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 |
|---|---|
| linkedin-analyzer c3emm/linkedin-career-analyzer Analyzes LinkedIn profiles for specific companies and roles to extract career patterns and insights using AI. | |
| Identity Admin MCP Server c3sc0-v4113/identity-service-mcp Enables admin operations for an Identity-Service, including user management, role assignments, and approval decisions via Cloudflare Workers. | |
| mirador-mcp c3sc0-v4113/mirador-mcp Thin MCP adapter for Mirador Core that exposes data tools through the Core Internal API, enabling business data queries and schema exploration. | |
| farmos-mcp c41m4n/farmos-mcp This server enables AI assistants to look up and record farm data, including assets, logs, plans, and taxonomy terms, through farmOS's JSON:API. It provides read-only access by default but allows for controlled write and delete operations. | |
| mcp-film c47-inc/mcp-film The mcp.film directory as an MCP server — search a curated, continuously re-verified catalog of MCP servers for AI filmmaking, get install configs for any client, and plan a full production stack. | |
| AutoCAD MCP Server c48h74/autocad-mcp Enables compatible AI assistants to inspect, draw, and modify drawings open in AutoCAD / AutoCAD Plant 3D through COM, including layers, entities, block attributes, and Excel attribute round-trips. | |
| Xray MCP Server c4m3lblue-star/xray-mcp Enables integration with Xray Cloud APIs for comprehensive test management including creating and managing test cases, test executions, test plans, and test sets. Supports CI/CD automation and test result tracking through GraphQL APIs. | |
| erp2pdf-studio-mcp c4pointer/erp2pdf-studio-mcp Lets AI agents build, validate, preview and translate Odoo PDF and HTML email templates through the erp2pdf.com Template API, without using the Studio UI. Agents can explore Odoo models and fields, inspect expression output for real records | |
| PDF MCP Server c70311tw/pdf-mcp-server A read-only MCP server for PDF analysis that enables text extraction, image extraction, metadata retrieval, and text search via natural language. | |
| remote-mcp-server-authless c8cw6rj9b5-code/remote-mcp-server-authless Enables deploying a stateless remote MCP server on Cloudflare Workers without authentication, with support for custom tool registration and connections from MCP clients. | |
| AgentRPA c8xm/rpa-llm-bridge Enables LLM clients to drive browsers, Windows desktop apps, and Office files through a unified action contract, with YAML-defined workflows, policy gates for irreversible actions, audit logging, and resumable human-approved runs. | |
| 재활용척척 c9boom7/recycling-helper-mcp Guides correct disposal methods for confusing household waste items. Provides tools for classifying waste, getting disposal steps, checking confusing items, making cleanup plans, and regional disposal info. | |
| SCHOOL101 ca0071/worldclass-educational-mcp A unified Model Context Protocol server that consolidates global educational platforms, enabling AI agents to seamlessly integrate with Canvas LMS, K-12 standards, assessment tools, and educational data analytics. | |
| evaconnect-mcp ca11mebaraka/evaconnect Provides read-only access to Evolute companion API, enabling retrieval of vehicle telemetry, trips, charge sessions, and authentication status without the official app. | |
| GenPDM MCP Server caa1211/mock-mcp-server Enables MCP clients to interact with a fixed business GraphQL API as typed, safely guarded tools, including JWT authentication, rate limiting, and query/mutation protections. | |
| MCP RAG Server caagudelo/mcp_rag A local RAG server using the Model Context Protocol (MCP) to allow AI assistants to query private documents with persistent memory and support for many file formats. | |
| Branchpoint caarlosgg/branchpoint Provides AI agents with persistent, branch-aware context memory by storing summaries per Git branch and automatically enriching them with recent commits and divergence from main. Enables agents to maintain coherent state across sessions wit | |
| CabalSpy Wallet Tracker MCP cabalspy/cabalspy-mcp-server KOL, smart money & whale wallets API on Solana, BNB, Base, ETH: Wallet tracker, Leaderboard | |
| loseit-mcp cabird/loseit-mcp An MCP server and CLI for logging food to Lose It!, enabling food search, diary management, meal logging, and weight recording via unofficial API. | |
| Simple Document Processing MCP Server cablate/mcp-doc-forge Provides comprehensive document processing, including reading, converting, and manipulating various document formats with advanced text and HTML processing capabilities. | |
| Calendar Tools MCP Server cablate/mcp-google-calendar Enables comprehensive calendar management with capabilities to create, list, update, and delete events through a Model Context Protocol server integrated with Google Calendar. | |
| Gmail MCP Server cablate/mcp-google-gmail Provides comprehensive Gmail integration with LLM processing capabilities, allowing users to read, search, filter emails and handle attachments through the Model Context Protocol. | |
| memory-lancedb-mcp cablate/memory-lancedb-mcp Enables AI agents to store and recall persistent long-term memories across sessions using LanceDB, with semantic search, automatic linking, conflict detection, and maintenance tools. | |
| MAPI cabo0m/mapi-agent-memory An auditable memory, lifecycle, and governance server for AI agents, providing durable memories with provenance, lifecycle management, and guarded workflows through the Model Context Protocol. | |
| Caboose MCP caboose-mcp/fafb A comprehensive personal AI toolserver that exposes 105 tools across 25 groups—including Slack, Docker, and calendar management—to Claude and VS Code. It features a Go-based MCP server integrated with a custom VS Code extension and n8n work | |
| Gramps MCP cabout-me/gramps-mcp Enables AI assistants to interact with Gramps genealogy databases for intelligent family tree research and management. Provides comprehensive tools for searching family data, creating records, analyzing relationships, and tracking genealogy | |
| Tuya MCP Server cabra-lat/tuyactl Provides a note storage system with a custom URI scheme and includes tools for adding notes and generating summaries for Tuya devices. | |
| Google Calendar MCP Server cabrac3g0/google-calendar-mcp Enables AI assistants to read, create, update, delete, and search Google Calendar events across multiple accounts, check availability, and handle recurring events and invitations through natural language. | |
| MCP Server cabrit0/mcp_server_reunemacacada A server that generates Master Content Plans (MCPs) by aggregating web resources and organizing them into structured learning paths for any topic. | |
| Canvas MCP Server cabrt/canvas-mcp Provides read-only access to Canvas LMS data including courses, assignments, grades, and deadlines through 23 structured tools. | |
| Site Knowledge cabrt/site-knowledge Crawls a website, indexes its content, and answers questions with cited sources over MCP. | |
| campaign-creator-provider cabscrypto/campaign-creator-provider Creates bilingual campaign strategies, channel copy, and publishing calendars from a URL and objective via a deterministic, network-free MCP stdio server. | |
| design-brief-provider cabscrypto/design-brief-provider Generates structured design briefs from a website URL and/or brand details, in English or Spanish, via MCP tools. | |
| research_with_sources cabscrypto/research-scout-provider Enables generating deterministic, cited research findings from caller-supplied source metadata and excerpts via a local-fixture MCP tool, supporting English and Spanish. | |
| Stellar Agent Merchant Lab cabscrypto/stellar-agent-merchant-lab An MCP server for AI agents to purchase resources via Stellar testnet USDC, handling quotes, purchase URLs, and merchant receipts. | |
| website-intelligence-provider cabscrypto/website-intelligence-provider Enables deterministic bilingual website intelligence audits by URL, returning fixed English or Spanish findings without ever contacting the submitted site. | |
| mcp-server-brewfather cacack/mcp-server-brewfather Enables LLM clients to read batches, recipes, fermentation readings, and inventory, and to perform routine writes such as updating batch status, logging measurements, and adjusting stock. | |
| vyos-mcp cacack/mcp-server-vyos An MCP server for managing VyOS routers via the HTTPS REST API, enabling configuration changes, operational commands, and system maintenance tasks. It also provides tools to search and read live VyOS documentation directly from official sou | |
| mcp-server-zwave-js-ui cacack/mcp-server-zwave-js-ui An MCP server that connects to Z-Wave JS UI's WebSocket to expose controller, node, and configuration information as tools for AI assistants to manage Z-Wave networks. | |
| ida-auto-mcp cacamelio/ida-auto-mcp Enables AI coding assistants to drive the IDA Pro lifecycle — opening, saving, switching, and closing binaries autonomously — so unattended multi-binary reverse-engineering pipelines can run. It handles database flushing, port release, auto | |
| wsl-mcp cacaview/wsl-mcp A MCP terminal management server with persistent sessions and terminal polling, optimized for Windows + WSL environments. | |
| cacheout-mcp cacheout-app/cacheout-mcp MCP server for macOS disk cache management. Enables AI agents to free disk space on demand by scanning and clearing developer caches. | |
| Kakao Navigation cachij/kakao-navigation-mcp-server kakao navigation mcp server using kakao mobility & kakao map api | |
| ResearchBrain MCP Server cacity/researchbrain Enables MCP clients to interact with a local-first research knowledge workbench, supporting literature search, evidence-grounded Q&A, and reference export. | |
| TradingAgent cactus001/trade-agent Enables natural-language paper trading with real-time market data, FinBERT sentiment analysis, conditional orders, and price alerts. | |
| mcp-headers cactuscash/mcp-headers Enables Claude to scan a website's HTTP security headers and receive an A–F grade against OWASP best practices, including per-header pass/warn/fail results and copy-paste fixes for missing headers. | |
| mcp-sqlite cactuscash/mcp-sqlite Enables Claude to safely explore and query a SQLite database through natural language, including listing tables, inspecting schemas, and running read-only SELECT queries. | |
| Parimit cad07/parimit Enables AI agents to propose structured payment intents, apply deterministic policy, require human approval, and record tamper-evident audit trails without connecting to live payment rails. | |
| AgeKey MCP Server cadamtech/agekey-mcp Enables managing AgeKey applications, credentials, and organizations directly from an AI IDE via Clerk-authenticated OAuth and RBAC. | |
| garmin-mcp cadencheng888/garmin-mcp Connects Garmin watch data to Claude Desktop, allowing users to ask natural language questions about their health and activity data from Garmin Connect. |
36,351–36,400 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.