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 |
|---|---|
| universal-browser-bridge code-x-coffee/universal-browser-bridge Enables MCP-compatible AI agents to securely control Chrome tabs via a local bridge, with explicit per-tab sharing and human approval for consequential actions. | |
| lsp-tools-mcp code-yeongyu/lsp-tools-mcp Exposes Language Server Protocol (LSP) tools such as diagnostics, goto definition, find references, symbols, and rename as a stdio MCP server. | |
| Perplexity Advanced MCP code-yeongyu/perplexity-advanced-mcp An advanced integration package that leverages OpenRouter and Perplexity APIs to provide enhanced web search capabilities, offering both simple and complex query processing with file attachment support. | |
| mitm-ssh code1-de/mitm-ssh-mcp Enables Claude to connect to remote hosts, run SSH commands, and read output while streaming the live terminal session in a visible window so users can monitor and debug connections in real time. | |
| mcp_query_table code1990/mcp_query_table A MCP server that queries financial website tables using Playwright, enabling automated data retrieval from sources like Tonghuashun and East Money, and exposing the results via MCP tools. | |
| MCP Email Server code2hack18/mcp Enables AI clients like Cursor to send emails via Resend, supporting multiple recipients, subjects, and HTML bodies, with configuration through environment variables. | |
| wxmon code2rich/wxmon Enables AI assistants to list, search, and retrieve locally collected WeChat Official Account articles, including full Markdown bodies when available, through MCP tools. | |
| IIIF MCP Server code4history/iiif_mcp MCP server for IIIF integration, enabling image fetching, manifest exploration, annotation search, and authentication support for cultural heritage resources. | |
| Cox's Bazar AI Itinerary MCP Server code4mk/mcp-boilerplate Provides travel planning tools for Cox's Bazar, Bangladesh, including weather forecasts, AI-powered itinerary generation, and pre-configured travel planning prompts. | |
| nerima-open-data-mcp code4nerima/nerima-open-data-mcp An MCP server that enables AI clients to search open data from Nerima City, Tokyo, including public facilities, AED locations, shelters, and parks. | |
| youtube-mcp code661/youtube-mcp Enables managing a YouTube channel from Claude by listing, searching, editing, and organizing videos and playlists while retrieving channel, video, and thumbnail insights. | |
| Codeabien Nest MCP PostgreSQL codeabien/codeabien-nest-mcp-postgresdb Enables interaction with a PostgreSQL database via MCP, using Docker and NestJS for AI-powered database operations. | |
| obsidian-mcp-guard codeafix/obsidian-mcp-guard Provides read/write file tools with lint validation to prevent agents from writing malformed Obsidian markdown, and constrains writes to a single configurable vault for security. | |
| Jules MCP Server codeagentbridge/jules-mcp-server An MCP server that exposes Google Jules Agent operations, enabling MCP-compatible clients to list sources, manage sessions, and inspect activities via the jules-agent-sdk. | |
| hsm-mcp codealandebug/hsm-mcp Enables querying the Dutch IND public register of recognised sponsors for work/residence permits. Offers tools to search sponsors by name or KvK number and check register status. | |
| Code & Blocks WordPress MCP codeandblocks/cb-wp-mcp Enables Claude to manage WordPress sites through a self-hosted MCP endpoint, including content, media, plugins, themes, page-builder pages, SEO fields, plugin data, theme files, PHP snippets, and updates with approval controls. | |
| BigQuery MCP Server codearranger/mcp-server-bigquery Enables LLMs to interact with Google BigQuery by inspecting database schemas, listing tables, and executing SQL queries. This server facilitates seamless data analysis and management through natural language via the Model Context Protocol. | |
| Kawa Code MCP codeawareness/kawa.mcp Team-aware memory for AI coding assistants that tracks intent, records decisions, and detects real-time conflicts before commit. | |
| Ticket API MCP Server codebasics/ticket-mcp-server An MCP server exposing the internal Ticket API to MCP clients, built with FastMCP's OpenAPI integration. | |
| CI Investigator MCP codebkashif/ci-investigator-mcp Provides tools to analyze and debug GitHub Actions CI failures, including summarizing failures, detecting flaky tests, and suggesting fixes. | |
| kilogent-browser codebridger/kilogent-browser MCP server that lets agents drive your real Chrome browser with existing logins and sessions via an outbound-only WebSocket extension. It exposes Playwright-compatible browser tools for navigation, clicking, typing, and snapshots. | |
| pharos-guardskill codebycinar/pharos-guardskill Pre-transaction security gate for Pharos AI agents that analyzes contract bytecode and on-chain state to assess risks like upgradeability and honeypot controls. | |
| Sensei codebyellalesperance/sensei Provides Claude with persistent memory about the user's skills, learning history, and project context to deliver personalized, adaptive explanations and avoid repeating basics. | |
| two-crowds codebyjaini/two-crowds Enables users to query Polymarket-vs-options probability comparisons, today’s disagreements, track-record scores, and implied probabilities for stock price levels through read-only MCP tools, plus a prompt for finding where the crowds disag | |
| CarlaMCP codebymov/carla-mcp Enables natural language-driven creation and execution of autonomous-vehicle scenarios in the CARLA simulator, with validated primitives and replay support. | |
| LinkedIn Poster MCP codebytemirza/linkedin-post-mcp MCP server that lets you publish text and image posts to LinkedIn, fetch your profile, and check auth status using natural language. | |
| GitLab PR Analysis MCP Server codebywaqas/mrconfluencelinker-mcp-server Integrates GitLab merge request analysis with Confluence documentation, allowing users to fetch merge request details, analyze code changes, and store analysis results in Confluence pages. | |
| Weather MCP Server codebywaqas/weather-mcp-server An MCP server that provides real-time weather information including temperature, humidity, wind speed, and sunrise/sunset times through the OpenWeatherMap API. | |
| runn-mcp codecoolglobal/runn-mcp A generic MCP server that wraps the Runn REST API v1 (read + write) with ID-based tools and dry-run safety for write operations. | |
| CredVault codecorelab/credvault Enables AI clients to discover and invoke authorized task-level capabilities with automatic secret injection, response redaction, approval workflows, and hash-chain audit logging without exposing raw credentials. | |
| mnemosyne-mcp codecorelab/mnemosyne-mcp Provides AI agents with persistent local memory management, including semantic recall, knowledge graph traversal, and automatic memory consolidation, enabling structured long-term memory across MCP clients. | |
| Nockit MCP codecrack-01/nockit A lightweight MCP server that enables AI assistants to execute local development tools and retrieve system status with low latency over stdio or HTTP. | |
| Overleaf MCP codecrack-01/overleaf_mcp Enables LLM agents to read and update Overleaf LaTeX papers via git, with tools for reading/writing main.tex and bibliography files. | |
| MCP Documentation Crawler codecracker2020/mcp-server-crawler This server crawls documentation sites and provides search and page-retrieval tools through MCP, enabling users to query indexed documentation content. | |
| GitHub Issue Intelligence MCP codecrafters-alt/mcp-server Enables AI clients such as Cursor to interact with GitHub repositories and perform issue listing, triage, health checks, prioritization, commenting, weekly digests, and release-note generation through purpose-built MCP tools. | |
| Local Voice MCP codecraftersllc/local-voice-mcp Enables MCP clients to speak by running local voice models using Chatterbox Turbo TTS or Kokoro TTS, with support for voice cloning, paralinguistic tags, and multiple voices. | |
| codecrafting-cloudflare-mcp codecraftingdevelopment/codecrafting-cloudflare-mcp Enables read-only access to Cloudflare analytics for the codecrafting.fr zone, providing traffic, threats, and path attack data via local MCP tools for Claude Code. | |
| JetBrains MCP Bridge codecraftingdevelopment/codecraftingdevelopment-mcp-jetbrain A bridge that enables MCP clients like Cascade and Windsurf to interact with tools and features within JetBrains IDEs. It facilitates communication between the client and the IDE via an SSE connection on a dedicated local port. | |
| kindle-dashboard codecube/kindle-mcp-dashboard Enables MCP clients to design and update an e-ink dashboard for a Kindle Paperwhite EY21, with widgets, live system metrics, and HTTP-based rendering. | |
| recit codedbytahir/recit Free, open-source screen recording MCP server for AI agents. Enables screen capture, screenshots, and frame extraction locally without cloud dependencies. | |
| ts-quiz-mcp codedonkeyuk/quiz-mcp Enables an LLM to act as a quiz master by generating and saving quiz questions, then issuing tests and recording results for long-term tracking and analysis. This lets users identify weak points and monitor progress over time. | |
| ts-mcp-tools codedonkeyuk/ts-mcp-tools Enables developers to build and deploy MCP servers with multiple modular tools bundled into a single executable file. | |
| Telegram MCP Server codedpro/telegram-mcp-server Lets any MCP-compatible AI agent read, search, and send Telegram messages through your real account via MTProto. | |
| Refactory codedrop-codes/refactory Hybrid code decomposition — AI plans module boundaries, deterministic engine handles routine extractions. Split monoliths into clean modules. JS and Python built in, AGPL-3.0. | |
| Material UI MCP Server codedthemes/mui-mcp-codedthemes Provides AI assistants with comprehensive access to Material UI documentation, component details, and setup guides for building React applications. It enables searching through 50+ components and provides structured information on imports, | |
| streamprobe-mcp codedtx/streamprobe-mcp Diagnoses HLS and DASH streams by reading manifests over HTTP, checking rendition ladders, segment timing, live windows, and DRM, and reports issues with evidence—no ffmpeg required. | |
| ophelia-execution-verifier codedvibesx/ophelia-execution-verifier MCP server that verifies restaurant booking outcomes by reconciling API claims against independent re-reads, with a recovery dial for stakes-based retry policies. | |
| RheinAgent File Upload codeelchi/rheinagent-file-upload Enables agents to securely stage, validate, and submit binary data for on-premises storage, then list, inspect, process via registered server-side processors, and token-guarded delete those assets using opaque identifiers. Upload bytes trav | |
| MCP Model Provider Example codeexplorehub/mcp_test Demonstrates a complete MCP server implementation supporting both local Ollama models and remote API models. Enables LangChain applications to dynamically discover and invoke tools including addition calculations and model invocation capabi | |
| mcp-proxy codefilabs/claude-desktop-skills-proxy Bypasses Claude Desktop sandbox network restrictions by providing tools to fetch any URL, execute network-capable CLI commands (yt-dlp, curl, ffmpeg), and read files created by those tools. |
39,651–39,700 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.