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 Server Example bhimprakashsingh/mcp-server-example Enables LLM clients such as Claude Desktop to connect to a local Model Context Protocol server that exposes resources, tools, and prompts through a standardized interface. | |
| Frontispice bhind/raveil-frontispice MCP server for local-first agent handoff: enables AI sessions to publish curated context, list/read updates, route handoffs to specialists, and advance per-consumer cursors, with SQLite persistence and no shell or network access. | |
| OpenAI MCP Server bhjo0930/openai_mcp Enables advanced OpenAI GPT model integration with Claude through 5 specialized tools including GPT-5 reasoning, token optimization, context management, batch processing, and model comparison. Features intelligent fallback mechanisms and ta | |
| SendGrid MCP Server bhoggard/twilio-sendgrid-mcp Enables AI assistants to send emails and manage contacts through SendGrid's Web API v3. | |
| deeplore bholagabbar/deeplore Self-hosted RAG-powered knowledge base that surfaces context from structured notes and transcripts, exposing each project as an MCP tool. | |
| Weather MCP Server bholemaharaj/mcp_node Provides weather forecast and alert data for US locations through the National Weather Service API, enabling access to real-time weather alerts by state and detailed forecasts by coordinates. | |
| tastytrade-mcp bholzer/tastytrade-mcp MCP server for the tastytrade brokerage API, providing tools for account management, market data, and order execution. | |
| Agentic RAG MCP Server bhonandh/agentic-rag-with-mcp-server-main MCP server providing tools for entity extraction, query refinement, and relevance checking to build Agentic RAG applications. | |
| lunchmoney-readonly-mcp bhonick/lunchmoney-readonly-mcp A read-only MCP server for Lunch Money that provides secure, retrieval-only access to financial data through ChatGPT Business, with OAuth authentication and enforced read-only restrictions. | |
| Skimlet bhoomabrsr/skimlet Enables deep-research agents to run search engine queries and batch-extract page content through a user's Chrome profile, returning search results and extracted content to MCP clients. | |
| Music Recommendation MCP Connector bhoomika-puttaraju/music-recommendation-mcp Enables music discovery and recommendations through the free Last.fm API by exposing tools for artist and track search, similarity-based suggestions, genre or mood-based discovery, and personalized recommendations built from a Last.fm user' | |
| mcp-server-text-editor bhouston/mcp-server-text-editor An open source implementation of the Claude built-in text editor tool versions:
text\_editor\_20241022 (Claude 3.5 Sonnet)
text\_editor\_20250124 (Claude 3.7 Sonnet) | |
| MCP 길잡이 (mcp-giljabi) bhpark1013/mcp-giljabi Helps users discover and install MCP servers from PlayMCP using hybrid search (keyword matching + semantic search) based on their requests, and provides installation guidance. | |
| Google Docs/Sheets MCP Server bhrtevents/gdocs-mcp-server A remote MCP server that lets Claude edit existing Google Docs and Sheets, supporting search, replace, append, and insert operations for Docs, and search, update, and append rows for Sheets. | |
| Messages MCP Server bhsantos11/mcp A Model Context Protocol server that provides access to messages from an external API endpoint using Bearer token authentication for integration with Claude Desktop. | |
| Drawing Guides MCP Server bhubbb/mcp-drawing-guides Provides access to step-by-step drawing tutorials from easydrawingguides.com, enabling users to search for drawing guides, retrieve detailed tutorial content in Markdown format, and browse categories for artists of all skill levels. | |
| Fetch as Markdown bhubbb/mcp-fetch-as-markdown Fetches web pages and converts them to clean, readable markdown format by extracting main content while removing navigation, ads, and other non-essential elements to minimize token usage. | |
| weather-mcp-server bhujangarao-db/mcp-server-app-v1 Enables AI to access current weather and forecasts via Open-Meteo, with optional natural language explanations using Groq. | |
| hiveLLM MCP bhuman-ai/hivellm-mcp Brings a real human expert into Codex or OpenCode by creating a hiveLLM room for message exchange, without using user's API quota or credentials. | |
| MapmyIndia Mappls MCP Server bhupendrajee07/mmi-mcp Enables AI assistants to query geographic data, perform geocoding, get directions, calculate distance matrices, discover POIs, and look up place details across India using MapmyIndia (Mappls) REST APIs. | |
| StarRocks MCP Server bhussein14784/mcp-server-starrocks Acts as a bridge between AI assistants and StarRocks databases, enabling direct SQL execution, database and table exploration, schema/data overviews, and metric access without complex client-side setup. It also generates Plotly charts from | |
| COUE bhuvan0808/coue-mcp Enables Claude to audit AI/ML projects for production readiness through deterministic static analysis, check ML system descriptions, compare model configurations, and generate readiness reports or deployment checklists. It returns scored, e | |
| Sentinel Core Agent bhuvanmdev/sentinel-core-agent Enables file system operations, web scraping, and AI-powered search through MCP tools for use by LLM agents. | |
| Personal Expense Tracker bhuvpal/personalexpensetracker Enables users to add expenses, retrieve expenses by date range, and get spending summaries by category through MCP tools. | |
| Splitwise MCP Server bhvkmuni/splitwise-mcp Enables conversational control of Splitwise accounts through Claude AI, allowing users to add expenses, check group balances, record settlements, and manage payment splits using natural language commands. Supports multiple currencies and fl | |
| Confluent Support RAG MCP Server bhwingt/mcp_server_confluent_rag An MCP server that provides hybrid search over Confluent support articles and lets AI assistants save solved problems back into the knowledge base. | |
| ocr-mcp bhxch/ocr-mcp Enables MCP clients to run OCR on local image files through a single long-lived PaddleOCR backend shared across clients, returning recognized lines as a Markdown table with optional coordinate and confidence columns. | |
| korea-holiday-mcp bhyunco/korea-holiday-mcp Enables accurate calculation of Korean public holidays, substitute holidays, and business days, with tools to check dates, list holidays, and compute working-day intervals. It works as a public MCP connector requiring no authentication or A | |
| jev bhzdcz/multica-typed-decision-router Enables typed Jev API evaluations through a Keychain-backed MCP bridge, with no external side effects. | |
| mcp-financial-data-server biahellens/mcp-financial-data-server Enables querying stock quotes and computing portfolio risk/return metrics such as Sharpe ratio, drawdown, volatility, and correlations, as well as historical summaries and asset comparisons. | |
| Paper Fact Check biajin-pku/paper-fact-check Serves the paper fact-checking checks over the Model Context Protocol, enabling an agent to recompute reported statistics, percentages and changes, compare text against tables, and verify references against Crossref, OpenAlex and arXiv. Eac | |
| topper-mcp biajin-pku/topper-mcp Enables natural-language search for top-tier academic papers by generating query plans, retrieving from Semantic Scholar and OpenAlex, and filtering results through CCF/中科院/JCR/flagship venue gates, while also offering venue tier lookup and | |
| entity-extraction-mcp biancaroh-design/entity-extraction-mcp Enables entity extraction from conversations using Claude AI, with tools to recommend coupons for membership inquiries and issue tickets for delivery delays. | |
| MediaWiki MCP Server bianchi758/mediawiki-mcp-server Enables LLM clients to read, search, create, edit, move, and delete pages and files across any MediaWiki wiki, including extension data from Wikibase, Semantic MediaWiki, Cargo, Bucket, and NeoWiki. Supports multiple wikis with per-wiki res | |
| Juror Cloud MCP bianchi9254/juror Enables MCP clients to inspect workspace-scoped findings and hosted runs, and to prepare or, after explicit confirmation, start or rerun existing hosted reviews without exposing raw diffs, full reports, credentials, or prompt text. | |
| tingji biancuihuo/tingji Enables AI agents to query a local, continuously recorded Mac audio timeline, including speaker-labeled transcripts, topic-organized events, projects, todos, daily summaries, insights, and long-term memories. | |
| Coding Tools MCP biaobiao2233/coding-tools-mcp-workbench Gives MCP-compatible AI clients safe, hands-on access to local codebases: file reading/search, multi-file patches, command execution, interactive sessions, Git inspection, and coordination of local agent providers such as Antigravity and Op | |
| true-solar-time-mcp biaogo94/true-solar-time-mcp Converts civil time to true solar time and audits whether civil and solar times cross Chinese 时辰 boundaries, for time-sensitive divination workflows. | |
| qwen-vision-mcp biaoqiang-love/qwen-vision-mcp Enables Claude Code to analyze images using Qwen vision models (via DashScope) when the main model is text-only. | |
| MySQL MCP Server bibaram/mysql-mcp-server A Model Context Protocol server that connects to MySQL databases, allowing execution of SQL queries, table listing, and schema inspection through Claude Desktop. | |
| Word Document MCP Server bibash44/word-documet-mcp-server Enables AI assistants to create and manipulate Microsoft Word documents programmatically with support for rich text formatting, tables, lists, headings, and find-and-replace operations. | |
| mydata bibekg/mydata Enables querying personal data synced from services like Lunch Money and Strava using SQL via Claude. | |
| PBIXRay MCP Server V2 bibiibjorn-finvision/mcp-server Enables Claude AI to analyze Power BI Desktop models with comprehensive capabilities including DAX analysis, performance monitoring with Storage Engine/Formula Engine breakdown, VertiPaq statistics, and natural language querying of model st | |
| pbi-webview2 bibiibjorn/pbi-webview2 Enables AI agents to interact with live Power BI Desktop report canvas via Chrome DevTools Protocol, performing actions like page navigation, clicking slicers, reading cards and matrices, and capturing baselines. | |
| DoneTick MCP Server bibiwan/mcp_donetick Enables AI assistants to manage DoneTick chores, subtasks, labels, projects, members, and smart sensor triggers over HTTP SSE. | |
| haraj-mcp bibo242/haraj-mcp MCP server for haraj.com.sa, the Saudi classifieds marketplace, exposing 21 tools to search, fetch feeds, and retrieve post details via real GraphQL endpoints. | |
| WeChat MCP Server biboyqg/wechat-mcp Enables automation of WeChat on macOS through the Accessibility API, allowing LLMs to fetch recent messages from contacts and send replies based on conversation history. | |
| notion-proxy bibstha/notion-proxy Enables reading and writing Notion pages as a guest using browser cookies, bypassing the official API's limitations. | |
| Bicameral MCP bicameralai/bicameral-mcp A provenance-aware decision ledger that maps meeting transcripts and PRDs to code symbols to track implementation and drift. It enables developers to maintain institutional memory by linking historical context and architectural decisions di | |
| live-comments bicameralai/live-comments Exposes a read_source tool that lets agents read cited tickets, docs, and files through the same path the checker verifies, so quoted business rules match their sources and stay in sync as those sources or their authors change. It also keep |
34,051–34,100 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.