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 |
|---|---|
| anydoc-mcp fclwtt/anydoc-mcp Enables AI agents and MCP-capable platforms to convert documents such as docx, pptx, xlsx, pdf, odt, rtf, epub, and csv into clean GitHub-Flavored Markdown through a single tool call. Runs fully locally with no API key, no network access, a | |
| mcp-server-mysql fcmyoo/mcp-server-mysql Enables LLMs to inspect MySQL database schemas and execute read-only queries via the Model Context Protocol. | |
| Cinema4D MCP Server fcoigvozst/cinema4d-mcp Enables Claude to create and manipulate 3D scenes inside Maxon Cinema 4D from natural-language prompts, with tools spanning primitives, object transforms, cameras and animation, lights, materials and shaders, Redshift inspection, MoGraph cl | |
| read-website-fast fcoigvozst/mcp-read-website-fast Fetches webpages locally, extracts readable content, and converts it to clean Markdown with preserved links, optional multi-page crawling, caching, and robots.txt support for token-efficient use by AI agents and LLM pipelines. | |
| web-data-mcp fctpe/web-data-mcp An MCP server that runs Apify scraping actors with quality-gated validation, scoring, and retries, returning embedding-ready chunks for AI agents. | |
| TAKO MCP Server for Okta fctr-identity/fctr-okta-mcp-server Enables AI assistants to securely query and manage Okta resources for IAM and security administration. It supports dual-mode operation for standard tool interaction or autonomous agent workflows with sandboxed code execution. | |
| financial-law-mcp fcukoksan/financial-law-mcp MCP server to fetch Japanese financial laws and regulations from the e-Gov API, preventing hallucinations in Claude's responses. Supports 9 domains including Financial Instruments and Exchange Act, Banking Act, etc. | |
| VSCode MCP fdabrowski688/vscode-mcp Enables AI coding agents to obtain real-time language-server diagnostics, type information, symbol definitions, references, and workspace-wide renames directly from open editor instances, avoiding slow external type and lint checks. | |
| Shark Scout MCP fdalamo/shark-scout-mcp Provides read-only Solana wallet intelligence for evidence-first copy-trading research, enabling exact wallet activity, parsed swaps, transaction evidence, current positions, token snapshots, source-vs-copy comparisons, watchlist scans, and | |
| oracle fdarian/oracle Enables Claude Code agents to look up curated per-library documentation domains, GitHub repositories, and personal notes before reading docs or source, so library questions are answered from trusted references instead of blind web searches. | |
| Philips Hue MCP Server fdbadmin/hue-mcp Enables AI assistants to control Philips Hue smart lighting systems using natural language, supporting light control, group management, scenes, and presets. | |
| mcp-adonis-docs fdciabdul/mcp-adonis-docs Version-aware AdonisJS documentation MCP server that detects your project's AdonisJS version and provides search and retrieval of relevant docs including core, Lucid ORM, Edge, VineJS, and Japa. | |
| MCP Image Generator fdciabdul/mcp-image-generator MCP server for AI image generation supporting multiple providers (OpenRouter, Together AI, Replicate, fal.ai) and compatible with various MCP agents. | |
| Sapphire User MCP Server fde-cohort/sapphire-user-mcp Enables AI assistants to access Sapphire Wellness user profile data, including health alerts, personalized recommendations, and partner service subscriptions. | |
| Sapphire Wellness MCP Server fde-cohort/sapphire-wellness-mcp Enables AI assistants to query health metrics such as activity, blood pressure, glucose, heart rate, sleep, and SpO2 from a PostgreSQL-backed wellness database, returning structured data and summaries through MCP tools. | |
| Vectorize MCP Server fdeboer161/vectorize-mcp-server Enables vector search and document retrieval, text extraction and chunking into Markdown, and private deep research through configured pipelines. | |
| sonic-boom fdiskas/sonic-boom Encodes a TypeScript/JavaScript codebase into a deterministic PNG heatmap that vision-capable AI models can read to bypass token limits for codebase-scale audits. | |
| android-agent fdondi/android-agent-mcp Enables coding agents to build, drive, and debug Android apps on a real device, with screenshots, UI dumps, local vision model analysis, and lock-safe Gradle builds. | |
| IDA Pro MCP Server fdrechsler/mcp-server-idapro A Model Context Protocol server that enables AI assistants to interact with IDA Pro for reverse engineering and binary analysis tasks. | |
| TheoremSearch-MCP fdscend/theoremsearch-mcp An MCP server for semantic search over 9.27 million mathematical statements from sources like arXiv and Stacks Project, offering 5 tools for filtered search, citation weighting, and dependency graph traversal. | |
| wechat-mp-mcp fdslk/wechat-mp-mcp Enables crawling WeChat Official Account articles via the mp.weixin.qq.com search interface, including account search, article listing, incremental crawling, and fetching articles as Markdown with local SQLite storage. | |
| Bookeo MCP Server fdstevex/bookeo-mcp Enables searching and retrieving customer bookings and payment details from Bookeo using natural language. | |
| mcp-me fe-m-bueno/mcp-me Transforms professional data (CV, projects) into MCP tools for LLMs to query, list, match job descriptions, and ask about experience. | |
| rsba1-mcp fe1iscurc0r/rsba1-core Enables AI agents to read frequency, mode, and signal meter, as well as set frequency and control PTT on Icom IC-705/9700 and CI-V transceivers over the network using the RS-BA1 protocol. | |
| Local-Files-View-MCP fe2o3-tpa/local-files-view-mcp Enables AI assistants to access and inspect local files within a specified sandbox root. | |
| Google Calendar MCP Server feamster/calendar-mcp Enables reading, analyzing, creating, and managing Google Calendar events across multiple accounts through natural language, with features like meeting pattern analysis and scheduling preferences. | |
| Digitakt MIDI MCP Server feamster/digitakt-midi-mcp Enables control of the Elektron Digitakt II drum machine through MIDI commands. Supports triggering drum sounds, adjusting parameters, switching patterns, and sending note sequences programmatically. | |
| google-drive-mcp feamster/google-drive-mcp Enables managing Google Drive files, Docs, and Sheets through natural language via Claude Code, with tools for listing, searching, editing, and formatting documents and spreadsheets. | |
| Paymo MCP Server feamster/paymo-mcp An MCP server for the Paymo platform that enables AI assistants to manage time entries, projects, and tasks through natural language. It supports tracking unbilled revenue and generating detailed invoice timesheets for efficient project man | |
| Slack MCP feamster/slack-mcp Read and respond to Slack from Claude. | |
| spark-mcp feamster/spark-mcp Enables users to access, search, and analyze Spark Desktop meeting transcripts and emails through natural language via the Model Context Protocol. | |
| MCP Databases Server fean-developer/mcp-databases Enables LLMs and agents to interact with relational databases (SQL Server, MySQL, PostgreSQL) through MCP tools. Supports executing queries, inserting records, listing tables, and exposing database schemas with secure credential management. | |
| imladris feanorscodesl/imladris Enables multi-LLM deliberation via a council of panel members, judges responses for consensus and contradictions, and returns analysis to the calling model. | |
| MCP Manager feanus/mcp-manager A gateway that manages multiple MCP servers behind one endpoint, providing namespaced tool routing and supervision. Currently bundles an Arxiv MCP server for paper search and retrieval. | |
| Autonomous Corporate Intelligence MCP fearlessversee/autonomous-corporate-intelligence-mcp Enables users to conduct deep forensic company research and generate executive dossiers covering company DNA, monetization, product sentiment, technology stack, strategy, competitive landscape, and pre-meeting intelligence. | |
| InfinityScrape MCP fearlessversee/high-performance-osint-scraping-mcp Enables AI clients to scrape anti-bot-protected and JavaScript-rendered websites, search the web, pull Wayback snapshots, transcribe YouTube videos, parse remote PDFs/Office docs, and run OSINT/GEOINT reconnaissance across 25+ platforms wit | |
| BitScale MCP Server featherflow/bitscale-mcp Connects your BitScale workspace to Claude, allowing you to manage grids, fetch row data, and trigger enrichment runs via natural language. It provides tools for listing grids, checking run status, and retrieving workspace details. | |
| FeathersMCP feathersjs-ecosystem/feathersmcp An MCP server that connects AI assistants to live FeathersJS v6 documentation, providing accurate, source-linked answers about hooks, services, authentication, and more. | |
| Mimir featurefactory-io/mimir A self-evolving engineering playbook system that provides AI assistants with structured access to development methodologies, workflows, and best practices. Enables generation of work plans, progress tracking, and continuous process improvem | |
| Featureflow MCP Server featureflow/featureflow-mcp Enables AI assistants to manage Featureflow feature flags, including creating and updating features, controlling feature states across environments, and managing projects, environments, and targeting rules through natural language. | |
| EnrichMCP featureform/enrichmcp Turns your data model into a semantic layer for AI agents, automatically generating typed, discoverable tools with entity relationships and schema discovery. | |
| featurejet-mcp featurejet/featurejet-mcp Official MCP server for FeatureJet, enabling agents to read and act on customer feedback boards: list/search posts, file feature requests, and pull top-voted planned items. | |
| featurepulse-mcp featurepulse/featurepulse-mcp A Model Context Protocol server for FeaturePulse feedback management, enabling AI assistants to query feature requests, analyze MRR impact, and manage product roadmaps through natural language. | |
| bitbucket-mcp febin-micheal/bitbucket-mcp Enables Claude and other AI agents to manage Bitbucket Cloud repositories, pull requests, branches, tags, commits, diffs, files, and pipelines through a secure local MCP server with read and write tools. | |
| claude-connectors-mcp febin-micheal/claude-connectors-mcp Lets Claude list, add, update, and remove your claude.ai connectors from chat, and set per-tool Always allow or Needs approval permissions. It drives your own signed-in Chromium session because claude.ai exposes no public API for this. | |
| signal-mcp-remote febin-micheal/signal-mcp-remote Enables remote Model Context Protocol clients to securely read, search, and send Signal Messenger messages through an HTTP interface backed by a personal signal-cli daemon. | |
| teamwork-graph-mcp febin-micheal/teamwork-graph-mcp Provides AI agents with secure, allowlisted access to Atlassian Teamwork Graph data (Jira, Confluence, and related services) via the twg CLI, enabling read and write operations over the Model Context Protocol. | |
| AFFiNE MCP Server febrianrz/affine_mcp Enables full read/write automation of AFFiNE workspaces, documents, databases, journals, and comments through MCP tools over stdio or HTTP, supporting self-hosted and AFFiNE Cloud instances as well as multi-tenant deployments where each ses | |
| MCP Alchemy Server febriansyahnr/oncall-mcp Provides access to financial transaction data from XB database, enabling lookup of payout transactions by UUID or Client Transaction ID. | |
| readonly-db-mcp febrifaresi/readonly-db-mcp Enables running single, validated SELECT statements against PostgreSQL, MySQL/MariaDB, SQL Server, SQLite, and Oracle through read-only sessions with schema/table inspection, query plans, row limits, timeouts, and an audit log. Keeps the as |
49,901–49,950 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.