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 |
|---|---|
| AI Workshop Guide MCP Server fayamonkey/mcp Enables AI educators to provide simple explanations, interactive demonstrations, and relatable analogies for complex AI concepts during workshops. Makes artificial intelligence topics accessible and engaging for participants through structu | |
| docs-to-mcp fayazara/docs-to-mcp A Cloudflare Worker that transforms Cloudflare AI Search (AutoRAG) instances into an MCP server for querying documentation. It enables AI models to search and retrieve relevant information from custom document sets stored in R2 buckets. | |
| AI Race Engineer fayazhussain2821/ai_race_engineer MCP server that provides F1 telemetry analysis, tyre degradation modeling, and pit strategy recommendations, delivering race engineer-style calls grounded in real data. It exposes tools for degradation fits, fuel correction, and strategy re | |
| Venice Browser MCP Bridge fayeblade1488/fayeblade_mcp Enables browser automation through Playwright with persistent sessions and cookie state management. Supports web navigation, page interaction, and browser control via JSON-RPC protocol over stdin/stdout. | |
| eval-sample-size fayehall-ai/sample-size-mcp Enables agents to calculate how many evaluation test cases are needed to trust model comparisons, find the smallest detectable accuracy gap, and assess paired or unpaired results using McNemar and two-proportion statistical tests. | |
| mcptestingwm fayezbast/mcptestingwm A minimal MCP server for validating connectivity to World Monitor, exposing tools for latest events, active alerts, country risk, and top incidents. | |
| fayna-rag-mcp fayna-digital/fayna-rag-mcp Enables local knowledge base management with retrieval-augmented generation (RAG), providing semantic search, document reading, listing, and Q&A via MCP tools and REST endpoints, all running locally without cloud dependencies. | |
| codeforces-mcp faysal-star/codeforces-mcp Enables coding agents to discover unsolved Codeforces practice problems, analyze tag performance, and inspect submissions, profiles, rating history, and upcoming contests through MCP-compatible clients. | |
| rungraph fayzan123/rungraph rungraph is an MCP server (stdio, npx rungraph mcp) that turns Claude Code and Codex transcripts into an interactive run graph. Seven tools: list_runs, get_graph, find_nodes, get_detail, focus_nodes, get_current_view, open_visualization. Re | |
| Telegram Web MCP Server fayzullo637/mytelegrammini1-mcp Enables AI agents to interact with Telegram Web through a clean text-based API, including chat search, message history, sending messages, and profile retrieval via a persistent Playwright session. | |
| MCP LocalStack Server fazaelirealty-ui/mcp-localstack-server- Provides conversational access to LocalStack AWS services (S3, DynamoDB, Lambda, SQS) through natural language, enabling local cloud infrastructure management without real AWS costs. | |
| chatuse fazakis/chatuse Enables AI assistants to inspect and control macOS apps via accessibility trees, screenshots, OCR, and input simulation, with a visible pointer. | |
| Airlock fazalrshah/airlock Enables LLM agents to safely search and fetch content from a single configured domain, preventing data exfiltration through deterministic enforcement. | |
| Triage MCP Server fazalrshah/triage Enables AI agents to autonomously check, diagnose, and recover Dockerized services through safe, tool-based ops without direct host shell access. | |
| MCP Obsidian Server fazer-ai/mcp-obsidian Enables LLMs to interact with Obsidian vaults via the Local REST API plugin for comprehensive note management, file operations, and vault navigation. It supports creating and editing notes, executing Obsidian commands, and performing advanc | |
| shared-memory fazerluga-creator/shared-memory A portable, self-hosted semantic memory layer for LLM agents, enabling them to search and add memories by meaning over the Model Context Protocol. | |
| daizee-mcp fazilnazkolambil/daizee-mcp Enables voice assistants to keep a persistent health memory across conversations, so allergies and temporary notes like a sore knee are remembered, expire on their own, and are checked against meals and daily calorie/macro goals as they are | |
| dblink fb0sh/dblink Enables agents to connect to and work with PostgreSQL, MySQL, Redis, SQLite, and MongoDB through a uniform tool surface for opening connections, running queries and commands, inspecting schemas, and managing documents. | |
| mcptools fb0sh/mcptools An MCP server providing built-in system info and nmap network scanning tools, with a registration system for adding custom tools. | |
| KFabric fbailleux2/kfabric KFabric is a platform for building traceable and weighted documentary corpora from heterogeneous sources, prioritizing data quality before RAG implementation. It provides tools for document discovery, scoring, and fragment synthesis via an | |
| gmail-mcp-server fbassas/gmail-mcp-server Enables searching and reading Gmail messages, listing labels, and creating email drafts without sending or deleting emails. | |
| business-day-mcp fbdo/business-day-mcp MCP server for business-day arithmetic with country-aware holiday calendars. It offers tools to check, calculate, and list business days and holidays for over 60 countries. | |
| Excel MCP Server fbeelm/excel-mcp-server Enables reading and writing Excel files (text, formulas, and images on Windows) via MCP tools with pagination support. | |
| Cellar fbereilh/cellar An interactive notebook server that enables humans and AI agents to collaboratively edit and run Jupyter notebooks on a shared kernel, with real-time streaming and automatic MCP integration for agent access. | |
| Obsidian MCP Agent fblake28/obsidian-mcp-agent A custom MCP server that cleans up raw notes into properly formatted, cross-linked notes in an Obsidian vault using Claude Desktop. | |
| Discord MCP fboiero/discordmcp MCP server that exposes Discord API as tools, enabling users to manage servers, channels, messages, and roles through natural language. | |
| bugpacker-cli fbonds/bugpacker-cli This server lets coding agents inspect Bugpacker bug packages locally, exposing console output, failed requests, repro steps, and package files over MCP while keeping all data on the machine. | |
| Oracle of Nethys fbonds/oracle-of-nethys Provides search and retrieval over a local database of Pathfinder 2e rules. Enables Claude Code to answer rules questions with cited, accurate answers from fetched entries. | |
| MCP Spotify Server fborello/mcpspotify Enables interaction with Spotify through LLMs using OAuth2 authentication. Supports music search, playback control, playlist management, and device management through natural language commands. | |
| JungleBridge MCP fbossiere/junglebridge-mcp Provides a local FastMCP STDIO server scaffold for connecting AI assistants to Welcome to the Jungle recruitment workflows, though the WTTJ integration is not yet implemented. | |
| GeekyGramps-MCP fbrawner3/geekygramps-mcp A shared memory gateway for AI coding agents using PostgreSQL, enabling collaborative context across agents. | |
| Hospitable MCP Server fbrmike/hospitable-mcp Connects Claude to the Hospitable API v2 for managing vacation rental properties, reservations, guest messages, and reviews. | |
| bradesco-rede-mcp fbsampaio/bradesco-rede-mcp MCP server for real-time querying of the Bradesco Saude referenced network, exposing a search_providers tool to search for doctors, hospitals, clinics, and labs. | |
| vibelore fbwndrud/vibelore Enables AI hosts to plan, draft, and check long-form novel chapters while honoring canon settings, character state, arcs, and check ordering, with approval-gated atomic commits. It keeps world, character, and chapter files as the human-edit | |
| benchtop-mcp fc0web/benchtop-mcp MCP server for operating, recording, and analyzing serial-connected measurement instruments and circuits via AI agents. Includes a built-in mock device so all features can be tested without physical hardware. | |
| lab-notebook-mcp fc0web/lab-notebook-mcp Enables persistent, append-only storage of measurement data and experimental records using a SQL schema, with read-only and read-write modes for professional lab notebook use. | |
| med-lit-mcp fc0web/med-lit-mcp Enables searching medical literature, clinical trials, drug information, guidelines, and medical fee schedules directly from Claude, returning only original sources and text without medical judgment. | |
| rei-checker fc0web/rei-checker-mcp Provides MCP tools to verify logical expressions and retrieve decision statistics, with verdicts VALID, INVALID, or UNDECIDED. | |
| rei-lads-mcp fc0web/rei-lads-mcp Enables LLM agents to connect to and control OPC UA LADS laboratory instruments, with approval-gated execution of state-changing operations and retrievable SHA-256 witnessed provenance records. | |
| rei-memory-mcp fc0web/rei-memory-mcp Read-only MCP server that lets Claude/Rei query a curated SEED_KERNEL repository of over 1,677 theories via full-text search, ID lookup, or STEP metadata. | |
| rei-meta-mcp fc0web/rei-meta-mcp A meta-layer MCP server that treats connectors as objects and access paths as morphisms, enabling automated coherence checks across multiple data sources to detect inconsistencies. It provides tools to list sources, compare fingerprints for | |
| rei-verify fc0web/rei-verify A verification infrastructure and MCP server that specializes in refutation (negation) rather than generation, providing tools for counterexample search, Lean verification, and audit chains with a 4-value verdict system. | |
| trackio-mcp fcakyon/trackio-mcp An MCP server that enables AI agents to observe and interact with trackio experiment tracking, providing tools for managing ML experiments through natural language. | |
| idm-mcp fcapub/idm-mcp Mock identity-management MCP server for decentralized identity that allows minting DIDs, issuing signed Verifiable Credentials, and verifying them. | |
| Zapr WhatsApp MCP Server fcavalcantirj/zapr-mcp Enables sending WhatsApp messages through Claude Desktop and other MCP-compatible LLMs. Supports single and bulk messaging, phone number validation, and session management via the zapr.link service. | |
| Teradata MCP Server fcdmoraes/teradata-mcp-server Enables running SQL queries, exploring metadata, and interacting with Teradata databases through the Model Context Protocol. | |
| autoicd-mcp fcggamou/autoicd-mcp MCP server for automated ICD-10 medical coding. Code clinical text to ICD-10-CM diagnoses, search 74,000+ codes, and de-identify PHI via the AutoICD API. | |
| agent-bridge fchamber/agent-bridge Enables Claude Code and Cursor to delegate tasks to each other, spreading workload across both AI coding subscriptions. | |
| Meteora DLMM MCP Server fciaf420/meteora-dlmm-mcp A personal MCP server for managing Meteora decentralized liquidity market maker positions on Solana, allowing users to view pool information, check positions, and claim accumulated fees through Claude AI. | |
| localSMTP-mcp fclef819/localsmtp-mcp Provides a dummy SMTP server for catching emails during development, with MCP tools to list, retrieve, and manage received messages. |
49,851–49,900 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.