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 |
|---|---|
| ifcopenshell-mcp daviidro/ifcopenshell-mcp An MCP server that lets users query, validate, convert, and compare IFC/BIM files using natural language. Runs fully locally and integrates with AI agents like Claude. | |
| speckle-mcp daviidro/speckle-mcp MCP server for Speckle that enables AI-powered AEC interoperability, letting users manage Speckle projects, models, and versions through natural language, with guidance for data push/pull via native connectors. | |
| Kawakami MCP Server daviiferrer/kawakami-mcp-server Exposes the catalog of Supermercados Kawakami (Paraguaçu Paulista/SP) as tools for MCP clients, enabling product search, offers, cart and list management. | |
| MCP Fiorilli Transparencia daviiferrer/paraguacu_transparente_mcp MCP server for accessing transparency data from Fiorilli SCPI portals, specifically for Paraguaçu Paulista, enabling queries on expenses, revenues, bids, contracts, transfers, personnel, and official diary. | |
| gmail-mcp-server-typescript daviiil/gmail-mcp-server-typescript-autogenerated An authenticating proxy that bridges Google's remote Gmail MCP server with OAuth token refresh, letting MCP clients use static credentials to access Gmail. | |
| Arkeonix CapCut MCP daviilpzdev/arkeonix-capcut-mcp An MCP server for inspecting and editing CapCut Desktop draft projects through local, version-safe timeline operations. | |
| MCP Merchant Scout davillafer/mcp-merchant-scout An MCP server that wraps the Universal Commerce Protocol (UCP) Discovery and Catalog capabilities, letting you search and compare products across UCP merchants directly from Claude. | |
| AgentGuard davin-06/agentguard A transparent MCP stdio proxy that sits between an agent client and a real MCP server, intercepting tools/call requests to enforce runtime guardrails derived from the same YAML rules used for CI regression testing. It blocks forbidden, out- | |
| Chrome MCP Server davincinewton/chrome-mcp-fix An extension-based MCP server that enables AI assistants to control your existing Chrome browser, leveraging your active login states and settings for automation. It provides over 20 tools for tasks like semantic tab search, screen capture, | |
| documentation-mcp davindermahal/ai-intake-documentation-mcp Enables onboarding a codebase for AI-agent-assisted development by scanning projects, collecting human-only answers, and maintaining traceable living documentation under .ai/ for both humans and AI coding agents. | |
| make-runner-mcp davindermahal/make-runner-mcp Enables AI agents to run predefined Makefile targets as MCP tools, with configurable allow/deny lists and environment variable restrictions, without granting shell or Docker access. | |
| Broken Link Checker MCP Server davinoishi/blc-ground Enables scanning web pages and entire domains to identify broken links, checking hyperlinks, images, scripts, and other resources. Provides comprehensive link validation with robots.txt compliance and detailed reporting of link status acros | |
| Broken Link Checker MCP Server davinoishi/broken-link-checker-mcp Enables checking for broken links on web pages and entire websites through natural language commands. Provides detailed reports including HTTP status codes and supports options like excluding external links and respecting robots.txt. | |
| Broken Link Checker davinoishi/mcp-broken-link-checker An MCP server that lets AI assistants check single URLs, scan HTML content, and crawl entire websites for broken links via four tools. | |
| Screenshot MCP Gateway davinoishi/screenshot-mcp-gateway A unified MCP server that combines screenshot capture with HTTP/SSE gateway for remote access, enabling full-page and element-specific screenshots via Puppeteer. | |
| Session Logger MCP davinoishi/session-logger-mcp Enables saving LLM chat conversations to JSONL log files and querying them by session ID, user ID, keyword, or date range. | |
| classroom-aluno-mcp davipac/classroom-mcp Enables students to access Google Classroom through MCP, listing courses, upcoming assignments, tasks, grades, announcements, materials, topics, and teachers, with optional tools to submit or cancel submissions. | |
| sigaa-ufrpe davipac/sigaa-ufrpe-mcp Enables deep access to UFRPE's SIGAA system, providing tools for login, retrieving raw HTML, making custom requests, downloading files, and accessing parsed academic data such as grades, classes, and curricula. | |
| engram-serve davis06507/engram Enables AI coding agents to query a local structural code graph and retrieve focused, token-bounded context about source entities, Git relationships, and selected project memory. | |
| web3-research-mcp davis4944/web3-research-mcp Enables local deep research on crypto tokens by aggregating CoinGecko, CoinMarketCap, DeFiLlama, and web search data into structured reports, with tools for market metrics, TVL, exchange listings, resource storage, and status tracking witho | |
| Riddle MCP Server davisdiehl/riddle-mcp-server Enables browser automation and debugging through the Riddle API, including taking screenshots across devices, running Playwright scripts, and capturing console logs and network traffic. | |
| MCP Partidos de Fútbol davise070893/mcp-gettodayfutbolmatches-usingia A Python-based MCP server that extracts football match data from multiple global sources like ESPN and BBC Sport using intelligent web scraping. It enables AI assistants to retrieve scheduled matches, real-time scores, and broadcasting deta | |
| @deliveriq/mcp davison-francis/min8t-sdks Email-deliverability tools for AI agents — 12 MCP tools across email verification, DNSBL across 50 zones, SPF/DKIM/DMARC analysis, spam-trap scoring, domain intelligence, and email finder. Free tier with no credit card. | |
| clever-code-mode-mcp davlgd/clever-code-mode-mcp An MCP server that gives AI agents full access to the Clever Cloud API through three tools: search, execute, and doc, using a code mode pattern to compose API commands. | |
| MCP JavaScript Server davlgd/mcp-js-server An unofficial JavaScript SDK to create customized servers for the Model Context Protocol, allowing definition of prompts, resources, and tools for tailored interactions. | |
| Drupal Scout MCP davo20019/drupal-scout-mcp A Model Context Protocol server for local Drupal development that combines file indexing with drush-powered database queries to provide AI assistants with knowledge of your site's structure, content, and the drupal.org ecosystem. | |
| MCP Firebase Server davo20019/mcp-firebase-server A bridge that enables Large Language Models to read from and write to Firebase Firestore collections through Model Context Protocol (MCP) tools. | |
| Social MCP Connector davolu/social-mcp-connector A remote MCP server that provides tools to query live Meta (Facebook+Instagram) and TikTok organic social data, such as follower counts, insights, recent posts, and aggregated overviews. | |
| my-design MCP Server davont/my-compoent-mcp An MCP server that enables AI to interact with the private 'my-design' React component library and design tokens for UI generation and technical support. It provides tools for component searching, API documentation retrieval, and migration | |
| Woopicx MCP Server davoooda/woopicx-mcp Enables searching free graphics on Woopicx (3D icons, mockups, stock photos, illustrations, certificates, tattoo designs) through natural language. | |
| local-tts davotank/tts-mcp A lightweight MCP server that provides offline text-to-speech via native OS speech engines. It allows AI assistants to speak task summaries instantly with no network calls. | |
| it-digest davpu/news-digest MCP server for RSS aggregation and LLM summarization, allowing users to fetch latest articles, search archives, and generate topic-specific digests via natural language. | |
| DAVS Gmail MCP Server davsdevelop/davs-gmail-mcp-server Enables an LLM to interact with a Gmail account via MCP, supporting email listing, sending, profile access, and PDF resource injection for context, with OAuth2 authentication and a Streamlit interface. | |
| Peekaboo MCP davstr1/peekaboomcp Provides read-only access to your entire codebase while restricting AI agents to only modify files in a specific workspace folder, preventing unintended broad changes. | |
| mcp_auth_server dawa/mcp_auth_server A proof-of-concept MCP server implementing OAuth 2.1 authorization with CIMD client registration and PKCE, demonstrating protected resource access and step-up authentication. | |
| atomic-computer-mcp dawdler-g/atomic-computer-mcp Enables automation of native Windows desktop applications through screen capture, mouse/keyboard control, and waiting for UI changes, exposing them as MCP tools. | |
| chrome-mcp dawei008/chrome-mcp Drive your real, signed-in Chrome browser from any MCP client, enabling browser automation such as navigation, clicking, typing, and screenshots through standard MCP tools. | |
| dawg-mcp dawgswarm/dawg-mcp Enables AI agents to provision and control remote stealth browsers, scrape web pages, and check account usage via the DAWG platform. | |
| CloakBrowser MCP dawid6614/cloakbrowser-mcp Provides a drop-in Playwright MCP-compatible browser automation server backed by CloakBrowser Chromium, letting AI agents run unchanged upstream browser tools over stdio or Streamable HTTP via npm or Docker. It adds persistent browser profi | |
| Pingfusi dawid68988/pingfusi Enables AI coding agents to request reviews from real human reviewers who pin specific issues on published artifacts and return verdicts, letting agents iterate against genuine human feedback until approved. | |
| Typst MCP Server dawid7372/typst-mcp Enables AI models to convert LaTeX snippets to Typst, validate Typst syntax, access Typst documentation, and render Typst code as PNG images. | |
| rq-mcp dawidblonski/rq-mcp Enables AI agents to inspect, debug, and operate Redis Queue (RQ) queues, jobs, and workers, with access gated by read-only, write, or admin modes. | |
| LINE OA MCP Ultimate dawidchoi3594/line-oa-mcp-ultimate Enables AI agents to run one or many LINE Official Accounts through natural language, covering broadcasts, Flex and tappable Rich Messages, rich menus, audiences, coupons, insights, and LINE Shopping. Includes quota and quiet-hour guardrail | |
| U.S. Census Bureau Data API MCP dawidlang94/us-census-bureau-data-api-mcp Enables AI assistants to query official Census Bureau statistics through tools for listing datasets, fetching dataset geographies, retrieving aggregate data, and resolving geographic names to FIPS codes. | |
| mcp-proxy dawidnowak/mcp-proxy Enables per-profile tool filtering and enforcement for one or more upstream MCP servers, exposing only allowed tools and rejecting blocked calls, with Streamable HTTP serving and observability. | |
| MediaWiki MCP Server dawidscholz57839/mediawiki-mcp-server Enables LLM clients to read, search, create, edit, move, protect, and delete pages and files across one or many MediaWiki wikis through the Model Context Protocol, with optional OAuth permissions. Extension packs add knowledge-graph, semant | |
| ReActMCP Web Search dawidvandermeer62228/reactmcp Enables AI assistants to run basic and advanced web searches through the Exa API, with filtering by domains, required text, and date ranges. Returns real-time, markdown-formatted results including titles, URLs, publication dates, and conten | |
| Zettelkasten MCP Server dawidz3492/zettelkasten-mcp Enables users to create, link, search, explore, and synthesize atomic notes through Claude and other MCP-compatible clients, using markdown files and a SQLite index. | |
| project-scaffold dawiegriesel/mcp-dev An MCP server that scaffolds full-stack projects with consistent structure, Docker setup, CI/CD pipelines, and database configuration. | |
| recall dawith-ai/recall Enables Claude to search through its own past sessions using full-text search and resume them. Works offline with zero runtime dependencies. |
42,851–42,900 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.