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 |
|---|---|
| word-mcp cheppy/word-mcp Enables measuring and fixing the page layout of .docx documents by driving Microsoft Word or LibreOffice, including page counts, section outlines, text search, paragraph formatting, field updates, and PDF export. | |
| Cheqd MCP Toolkit cheqd/mcp-toolkit Enables AI agents to securely manage decentralized identities, verifiable credentials, and trust registries on the Cheqd network via the Model Context Protocol. | |
| quota-aware-resumer cher9lie/quota-aware-resumer Enables Codex users to automatically resume selected tasks after rate-limit resets by reading local metadata and updating native scheduled tasks, and optionally attempts to start an inactive five-hour window at a chosen time via a lightweig | |
| pingcode-health-mcp chercr/pingcode-health-mcp An MCP server for monitoring PingCode project health, enabling PMs to query project status, sprint progress, and risk items directly from Claude Code. | |
| cuadra chere3/cuadra Enables importing and reconciling Mexican bank statement PDFs and files into an auditable SQLite ledger, with tools to preview, review, and commit transactions via Claude. | |
| BioNext-mcp cherine0205/bionext-mcp Enables bioinformatics analysis through natural language conversations with Claude Desktop, automatically generating and executing Python scripts to produce HTML reports and visualizations. | |
| alexchernysh-mcp chernistry/alexchernysh-mcp Enables querying a stateless, read-only MCP endpoint for profile information, projects, CV details, and grounded answers based on published site content. | |
| crewio-mcp cherry-it/crewio-mcp Hosted HTTP MCP server that exposes Crewio CRM as tools for AI assistants, enabling CRUD operations on deals, contacts, companies, comments, and full-text search. | |
| Gmail MCP Server cherryaugusta/gmail-mcp-server A Windows-first Python MCP server for Gmail that reads unread emails and creates correctly threaded draft replies using the Gmail API. | |
| LeafMCP cherrylemon/leafmcp Enables AI assistants such as Gemini, Claude, and ChatGPT to read, search, edit, compile, and review LaTeX files in your actual Overleaf projects, with versioned and atomic multi-file changes. Edits are published straight to Overleaf, so ch | |
| Google Analytics MCP Server chervinkos/ga4-mcp-server Enables natural-language access to Google Analytics 4 properties and reports, including page views, users, events, traffic sources, device metrics, and custom reports, with automatic OAuth 2.0 authentication and token management. | |
| Zettelkasten MCP Server cheryl066/zettelkasten-mcp Enables users to create, link, search, explore, and synthesize atomic notes and knowledge graphs through Claude and other MCP-compatible clients, with Markdown-backed storage and SQLite indexing. | |
| Bitbucket MCP cheryl35426/bitbucket-mcp Enables AI assistants to access and manage Bitbucket repositories and pull requests through Bitbucket Cloud and Server APIs, including listing and retrieving repositories and fetching or creating pull requests. | |
| BOSS 直聘 MCP Server cherylkim306/boss-zhipin-mcp Enables AI assistants to automate recruiter-side candidate sourcing, resume screenshot/OCR viewing, multi-keyword search and deduplication, scoring and filtering, greeting, and Markdown report export. | |
| loci-mcp cherylkuznetsov/loci Enables AI agents and MCP hosts to query a local, machine-resident index of scattered notes, project docs, PDFs, Office files, and chat exports using hybrid vector + BM25 retrieval with section-level citations. Exposes tools, resources, and | |
| NotebookLM MCP Server cheryllacroix793/notebooklm-mcp Enables agents and workflows to query Google NotebookLM notebooks through both MCP and a plain HTTP REST API, returning citation-backed answers with source excerpts and handling multi-account rotation with automatic re-authentication. Also | |
| DSH Crew cherylmatsumoto/dsh-crew An MCP server that lets hosts like Claude Code, Codex, Antigravity and Grok dispatch work to DSH agents as native subagents with live progress, tiered presets, escalation, guardrails and a jobs board. It also bridges the text-only harness t | |
| codex-image-context-runtime cherylmiyazaki/codex-image-context-runtime Enables users to run context-bounded image generation and inspection as durable local jobs that return bounded text handoffs, hashes, relative references, and Job IDs instead of media bytes. | |
| WeChat MCP Server chesereri/lingyu Exposes Windows WeChat desktop client automation as MCP tools, letting AI agents check connection status, list chats, read buffered messages, and send text or files to explicitly specified contacts or groups. Includes safety controls such a | |
| mcp-tools-server cheshirecache/mcp-tools-server A small MCP server for course experiments that provides tools to read recent commits from public GitHub repositories. | |
| Hashcat MCP Server chess960king/hashcat-mcp Enables AI assistants to perform password hash auditing locally via Hashcat, with automatic attack escalation and plain-English results. | |
| sdf chessceo/chessceo-mcp ddd | |
| W Agent chessing234/w-agent A self-hosted WhatsApp bridge with an AI agent enabling searchable context, message drafting, and approval workflow via MCP protocol for Claude Desktop and other MCP clients. | |
| mcp-server-return-to-dark-tower chessmess/mcp-server-return-to-dark-tower Lets AI assistants control the physical Return to Dark Tower board game tower via Bluetooth, enabling connection, calibration, sound, lights, drum rotation, seal breaking, and game sequences through natural language. | |
| Chest MCP chest-by-argentic/chest-mcp Enables assistants to securely work on a Chest via personal access token: reading tool logs, builds, and databases, editing rows and variables, and installing or linking tools, with every write requiring a dry run and human confirmation. | |
| CalledIT chesterguan/calledit-mcp A judgment game played by Humans VS AI bots | |
| @boxverse_ai/listenme-mcp-server chesterkuo/boxverseai-mcp-server MCP server for ListenME — product research task management via Boxverse AI. Provides 21 tools for managing research tasks, reviewing user feedback, and generating insights. | |
| webfetch chesternotchest/yet-another-webfetch-mcp-alternative A local MCP server that fetches any http/https webpage, extracts main content, and converts it to Markdown, serving as a drop-in replacement for the built-in WebFetch tool. | |
| ccontext chesterra/ccontext Provides AI agents with persistent execution context across sessions through local YAML files, enabling shared memory, task tracking, milestone management, and context hygiene for single or multi-agent workflows. | |
| 命盘 Mingpan chesterra/mingpan Provides traditional Chinese astrology (Bazi, Ziwei) and divination (Liuyao, Meihua, Qimen, etc.) calculations as MCP tools for AI assistants. | |
| MCP Financial Datasets Server chestnutforty/mcp-financial-datasets Provides backtesting-compliant financial data including company financials, historical stock and crypto prices, and news with sentiment analysis from financialdatasets.ai API. | |
| MCP Google Trends Server chestnutforty/mcp-google-trends Provides access to Google Trends search interest data with backtesting support, allowing retrieval of historical 30-day trend windows ending at specified cutoff dates for forecasting applications without future information leakage. | |
| MCP Metaculus Server chestnutforty/mcp-metaculus Retrieves historical prediction data, community forecasts, and user comments from Metaculus forecasting platform with strict date filtering to prevent future information leakage for backtesting applications. | |
| DeepFusion MCP Server chestnutsheep/deepfusion-server Enables AI agents to access Chinese financial market data and investment research through 177 tools, covering stocks, industries, macroeconomics, economic cycles, commodities, crypto, funds, and asset allocation. | |
| Student MCP File-Server Connector chesuu/-my-mcp-file-server Enables MCP clients to manage files in an isolated workspace and perform lightweight Git operations through a protected Streamable HTTP endpoint, including listing, reading, writing, searching, replacing, and deleting files plus checking st | |
| Cairn cheswickdev/cairn A local-private context-handoff tool for AI agents, preserving decisions, evidence, and verbatim code in a SQLite ledger and providing zone indicators to prevent context rot across sessions. | |
| grounded-rag-mcp chetan1521/grounded-rag-mcp Enables any MCP host to search and answer over your own documents with hybrid BM25+dense retrieval, cross-encoder reranking, and grounded, cited responses that refuse when no evidence is found. | |
| grounded-rag-mcp chetan1521/grounded-rag-mcp-ts Enables LLM hosts to perform grounded, cited retrieval and answer generation over your own documents using hybrid BM25 and dense search, with explicit refusal when answers are not supported by the sources. | |
| GitHub Repository Health MCP chetangpande-ai/githubreposhealth-mcp Enables real-time assessment of GitHub repository health by exposing tools and resources for repository metadata, open issues, recent commits, and GitHub Actions workflow runs, plus prompts for health reports and issue triage. | |
| Keyword Search MCP Server chetaniitbhilai/ressl_mcp Enables case-insensitive keyword search within files, returning matching lines with their line numbers through a FastAPI-powered interface. | |
| WorkplaceSearchAgent MCP Server chetanm0311/workspacesearchagent Enables AI agents to search, retrieve, and summarize content from workplace tools including Google Drive, Notion, Slack, and Confluence through secure Model Context Protocol. | |
| Angular PR Review MCP chetanraj-r/angular-pr-review-mcp Enables automated pull-request review workflows for Angular repositories by providing tools to generate, read, and save diffs, and to fetch review templates. | |
| Broker Analysis MCP chetto1983/broker-analysis-mcp Read-only MCP server that lets analysts pull Yahoo Finance data and compute risk metrics, technical indicators, fundamental and peer ratios, ETF tracking statistics, plus user-defined parametric indicators, conditions and saved hooks with c | |
| turing_AgentMemory_MCP chetto1983/turing_agentmemory_mcp TuringDB-backed Agent Memory MCP server with provider-agnostic embedding and rerank integrations, memory lifecycle tools, document ingest, and cited retrieval. | |
| Mathematical Calculator MCP Server chetto983/calculator-mcp-server Enables advanced mathematical computation through MCP tools, including safe expression evaluation, symbolic solving and calculus, statistics, matrix and vector operations, and headless function plotting. It supports integration with MCP hos | |
| turing_AgentMemory_MCP chetto983/turing_agentmemory_mcp Enables persistent agent memory and document ingestion with hybrid vector and lexical retrieval, memory lifecycle management, graph-backed entities, preferences, facts, and cited search through ArcadeDB. It also supports provider-agnostic e | |
| Salesforce MCP Server chetyz/mcp_salesforce Enables Claude to interact with Salesforce for querying, modifying, and managing objects and records, with automatic integration setup for external services like WhatsApp, Slack, email, and webhooks. | |
| croissant-mcp cheungbrenden/croissant-mcp MCP server that gives Claude programmatic access to a local En Croissant chess opening trainer, enabling conversational opening prep by reading its SQLite database, PGN files, and Lichess API. It supports repertoire review, due cards, and o | |
| JianDaoYun MCP Server cheungxin/jiandaoyun-mcp-server A Model Context Protocol server for JianDaoYun form data management, supporting complete CRUD operations, advanced queries, and automatic field type matching across multiple applications. | |
| things3-mcp-gtd chevalicious/things3-mcp-gtd An MCP server for Things 3 on macOS that enables AI assistants to manage tasks using the Getting Things Done (GTD) methodology, including capture, clarify, organize, reflect, and engage stages. |
38,301–38,350 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.