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 Relay Server econ-watch/mcprelay Exposes provider-specific tools and relays HTTP requests to configured providers like Supabase, Vercel, and Context7, enabling interaction with multiple external APIs through a unified MCP interface with configurable authentication and acce | |
| Practitioner Knowledge MCP econmatrix007/practitioner-knowledge-mcp Enables Claude to save, retrieve, update, search, and organize personal ideas and reusable analytical frameworks in a private SQLite-backed knowledge base. Supports local desktop use or always-on access across a user's own devices over a pr | |
| 0G MCP Server econyx-ai/0g-mcp-server Enables interaction with 0G.AI decentralized infrastructure including documentation access, storage operations (file upload/download, key-value store), and AI service discovery on the 0G Compute Network with TEE verification and pricing inf | |
| Siri Shortcuts MCP Server ecook70017/mcp-server-siri-shortcuts Enables LLMs to list, open, and run automations from the macOS Shortcuts app, with optional input parameters and dynamically generated tools for each available automation. | |
| Ecosyste.ms Package Data ecosyste-ms/mcp Enables querying package ecosystem data from ecosyste.ms, including package metadata, versions, security advisories, dependencies, and repository information across 40+ package registries with fast local SQLite lookups and API fallback. | |
| Science MCP ecosyste-ms/science-mcp Enables local MCP clients to search software names, look up exact identifiers, and retrieve project summaries, packages, and direct dependencies from ecosyste.ms Science, with an optional offline SQLite snapshot for lookup. | |
| Ecovacs MCP Server ecovacs-ai/ecovacs-mcp A control server that enables AI assistants to interact with Ecovacs robot vacuums through MCP protocol, supporting device listing, cleaning control, charging control, and status queries. | |
| Laraguard MCP ecr17dev/laraguard-mcp A security audit server for Laravel projects that performs static code analysis, dependency CVE checks, and configuration audits. It enables developers to detect vulnerabilities like SQL injection and XSS while providing active attack simul | |
| gigahost-mcp ecschoye/gigahost-mcp Exposes the Gigahost REST API (DNS, domains, servers, web hosting, etc.) to MCP clients via a single passthrough tool, enabling natural language management of Gigahost resources. | |
| etAI MCP Server ectdev/etai Enables assistants such as Claude Desktop to call document search over a folder of markdown as a tool, returning grounded answers with citations or measured refusals when the evidence is insufficient. | |
| Ed-Fi SDK MCP ed-fi-exchange-oss/ed-fi-sdk-for-ai-assistants Enables AI assistants to explore Ed-Fi API endpoints, schemas, and generate entity relationship diagrams, aiding development of Ed-Fi client applications. | |
| Competitive Intelligence MCP Server ed-lin12/competitive-mcp Provides structured competitive intelligence profiles and listing capabilities through natural language prompts, enabling on-demand sales collateral from a single source of truth. | |
| dbmole-mcp ed-smartass/dbmole-mcp Enables AI agents to add, edit and remove their own PostgreSQL and MySQL connections at runtime, stored in a per-project or global file that is hot-reloaded on every tool call. Connections can run through SSH tunnels with TLS verification, | |
| mcp-peek ed-smartass/mcp-peek Optimizes REST API calls for AI agents by returning compact schemas instead of full responses, allowing agents to fetch only needed fields via jq masks, reducing token consumption by up to 50x. | |
| Túnel Chat MCP edalxgoam/tunel_chat_mcp_own Enables working with private files on a local machine from ChatGPT through OpenAI Secure MCP Tunnel without opening inbound ports or exposing the local server to the Internet, with tools for listing, reading, creating, modifying, deleting, | |
| mail-mcp edamame-x/simple-mail-mcp Enables read-only Gmail access via MCP, allowing users to list and retrieve email messages with query and pagination support. | |
| gmail-mcp edarrington/gmail-mcp Enables Gmail integration with Claude Code for reading, sending, searching emails, and managing labels through natural language. | |
| proxmox-mcp-server edasan0568/proxmox-mcp-server Enables management of Proxmox VE environments via the Proxmox API, including node listing, guest management, and VM/LXC creation with Cloud-Init. | |
| PG Airman MCP edb-korea/pg-airman-mcp-multidb Enables AI agents to interact with PostgreSQL databases through MCP, offering index tuning, query plan analysis, schema intelligence, health checks, and safe SQL execution, with support for multiple databases. | |
| banker-hub-mcp eddiedibs/banker_hub_mcp Exposes an aggregated banking transaction history — paginated Binance and BNC transaction listing, source freshness, single-transaction lookup, and per-asset credit/debit/net summaries — to LLM clients over stdio. All tools are read-only, a | |
| actiongate eddiedotdev/actiongate-examples Pre-execution safety layer for autonomous agent wallets. Risk scoring, transaction simulation, and policy enforcement via MCP. | |
| preflight-mcp eddiehale3/preflight-mcp Enables pilots to assemble a preflight briefing per 14 CFR §91.103 by fetching weather, airport info, aircraft performance, fuel estimates, alternates, and NOTAMs. | |
| retrieval_mcp_server eddieiskl/novaops-company-brain Enables LLMs to access cited company documents and perform permission-gated operational actions (HR, IT access, vendor extraction, renewal) with explicit scope, evidence checks, and durable human approval gates. | |
| hestia eddienubes/hestia Enables users to search Airbnb listings using natural language, including flexible dates, guest counts, price range, property type, and amenities. It provides listing summaries and details but does not handle bookings. | |
| markupR MCP Server eddiesanjuan/markupr Enables AI coding agents to capture screen and voice recordings, extract timestamped frames, and receive structured Markdown reports with context for bug fixing and UI feedback. | |
| poker-solver eddieyang-97/poker-solver Enables heads-up Texas Hold'em river analysis by exposing exact showdown equity/call EV and restricted-tree CFR+ solve frequencies/action EVs through MCP tools. It is intended for post-session review, not live or unconstrained GTO decisions | |
| Payment Delay MCP eddii1/mcp-payment-delay Enables any MCP-compatible LLM client to invoke a trained classifier for predicting customer payment delays through exposed tools, resources, and a prompt, with no client-specific integration code. | |
| amp-mcp-server eddinsw/amp-mcp-server MCP server that wraps CubeCoders AMP to list, inspect, and control game-server instances. | |
| Arxivum eddisonpham/arxivum An MCP server that enables searching arXiv, importing papers, enriching with citation data, generating summaries and research ideas, and querying a local library using local LLMs and embeddings. | |
| Pexels MCP Server eddjesus/pexels-mcp-server Enables searching and retrieving free photos and videos from Pexels using natural language queries, with support for filters like orientation, size, color, and duration. | |
| Garmin Connect MCP Server eddmann/garmin-connect-mcp A Model Context Protocol (MCP) server for Garmin Connect integration. Access your activities, health data, training metrics, and more through Claude and other LLMs. | |
| intervals-icu-mcp eddmann/intervals-icu-mcp A Model Context Protocol (MCP) server for Intervals.icu integration. Access your training data, wellness metrics, and performance analysis through Claude and other LLMs. | |
| Obsidian MCP Server eddmann/obsidian-mcp Enables LLMs like Claude and ChatGPT to access and manage git-backed Obsidian vaults through tools for file operations, search, tags, and journal logging. | |
| strava-mcp eddmann/strava-mcp MCP server for Strava integration, enabling LLMs to query activities, athlete stats, segments, routes, and perform training analysis. | |
| onenote-mcp-python eddyficial/onenote-mcp-python A standalone Model Context Protocol server for Microsoft OneNote desktop, connecting via the Windows COM API through a PowerShell bridge to enable page CRUD, search, export, and organization tools without an API key. | |
| OneNote MCP for Windows eddyficial/onenote-mcp-windows Connects to Microsoft OneNote desktop via COM API, exposing 27 tools for hierarchy, page CRUD, search, rich content, export, health checks, and more. Enables natural-language control of OneNote without API keys or embedded AI providers. | |
| recall-mcp eddyflores100-lang/recall-mcp Provides persistent, cross-session memory for AI agents, letting them store, search, and manage memories with tools like remember, recall, forget, list, summarize, and import/export. | |
| Gemini-Proxmox VE Operator eddygk/gemini-proxmox Enables Google Gemini and any MCP-compatible client to securely monitor and manage hypervisor guests — starting, stopping, rebooting, snapshotting, rolling back, and backing up VMs and containers — through the Model Context Protocol over St | |
| WinCU eddyhhlure1eddy/win-cu An MCP server that lets AI models operate a Windows PC through screenshots, mouse, keyboard, clipboard, window control, and UI Automation, with safeguards for user input and restricted applications. | |
| Postgres MCP Server eddykuhan/postgres-mcp Enables interaction with PostgreSQL databases through MCP, allowing users to explore database structures, inspect table schemas, and execute read-only SQL queries. | |
| Chrome Devtools Advanced MCP eddym06/chrome-devtools-advanced-mcp Enables AI assistants to control Chrome using real user profiles, providing undetectable automation with over 40 tools for navigation, data extraction, and interaction. | |
| Eddyter MCP Server eddyterai/eddyter-mcp Connects AI assistants to Eddyter, the AI-powered rich text editor for React, Next.js, Vite and Remix. Check your license, plan and AI credit usage, turn editor features (AI chat, tables, comments, image upload, exports) on or off live, and | |
| TaskGrade MCP Server eddyvlad/taskgrade Classifies software implementation tasks using local Ollama models and recommends coding-agent models based on a deterministic policy. | |
| Salesforce Metadata-Aware RAG MCP eddywebs/sfdxmcp Enables AI copilots to understand and query Salesforce org configurations through intelligent metadata chunking and semantic search. Provides access to Apex classes, custom objects, flows, layouts, and other metadata with hybrid vector and | |
| TelegramBotMCP edealvea/telegrambotmcp Enables a Telegram chatbot to create Google Calendar events, schedule reminders, and summarize CSV files via an AI agent using the Model Context Protocol. | |
| job-search-mcp edefice/job-search-mcp Enables searching justjoin.it for job listings and tracking applications locally with status updates, all via natural language in Claude. | |
| django-admin-fastmcp edelvalle/django-admin-fastmcp Exposes the Django admin as an MCP server, letting authorized staff interact with admin models via natural language while delegating all permissions to the existing ModelAdmin. | |
| Overseerr MCP Server edemal/mcp-server-overseerr Enables interaction with Overseerr media request management through natural language. Supports searching for movies/TV shows, managing media requests, approving/denying requests, and monitoring server status. | |
| Accord edenbuilds/accord Provides a policy-controlled MCP gateway that lets agents invoke tools with explicit policies, bounded execution, scoped visibility, and decision receipts. | |
| maharashtra-courts-drafting edenbuilds/maharashtra-courts-drafting Local-first MCP server that generates court-ready pleadings for Bombay High Court and Maharashtra tribunals, using fill-in templates, bench-aware formatting, and a multi-agent drafting pipeline. |
46,901–46,950 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.