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 |
|---|---|
| KYA-BRASIL celfons/kya-brasil Know-your-agent backed by ICP-Brasil: a company (e-CNPJ) or a person (e-CPF) signs that an AI agent acts for them, within a mandate. Signed credentials and verdicts, CRL checks, MCP + HTTP with x402, and an npm library to verify or issue wi | |
| Hello MCP Server celfons/mcp A stateless MCP server for Cloudflare Workers that uses createMcpHandler to expose a simple greeting tool, requiring no persistent state. | |
| ClinicalTrials-MCP celia-zheng/clinicaltrials-mcp Enables searching clinical trials, retrieving trial details, matching patient profiles to recruiting trials, and extracting eligibility criteria from ClinicalTrials.gov. | |
| serum-mcp celian-mrc/serum-mcp An MCP server that lets users generate, edit, and save Xfer Serum 2 presets from plain-English descriptions directly through MCP clients like Claude Code or Claude Desktop, without any separate API keys or LLM calls. | |
| Celi Miro MCP celicular/miro-mcp Enables AI coding assistants to turn live Miro architecture diagrams into semantic, queryable graph context, allowing them to inspect, search, and apply board topology directly to code. | |
| Jira Utilities MCP Server celigo/jira-utilities-mcp-server Provides JIRA issue management and automation through MCP tools and standalone scripts, enabling reading, searching, analyzing, and modifying issues with batch processing and OCR capabilities. | |
| io.github.Hylouis233/bibverify celik274/bibverify Enables MCP clients and AI assistants to verify bibliographic records and BibTeX metadata across multiple scholarly sources, with explainable matching and non-destructive review/apply workflows. | |
| KaaS celik50/kaas Enables MCP clients to query a compiled Markdown knowledge base through a single ask tool that returns cited, wiki-grounded Markdown answers over stdio or streamable HTTP. | |
| GIS Toolkit MCP celikn/gis-toolkit-mcp Enables MCP clients to run whole-dataset GIS operations such as buffer, clip, reproject, overlay, spatial join, dissolve, zonal statistics, and attribute selection by passing file paths in and out, so an entire dataset is processed in a sin | |
| @cellar-door/mcp-server cellardoorexits/mcp-server Give any MCP-compatible AI the ability to create and verify agent departure records. | |
| cellpy-mcp cellpy/cellpy-mcp Lets agents and chat clients load battery cells, collect them into frames, render figures, export data, look up cellpy API calls, and set up batch projects without writing Python. | |
| Composer Kit MCP Server celo-org/composer-kit-mcp This MCP server provides access to Composer Kit React component documentation, examples, and Celo Composer templates for building web3 applications on the Celo blockchain. | |
| celp-mcp celpai/celp-mcp Celp-MCP enables natural-language analytics over SQL, MongoDB, and Databricks warehouses through MCP-compatible clients, converting questions into multi-step database plans and returning markdown reports. | |
| obsidian-semantic-mcp celstnblacc/obsidian-semantic-mcp A persistent memory layer for Claude Desktop that enables semantic search and CRUD operations on your Obsidian vault using local embeddings and PostgreSQL+pgvector. | |
| cb-analytics-mcp celticht32/enterprise-analytics-mcp A standalone MCP server plus admin GUI for Couchbase Enterprise Analytics and Couchbase Capella Analytics, exposing 55 well-typed, audited tools for query execution, schema introspection, and cluster management. | |
| Couchbase-Analytics-MCP celticht32/mcp-couchbase-analytics A production-grade MCP server for Couchbase Enterprise Analytics, exposing 25 tools to execute SQL++ queries, manage schema and indexes, configure links, and monitor cluster health. | |
| fpl-strategy-mcp celyousfi/fpl-strategy-mcp Enables Fantasy Premier League squad management with custom tools for player search, fixture outlook, tier classification, hit math, and chip timing, all using public FPL data without requiring login credentials. | |
| Hegelion cem163/hegelion Enables LLMs to argue with themselves through Thesis → Antithesis → Synthesis prompting for deeper analysis, plus a Player-Coach autocoding loop that independently verifies code implementations against requirements. Supports prompt-driven u | |
| locklens cem6513/locklens Enables auditing of npm, Yarn, and pnpm lockfiles in local project directories or remote Git repositories, returning vulnerability findings filtered by severity threshold in text or JSON. | |
| MariaDB MCP Server cemalturkcan/mariadb-mcp-server Enables AI assistants to securely interact with MariaDB and MySQL databases using granular per-connection read/write permissions and transaction support. It allows users to manage multiple database connections, explore schemas, and execute | |
| DashWebMCP cemberk/dashwebmcp Enables AI agents to interact with Dash dashboards by exposing them as MCP servers via a WebSocket bridge, with automatic tool registration and human-in-the-loop confirmation. | |
| engram-serve cemjuncker605/engram Enables AI coding agents to query a local structural code graph for focused context, inspect relationships, and carry recorded project memory into later sessions. It helps find relevant code before reading full files and supports graph-back | |
| AgentQL MCP Server ceml46064/agentql-mcp Enables AI agents to extract structured data from web pages by providing a URL and a natural-language prompt describing the desired fields. | |
| Sonicmatch cemmehta/sonic-match-mcp Watches video footage to analyze mood, energy, pace, speech, and scene cuts, then returns license-safe BGM shortlists with a 12–20s hook window, beat-snapped cut suggestions, and an ffmpeg ducking/mix spec. Enables agents in Claude Desktop, | |
| Weather MCP Server cemremengu/weather-mcp Provides weather information tools based on the National Weather Service APIs through an SSE-based MCP server that can run as a standalone process or Docker container. | |
| searxNcrawl cemyoon046/searxncrawl Enables AI agents to search the web through configured providers and crawl individual URLs or whole sites into clean Markdown or JSON. It merges and attributes search results and supports authenticated crawls. | |
| J-SQUAD TradingView MCP Combined cenblueone/jsquad_tradeview_mcp A comprehensive MCP server that integrates TradingView Desktop automation, screener API, Yahoo Finance, IDX/BEI tools, backtesting, news sentiment, trade math, and market sessions. It enables traders to perform technical analysis, backtest | |
| tradingview-mcp-py cenblueone/tradingview-mcp-py MCP server for stock analysis providing 30 tools across technical analysis, Yahoo Finance, IDX/BEI, backtesting, news sentiment, and trade math, with no TradingView Desktop required and VPS compatibility. | |
| stoneai MCP Server cenchunjun123/stoneai Exposes CAREL STone automation to AI agents so they can create projects, generate compilable ST code, build, read structured compiler diagnostics and symbol tables, and search System library APIs without opening the IDE — enabling a generat | |
| windext cendaar/windext Enables riders to ask an assistant for wind-sport forecasts at a named spot, combining AROME, ICON, ECMWF, GFS, UKMO and other models into one hourly table with consensus, spread, gust diagnosis, and onshore/offshore safety relative to the | |
| DNS MCP Server cenemil/dns-mcp-server Enables comprehensive DNS operations including lookups for various record types, reverse DNS queries, batch processing, and DNS resolution tracing. Supports multiple DNS servers with configurable caching and robust error handling. | |
| discord-music-mcp cengizhanpece/discord-music-mcp Enables Claude and other MCP clients to control music playback in Discord voice channels by routing tool calls to a locally running Discord YouTube DJ bot. Lets users play songs by URL or YouTube search, search without playing, list availab | |
| anytype-grpc cengizozel/anytype-grpc Enables AI assistants to control Anytype objects, blocks, and views via its internal gRPC API. | |
| MemoryAI Local cenkierpiotr/memoryai-local-windows2 Provides persistent long-term memory and local RAG document search for Claude Desktop, fully offline. Enables memory save/search and document retrieval via MCP. | |
| database-mcp-server cenmiao/database-mcp-server A Model Context Protocol server for unified database access and management, supporting multiple databases with CRUD operations, transactions, metadata queries, and built-in security features. | |
| discord-mcp center2055/advanceddiscordmcp Comprehensive Discord server management through MCP, enabling channel, role, permission, message, moderation, and automation tasks via natural language. | |
| Centia MCP Server centia-io/mcp-server Exposes the Centia API as MCP tools generated from its OpenAPI spec, enabling natural language interaction with Centia services. | |
| Gemini CLI MCP Server centminmod/gemini-cli-mcp-server Bridges Google's Gemini CLI with MCP-compatible clients and integrates OpenRouter API for access to 400+ AI models. Provides 33 specialized tools enabling multi-AI workflows, collaborations, and debates between Claude, Gemini, and other LLM | |
| cic-mcp-gateway centralinfracore/cic-mcp-gateway Compiles and routes context from trust-domain sources (session, workdir, knowledge, shared) into unified, trust-tagged context envelopes for agents, without storing any data itself. | |
| cic-mcp-session centralinfracore/cic-mcp-session Stores and serves a single conversation/session context for CIC agents, providing event ingestion, timeline projection, and search capabilities within a session scope. | |
| cic-mcp-shared centralinfracore/cic-mcp-shared Enables cross-session memory, weighting, and factory/PR/artifact linking for CIC agents, aggregating multiple sessions to identify promotion candidates. | |
| CashClaw GHL MCP centrender/highbridge-ghl-mcp An MCP server for GoHighLevel with 82 live-tested tools, enabling CRM operations like contact management, appointments, invoices, and workflows via natural language. | |
| mcpbrain centrepoint-church/mcpbrain A local-first personal knowledge daemon that syncs Gmail, Drive, and Calendar into a SQLite store for search and context retrieval via Claude Desktop over MCP. | |
| Centric Demo MCP centricai/centric-demo-mcp A public demo MCP server that exposes Centric RM tools (list contacts, brief, draft, radar, temperature check) with a frozen fictional cast, safe for registry listing. | |
| @centry-digital/bukku-mcp centry-digital/bukku MCP server enabling AI assistants to manage invoices, contacts, products, and other accounting data through the Bukku API. | |
| mcp-server-engine ceonex420/mcp-server-engine An archived MCP server providing 14 tools (bant_qualify, ocr_extract, asr_transcribe, etc.) originally built on Python/FastAPI/Cloud Run. | |
| Kratos MCP ceorkm/kratos-mcp Ultra-lean memory system for AI coding tools that stores project knowledge locally with SQLite and enables AI to remember your project across sessions. | |
| ReactBits MCP Server ceorkm/reactbits-mcp-server A Model Context Protocol server that provides AI assistants with access to ReactBits.dev components - a collection of 135+ animated React components for creative developers. | |
| ghl-context-mcp ceosykes/ghl-context-mcp Enables AI agents to pull focused GoHighLevel context before talking to a contact, including contact lookup, timeline summaries, pipeline positions, and appointments, with optional guarded writes. It helps agents brief themselves on a perso | |
| Google Ads MCP Reader ceotind/open-google-mcp A read-only MCP server for querying Google Ads data using GAQL, enabling AI assistants to safely read campaign performance, ad groups, and keywords. |
37,601–37,650 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.