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 |
|---|---|
| MCP: Local PR Description Generator adixgit/mcp A lightweight tool that uses Mistral AI running locally to generate structured GitHub pull request descriptions from git diffs. | |
| MCP-Discord adixon637/mcp-discord Enables AI assistants to interact with the Discord platform, including sending and searching messages, managing channels, categories, forums, threads, roles, members, reactions, and webhooks. It works with a configured Discord bot token ove | |
| Mail MCP Server adjia/mail-mcp-server An MCP server providing comprehensive email management through IMAP and SMTP, allowing users to search, read, and organize messages. It supports advanced features like folder manipulation, sending emails with attachments, and secure authent | |
| 163 Mail MCP adjurtime/163-mail-mcp Privacy-first local MCP server for personal @163.com mailboxes, connecting via IMAP/SMTP with read-only search and write operations guarded by confirmation tokens. | |
| billing-doctor adkchrgr/billing-doctor Enables diagnosing Metronome usage-billing issues by inspecting events, running deterministic checks, and drafting customer replies through natural language in Claude Code. | |
| Universal Computer Control MCP adkdev200/universal-computer-control This server enables AI agents to operate Windows and Linux computers by observing the screen, understanding the UI through accessibility, OCR, and vision, and performing mouse, keyboard, window, clipboard, and system actions with verificati | |
| Microsoft Teams MCP Server adkins-amdg/teams-mcp-server Enables AI agents to interact with Microsoft Teams through Microsoft Graph API, using delegated device-code authentication to act on behalf of the user. | |
| db-connector adlkt/mcp-demo-server Enables AI assistants to query business databases directly via natural language, with enforced read-only access and secure query limits. Supports SQLite and PostgreSQL, and works with any OpenAI-compatible model. | |
| await-mcp adlternative/await-mcp Provides blocking await tools to poll commands, URLs, or files until a condition is met, eliminating the need for sleep loops in agent workflows. | |
| New Relic MCP Server adm-alvin-decruz/mcp-newrelic A comprehensive Model Context Protocol (MCP) server for New Relic monitoring, observability, and management operations. | |
| AutoBuildMCP admica/autobuildmcp A profile-based build automation server powered by MCP that manages, executes, and monitors build processes across multiple projects with features like build queuing, asynchronous execution, and file-watching for automatic rebuilds. | |
| uni-kb admin-init/uni-kb Enables parsing, indexing, and querying source code as structured knowledge, providing code exploration, spec generation, and migration tools via 20 MCP tools. | |
| KnowledgeBase MCP admin0330/kb-mcp Enables storing, importing, hybrid full-text/semantic searching, and AI-assisted organizing of markdown notes and documents in a personal knowledge base kept on an external drive. It stays usable across unplug/replug cycles, returning offli | |
| KnowledgeBase MCP admin0330/kb-mcp-temp Enables AI clients to search, organize, and maintain a personal knowledge base stored on external drives, with mount-tolerant indexing, hybrid full-text and semantic retrieval, inbox processing, and document management tools. | |
| Pynite MCP Server admindev-buildwellai/mcp-pynite Enables AI assistants to perform structural engineering analysis using the Pynite finite element library, including model creation, element definition, analysis execution, and result visualization through natural language. | |
| privateemail-mcp admingsph/privateemail-mcp Enables reading, searching, and sending emails through a Namecheap PrivateEmail mailbox. | |
| Smart Search MCP adminhuan/smart-search-mcp Provides 14 enhanced intelligent search tools for both international platforms (GitHub, StackOverflow, NPM, etc.) and Chinese platforms (CSDN, Juejin, WeChat docs, etc.). Each tool includes smart URL generation, search tips, and related sug | |
| Etsy MCP Server administrativetrick/etsy-mcp-server Enables AI assistants to search for products, retrieve listing details, get shop information, discover trending items, and access reviews on Etsy through the Etsy API v3. | |
| LinkedIn Jobs MCP Server administrativetrick/linkedin-mcp Enables users to search LinkedIn's public job listings with advanced filters like location, salary, and experience level. It allows MCP-compatible clients to retrieve real-time job opportunities without requiring LinkedIn authentication or | |
| DataForSEO MCP Server administrator-prog/data-for-seo A production-ready MCP server that gives Claude access to the entire DataForSEO API v3 through 51 tools, covering SERP, Labs, Keywords, Backlinks, OnPage, Business, and more, with cost controls and response normalization. | |
| Google Ads MCP Server administrator-prog/g-ads-mcp A read-only MCP server for the Google Ads API, exposing reporting tools for account summaries, campaigns, performance, search terms, and conversion actions. Enables natural-language queries to Google Ads data without write access. | |
| MetaVision AI Studio adminmetavision-rgb/metavision-mcp Generate 3D models from text or image. Browse 10K+ free 3D models. AI creative platform with API | |
| Nightscout MCP Server adminpb/nightscout-mcp Bridges your Nightscout CGM data with AI assistants via the Model Context Protocol, enabling natural language queries about glucose readings, treatments, statistics, and pattern analysis. | |
| Libs MCP Service adminrhs/libs-mcp-service A Model Context Protocol (MCP) service for integration with external platforms, providing CRUD operations for 23 entity types through a standardized MCP interface. | |
| OA-Y MCP Service adminrhs/oa-y-mcp-service MCP for managing courses via HTTP API at oa-y.com. | |
| Screeps World MCP Service admon84/screeps-world-mcp Integrates live Screeps game data into AI development workflows, providing comprehensive tools for room operations, market analysis, and user management. It enables AI agents to monitor game status and interact with the game world through t | |
| Nanites adn-001/nanites_mcp Enables Claude Code and Claude Desktop to delegate bounded, disposable tasks to local or cheap cloud models, with model scoring, guardrails, and cost-saved tracking. | |
| Facebook MCP Server adnaan-abdi/facebook-mcp-server Enables managing Facebook Pages via the Graph API, including posting, comment moderation, and post insights through natural language. | |
| bug_report_tool adnan-commits/bug_report_tool MCP server that converts informal issue descriptions into structured, developer-ready bug reports using Groq, with automatic classification into bug, feature request, question, or unclear. Enables agents to generate bug reports directly wit | |
| Crawl4AI RAG MCP Server adnan0758/crawl4ai-rag-mcp-server Enables AI assistants to crawl, index, and retrieve information from technical documentation using semantic search, with optional knowledge graph validation for code hallucination detection. | |
| remote-mcp-server-authless adnanhassan16/remote-mcp-server-authless Enables deploying a stateless remote MCP server on Cloudflare Workers without authentication, allowing clients to connect and use custom tools remotely. | |
| jevjob adnanrules/jevjob Enables AI assistants to find live job postings from employer career sites and rank them against a user's resume, with each requirement matched and tiered for fit. | |
| OpenGenUI MCP adner/genui_mcp An MCP server that turns natural-language descriptions into interactive HTML/JS UI components, leveraging OpenGenerativeUI and AG-UI protocol. | |
| DA Live Admin MCP Server adobe-rnd/da-mcp Enables LLM assistants to manage Document Authoring (DA) repositories through the DA Live Admin API, supporting operations like listing, creating, updating, and deleting source files, managing configurations, and looking up media and fragme | |
| MCP Remote with Adobe and Okta Authentication adobe-rnd/mcp-remote-with-okta A wrapper for mcp-remote that provides secure authentication for protected MCP servers using Adobe IMS or Okta OAuth flows. It features automated token management, validation, and background refreshing for seamless access to remote resource | |
| @loxeai/mcp-server adog0822/loxeai-mcp-server Enables local SOC 2 compliance work by scanning Infrastructure-as-Code, mapping findings to SOC 2 Trust Services Criteria, explaining risks in plain English, and drafting audit-ready documents without uploading files. | |
| DSH Crew adogan24050/dsh-crew Enables orchestrating hosts such as Claude Code, Codex, Antigravity and Grok to dispatch tasks to DeepSeek Harness agents that run as native subagents with live progress, tier/effort presets, escalation and workspace guardrails. Also bridge | |
| TetherIQ adole1982/tetheriq A zero-config local desktop proxy gateway for AI coding agents, providing model failovers, spend caps, and 1-click MCP tool syncing across multiple client environments. | |
| zotero-mcp-server adolinjonathan-bot/zotero-toolkit Enables read and write access to a Zotero library via its Web API, allowing search, create, update, and delete of items, notes, and collections. | |
| Adology adologyai/content-intelligence-plugin Perplexity for social: ask what competitors are running across social and get answers grounded in real ad and creative data, not guesses. | |
| word2img-mcp adolphnb/md2img-mcp Enables converting Markdown text into high-quality 3:4 ratio JPG images using multiple rendering backends. Supports intelligent fallback between imgkit/wkhtmltopdf, markdown-pdf, and PIL rendering engines with customizable styling options. | |
| mcp-todo-server adonis2310/mcp-todo-server MCP server for managing todo tasks, exposing tasks resource, add/complete task tools, and a daily summary prompt. | |
| LinkedIn Ads MCP Toolkit adops-tool/linkedin-ads-mcp-toolkit Enables MCP-compatible clients to query advertising data, analyze spend, conversions, and audiences, compare campaigns, generate dashboards, and manage campaigns with optional read-only safeguards. | |
| Tripo Studio MCP ador-able/tripo-studio-mcp Enables interaction with Tripo Studio for 3D model generation, management, and post-processing through natural language, with safety features to prevent duplicate charges. | |
| twine-play-mcp adorablelovelymia/twine-play-mcp Enables AI agents to play, test and QA Twine / interactive-fiction HTML games by reading passages as Markdown, clicking numbered choices, inspecting story variables, screenshotting, and saving or restoring state to explore branches. It prov | |
| bilibili-mcp adoresever/bilibili-mcp Enables AI assistants to directly operate Bilibili, providing 27 tools for login, search, content publishing, data analysis, and interaction. | |
| flomo-mcp adou0510/flomo-mcp Enables writing and managing notes in flomo through MCP tools, resources, and prompts. | |
| teadata-mcp adpena/teadata-mcp MCP server for exploring Texas public school data through conversational interfaces, enabling campus search, district details, geospatial lookup, comparisons, and transfer insights using TEA data. | |
| convocatorias-mcp adrada03/convocatorias-mcp Enables Claude Desktop or Code users to converse in natural language to find Spanish official gazette (BOE) notices — scholarships, aid, public employment and subsidies — that match their profile, via a local searchable index, watchlist-bas | |
| MCP Weather and Currency Assistant adri14gl/mcp-weather-and-currency-assistant A local MCP server that integrates FastMCP with OpenAI to enable natural language queries for current weather, forecasts, and currency conversion using ExchangeRate-API and Open-Meteo. |
23,901–23,950 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.