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 |
|---|---|
| telegram-bot-mcp eweol/telegram-bot-mcp Exposes the Telegram Bot API as tools for MCP clients, enabling sending messages, photos, polls, and more via a Telegram bot. | |
| Splunk SOAR MCP Server ewiges-m/splunk-soar-mcp Enables AI assistants to operate a Splunk SOAR instance headlessly via its REST API, supporting container triage, playbook authoring and execution, and asset management. | |
| mindmap-mcp ewigmidori/mindmap-mcp A local MCP server that combines a browser mind map UI with a Streamable HTTP MCP endpoint, letting AI agents create, edit, and manage mind maps in real time through tools like mindmap_apply_op. | |
| Fountain Pen Ink MCP Server ewilderj/inks-mcp Provides LLMs with specialized knowledge about fountain pen inks, enabling intelligent ink search, color matching, and recommendations through various tools. | |
| Minecraft Structure Lab ewitulsk/minecraftstructureinjector Enables generating NBT structures, placing them in superflat worlds, capturing labeled screenshots, and exporting clean datapacks through MCP. | |
| revision-mcp ewiwlll/revision-os Enables agents to create courses, upload lecture recordings, run the transcription and generation pipeline, retrieve study sheets and flashcards, and export Anki decks. It supports both local operation and a hosted instance with account-tok | |
| fitness-mcp-server ewongz/fitness-mcp-server Provides MCP servers for Claude to access fitness data from Strava and intervals.icu, enabling natural language queries for activity analysis, advanced training metrics, and wellness tracking. | |
| NotebookLM MCP Server ewulff980/notebooklm-mcp Enables citation-backed Q&A grounded in your own uploaded sources, plus programmatic generation of audio overviews, video, infographics, reports, presentations, data tables, flashcards, quizzes and mind maps. It also exposes this over a 33- | |
| nirikshak ewwhardik/nirikshak MCP server for passive domain reconnaissance and attack surface monitoring. It scans subdomains, security headers, TLS certs, and tech stack, detects subdomain takeovers, and reports changes since the last scan. | |
| EXBANK MEO ex-bk/meo-mcp Provides AI assistants read-only access to a store's MEO management data from EXBANK, including reviews, Google Maps ranking trends, performance metrics, monthly reports, and survey answers. It lets users query and summarize listing details | |
| eve-fit-mcp ex-ct/eve-fit-mcp Enables AI assistants to search EVE Online ships, modules and charges, build and validate fits, compute Pyfa-parity statistics, compare fits, run what-if scenarios, and rank candidate modules, charges and drones via batch optimisation. It i | |
| agent-auth ex-nihilo-labs/agent-auth Zero-knowledge credential injection for AI agents. Your agent authenticates to websites and APIs without ever seeing a password, TOTP code, or API key. | |
| glm-image-mcp-server ex-takashima/glm-image-mcp-server MCP server for generating images using Z.AI's glm-image model. Supports image generation with various sizes and qualities, and includes batch CLI functionality. | |
| Google Veo 3.1 MCP Server ex-takashima/google-veo3-1-mcp-server MCP server for Google Veo 3.1 video generation. Supports text/video/image-based generation, extension, and interpolation with cost estimation and batch processing. | |
| Grok Imagine Video MCP Server ex-takashima/grok-imagine-video-mcp-server MCP server for generating, editing, and batch processing videos using xAI's Grok Imagine Video API, with support for text-to-video, image-to-video, and video editing via natural language prompts. | |
| OpenAI GPT-Image MCP Server ex-takashima/openai-gpt-image-1-mcp-server Enables image generation and editing using OpenAI's GPT Image API (gpt-image-1, 1.5, 2) with support for multi-image generation, history management, and batch processing. | |
| Vertex AI Imagen MCP Server ex-takashima/vertexai-imagen-mcp-server Enables image generation and editing using Google Vertex AI's Imagen API through natural language commands in MCP clients like Claude Desktop. | |
| pump-codemode-mcp ex0th3rmic/pump-mcp Enables agents to reach pump.fun's full API surface — official developer routes, bonding-curve reads, Solana RPC, and unsigned trade building — by writing JavaScript against one merged OpenAPI document, using just two tools (search and exec | |
| Pump MCP ex0th3rmic/pump-mcp-bundler Enables coordinated pump.fun buys, sells, and token launches using encrypted local Rust wallets, with previews, simulation, Jito bundle submission, status tracking, and pump.fun API/RPC access through MCP tools. | |
| Exa Websets MCP Server exa-labs/websets-mcp-server Enables creation and management of AI-powered web entity collections (companies, people, research papers) with automated search, data enrichment, monitoring, and verification through Exa's Websets API. | |
| mailpit_mcp exabyteso/mailpit_mcp Enables interaction with a local Mailpit instance for capturing and inspecting test emails during development and E2E testing. | |
| Fetch MCP Server exactdoug/mcp-fetch Enables retrieval and processing of web page content for LLMs by converting HTML to markdown, with support for content truncation and pagination. | |
| document-mcp exadev/document-mcp An MCP server that exposes documents.js's document conversion, .odb, metadata, and font tooling as MCP tools, enabling agents to convert, inspect, and edit a wide range of document formats over stdio. | |
| claude-session-bus exalsch/claude-session-bus Enables Claude Code sessions sharing a project root to broadcast short messages to each other via a JSONL mailbox, with sending as an MCP tool and receiving as a prompt hook. | |
| Examplary MCP Server examplary-ai/mcp Provides AI assistants with access to Examplary's exam management platform, enabling users to create and manage exams, generate questions from materials, grade student responses, and collaborate in workspaces through 60+ API endpoints. | |
| Exasol MCP Server with Governed SQL option exasol-labs/exasol-labs-text2sql-mcp-server Provides LLM access to Exasol database via MCP tools, including metadata reading and data queries, with an optional on-premise text-to-SQL (Governed SQL) translation. | |
| Exasol MCP Server exasol/mcp-server Provides an LLM access to the Exasol database via MCP tools, enabling reading of database metadata and execution of data reading queries. | |
| Excalidraw MCP App Server excalidraw/excalidraw-mcp Enables AI assistants to generate interactive Excalidraw diagrams with viewport camera control and fullscreen editing directly in the chat. | |
| @excalimate/mcp-server excalimate/excalimate Turn Excalidraw diagrams into keyframe animations. AI-powered creation via MCP, E2E encrypted sharing, export to MP4/WebM/GIF/SVG. | |
| meta-insights-mcp excellario/meta-mcp-server Provides Meta (Facebook/Instagram) business insights through the Graph and Marketing APIs, enabling access to ad accounts, pages, campaigns, and business assets using a System User access token. | |
| whatsapp-mcp-server excellario/whatsapp-mcp-server A least-privilege, send-only MCP server for WhatsApp, backed by Meta's official WhatsApp Cloud API. It exposes tools to send text messages and pre-approved templates. | |
| x-feed-mcp excellario/x-feed A least-privilege, read-only MCP server that returns recent tweets from a set of tracked X (Twitter) accounts via a single tool. | |
| home-ai excellence-wh/home-ai Enables control of Mijia (Xiaomi) smart home devices through MCP, including querying homes, devices, scenes, and specs, setting properties, running actions and scenes, and issuing speaker commands. | |
| Things MCP Server excelsier/things-fastmcp Lets you use Claude Desktop to interact with your task management data in Things app, enabling you to create tasks, analyze projects, manage priorities, and implement productivity workflows through natural language. | |
| Things MCP Server excelsier/things-mcp Enables Claude to interact with task management data in the Things app, including creating tasks, managing projects, searching, and organizing priorities. | |
| nats-channel-mcp except-pass/nats-channel-mcp Bridges NATS pub/sub into Claude Code sessions, enabling agents to receive and respond to NATS messages as channel tags with a reply tool. | |
| Kryfto exceptionregret/kryfto Provides 42+ MCP tools for browser automation, web scraping, and search, enabling AI agents like Claude and Cursor to browse, extract data, and run research agents on the live web. | |
| affine-chatgpt-mcp-bridge excitingadventures8/affine-chatgpt-mcp-bridge Enables ChatGPT to search and read documents in an AFFiNE Cloud workspace via MCP, secured by GitHub OAuth and an allowlist. | |
| Reevl MCP exclusiveyon-a11y/reevl-mcp Enables AI assistants to query Korean apartment real-estate data, including official transaction prices, jeonse ratios, and AI price forecasts for 45,000+ complexes. | |
| agent-memes exdzy/agent-memes Enables AI agents to find meme and reaction clips via the Vlipsy API or local folders, look at them as contact-sheet images, and fetch or convert them into rendered assets with attribution sidecars. It also drops those clips into ffmpeg ren | |
| REVAID MCP Server exe-blue/revaid-mcp-server MCP server for REVAID knowledge base with OAuth 2.1 authentication, providing tools for concepts, propositions, relations, and session management. | |
| mika-mcp executant16/mika-mcp Connects the web version of ChatGPT to a local Windows development environment, letting the chat read project files, search and edit code, run commands and tests, and build or verify release artifacts through natural language. It also provi | |
| ExecuteAutomation Database Server executeautomation/mcp-database-server A Model Context Protocol server that enables LLMs like Claude to interact with SQLite and SQL Server databases, allowing for schema inspection and SQL query execution. | |
| execution-run-mcp execution-run/execution-run-mcp Enables AI agents to interact with the Execute.run bot API for managing Shell balances, transferring funds, and executing LLM requests. It provides tools for identity verification, transaction tracking, and performing compute tasks through | |
| Polyagent MCP execveat/polyagent-mcp Enables any MCP-compatible client to use existing Claude Code agents from .claude/agents/ directories. Spawns agents in separate CLI sessions for better context optimization and performance across Codex, Gemini CLI, and other AI coding assi | |
| 3xpl MCP Server exekerey/3xpl-mcp Enables LLMs to interact with blockchain data across 48 networks via the 3xpl JSON API, supporting tools for transactions, addresses, blocks, and more. | |
| Todo List MCP Server exemuneeb/mcp-task A simple MCP server that turns a JSON file into a todo list, letting users add, list, complete, delete, and clear tasks through natural language in MCP-compatible clients. | |
| exfu-multiaccount exfu/multiaccount A local MCP server that lets AI assistants access Gmail, Drive, Docs, and Calendar across multiple Google accounts, routing each request by a human-readable account alias. It supports reading, searching, and writing with per-account tagging | |
| taskmarket-mcp-server exhaustingsky/taskmarket-mcp-server MCP server that connects AI agents to the Taskmarket onchain marketplace on Base, enabling them to browse bounties, claim tasks, submit deliverables, and manage their wallet. | |
| Exegol MCP Server exho7/exegol-mcp Enables AI agents to interact with Exegol pentesting containers to execute commands and manage container status. It includes seven predefined workflows for automated security tasks such as web reconnaissance, port scanning, and vulnerabilit |
49,101–49,150 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.