDB, enabling Claude Desktop to retrieve relevant document chunks. | |
| whoop-mcp andreeevtinislav/whoop-mcp Enables Claude to access WHOOP data such as recovery, sleep, strain, and workouts through local MCP tools. | |
| Lore DB MCP Server andreehultgren/lore-db Provides tools for semantic search, CRUD, verification, and reindexing of documents in a local vector-based knowledge base, usable via HTTP or stdio. | |
| hybris-mcp-lite andreescocard/hybris-mcp-lite Enables read-only inspection of a local SAP Commerce (Hybris) instance through HAC, letting an MCP client query the type system, Spring beans, configuration properties, cronjobs, console logs and FlexibleSearch results in plain language. In |
28,651–28,700 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.