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 |
|---|---|
| Kroger MCP Server ericlott/kroger-mcp Allows Large Language Models to interact with Kroger's grocery services, enabling product search, store lookup, and cart management through the Model Context Protocol. | |
| Pipedrive MCP Server ericluciano/pipedrive-mcp Enables AI assistants to interact with the Pipedrive CRM to manage deals, contacts, organizations, and activities. It features automatic custom field synchronization and guided onboarding to ensure assistants follow specific business rules | |
| sienge ericluciano/sienge-agent Enables Claude to read photos of invoices and create accounts payable entries in the Sienge construction ERP, with supplier lookup, expense classification, duplicate checking, and user confirmation before posting. | |
| youtube-mcp ericluciano/youtube-mcp A local MCP server for extracting YouTube video transcripts, metadata, and performing visual analysis using Gemini Vision or local Whisper models. It enables users to process video content through various tools for subtitle retrieval and fr | |
| calendly-mcp ericlucianoferreira/calendly-mcp Enables Claude to schedule, query, and cancel Calendly events via Calendly API v2, allowing direct event management without the public booking form. | |
| Genie ↔ Fabric/Power BI bridge ericlxbgit/databricks-genie-fabric-mcp Enables MCP clients to ask Databricks Genie questions, check Fabric mirroring health, manage Power BI datasets and reports, and create Copilot-ready handoff prompts. | |
| agent-jmap-mcp ericmaddox/agent-jmap-mcp Enables AI agents to manage email over JMAP, including inspecting mailboxes, searching and retrieving messages, navigating threads, downloading attachments, triaging inboxes, and sending emails atomically via HTTP. | |
| Calyx MCP ericmaddox/calyx-mcp Enables AI coding agents to evaluate code snippets and learn from execution outcomes through local bio-inspired associative memory, delivering instant zero-token bug and antipattern reflexes without LLM inference. | |
| Compressor Reflex MCP ericmaddox/compressor-reflex-mcp Enables MCP-compatible developer environments to shrink verbose tool outputs—test logs, git diffs, directory listings, and file dumps—before they reach the context window, preserving compiler errors, failure signatures, and decisive anchors | |
| System 1 MCP Server ericmaddox/system1-mcp Provides AI agents with low-latency reflex tools for fast safety checks, option selection, verification, and scoring using calibrated probabilities, reducing reliance on slow LLM deliberation. | |
| stessa-mcp ericmanyc/stessa-client-ts MCP server for Stessa rental-property accounting platform, enabling AI agents to query properties, portfolios, banking, documents, and tenancies via natural language. | |
| TenantCloud MCP Server ericmanyc/tenantcloud-client-ts Enables AI agents to manage rental properties on TenantCloud via natural language, including contacts, messaging, maintenance, and financials. | |
| HAPI-MCP ericmc21/hapi-mcp A Model Context Protocol server that enables querying FHIR healthcare data using natural language, allowing doctors to retrieve patient information, medications, observations, and other healthcare records. | |
| mcp-plotting-server ericmjl/mcp-plotting-server A FastMCP server that turns JSON data into Plotly figures, deployable as an isolated service on Modal. Data goes in as JSON; a validated Plotly figure (JSON) or a rendered PNG comes back over the Model Context Protocol. | |
| erm-github-mcp ericmusa-ibm-public/erm-github-mcp A minimal MCP server that exposes health-check and server information tools over stdio or HTTP, and can be containerized and deployed to IBM Code Engine. | |
| Feedback Pipeline MCP Server ericnotion/feedback-pipeline-mcp Bridges Notion custom agents with Claude Code to automate bug reproduction and fix implementation. It utilizes Playwright for browser automation to verify issues and Claude Code to develop and test software fixes. | |
| Real Estate Investment MCP Server ericnsibley/genai_mcp An MCP server that connects to a SQLite database of Zillow real estate data, enabling users to explore property values, rent indexes, and forecasts through a chat interface to make informed investment decisions. | |
| mcp-tool-search ericnunes30/mcp-gateway-proxy A standalone MCP gateway/proxy server that lets any MCP-compatible client search and call tools across multiple downstream MCP servers through a single mcp proxy tool. | |
| Langfuse MCP Server ericortiz604/langfuse-mcp Enables AI agents to locally inspect and debug trace data, sessions, exceptions, routing decisions, prompts, datasets, annotation queues, scores, and metrics, with compact output, selective tool loading, and read-only mode. | |
| cervo ericovis/cervo Enables management of static website hosting on a shared VPS through an AI chat interface, providing tools for configuration and deployment. | |
| Swiss Lawyer MCP ericp/swiss-lawyer-mcp A production-minded Agentic RAG backend for informational guidance about Swiss immigration and administrative procedures, using only official Swiss government sources with evidence metadata. | |
| jevcore-mcp ericpatel80/jevcore Exposes three tools over MCP stdio that answer typed questions — yes/no, choice, and score — returning calibrated probabilities instead of prose, with offline mock answers by default and explicit egress reporting before any live transmissio | |
| Framer MCP Server ericpjtsai/framer-mcp-server Connects MCP clients to Framer projects for reading sites, editing CMS content, designing pages with a DSL, managing code components, and previewing changes locally. | |
| WhatsApp MCP Server ericporres/whatsapp-mcp-server Connects WhatsApp group chats to Claude, enabling reading, searching, exporting, replying, and AI-powered intelligence processing of conversations. | |
| Joke MCP Server ericqian77/joke-mcp Enables developers to retrieve short jokes in multiple categories and languages during task processing. Provides fast offline fallbacks and configurable joke providers for entertainment during development workflows. | |
| Concisr ericrdzmtz/concisr Token compression for AI contexts, reducing token consumption by compressing conversation exchanges before they enter the LLM context window. | |
| gwen-digestor ericrdzmtz/gwen-digestor Model Context Protocol server for conversation compression that reduces token consumption using deterministic, embedding-free compression with mode-aware strategies. | |
| tinytask ericroliver/tko A minimal task management system for LLM agent collaboration via the Model Context Protocol, supporting CRUD operations, task blocking, subtasks, queues, and comments. | |
| Express MCP Server ericsegovia/mcp-examples A basic serverless MCP server example running on Netlify Functions using Express. Demonstrates how to deploy and run Model Context Protocol servers in a serverless environment. | |
| Perfect Web Clone IDE ericshang98/perfect-web-clone-ide Enables pixel-perfect website cloning from within the IDE by extracting real source code, styles, and assets, and assembling them into a React project with live preview. | |
| MBTA Worcester Line MCP Server ericskiff/mbta-mcp Provides real-time train schedule information and live predictions for all 18 stations on the MBTA Worcester Line. It enables users to query upcoming departures and filter by direction or date through natural language. | |
| ComfyUI MCP ericsunsk/comfyui-mcp Minimal MCP server that wraps ComfyUI HTTP routes enabling LLM clients to inspect server status, models, features, node metadata, submit workflows, manage queue/history, interrupt runs, and upload images. | |
| Joplin MCP Server ericsyed14666/joplin-mcp Enables AI assistants to interact with the Joplin note-taking application via its API, supporting note, notebook, tag, trash, and import operations through a standardized interface. | |
| DuckDuckGo MCP Server ericthered926/duckduckgo-mcp-server Provides web and news search via DuckDuckGo with support for region filtering, time ranges, and token optimization for AI assistants. | |
| ops-platform-mcp ericthlai/ops-platform-mcp MCP server wrapping a mock internal ops platform (FastAPI + SQLite) so Claude Code can read and write employee, project, task, and time data through natural language. | |
| ops-platform ericthlai/ops-platform-mcp-demo Lets an AI assistant read and write business records in plain language, including looking up people, creating and updating tasks, logging time, and pulling utilization reports through a synthetic ops platform or an optional ClickUp adapter. | |
| Verified Burst ericutility-prog/verified-burst-broker MCP stdio server, one tool buy_verified_burst — x402 pay-only-if-verified inference. | |
| bitrix24-mcp-server ericvanin/bitrix24-mcp-server A secure, self-hosted MCP server for Bitrix24 CRM that enables reading CRM data and performing confirmation-gated writes through schema discovery and OAuth integration. | |
| sg-haze-rain-mcp ericwang915/sg-haze-rain-mcp Zero-config MCP access to Singapore's live NEA air quality and rainfall data, including pollution levels, weather warnings, health advice, and local forecasting based on inferred or provided locations. | |
| Plex-MCP ericwarthan/plex-mcp Enables full management of a Plex Media Server via Claude, including browsing libraries, fixing metadata, managing collections, and more. | |
| TikRSS MCP Server ericx0/tikrss-cli Connects AI agents such as Claude Desktop and Cursor to your personal video and podcast briefing archive over stdio. Enables agents to fetch daily synthesized briefings, read full video distillations, semantically search claims and argument | |
| crypto-earn-mcp ericxstone/crypto-earn-mcp Provides market data and user position information from earn providers like AAVE, enabling queries on APRs and deposits across multiple blockchain networks. | |
| Scan QRCode MCP Server ericyangpan/scan-qrcode-mcp Enables decoding QR codes from images provided as either base64 data URLs or HTTP(S) image URLs. Supports common image formats and returns the decoded text content with clear error handling. | |
| gpuctl-mcp ericyuan2007/gpuplane Enables AI agents to manage GPU training end-to-end through natural language, including submitting and scheduling jobs, monitoring logs and metrics, diagnosing failures, comparing runs, and recommending the best checkpoints. | |
| TesteMCP ericzaim/testemcp MCP server for reading and listing JSON documents, designed to be used with Claude Haiku and Headroom compression to reduce token usage. It demonstrates an end-to-end MCP tool-use loop with stdio transport. | |
| Postgres MCP Server ericzakariasson/pg-mcp-server Enables LLMs to query and analyze PostgreSQL databases through a controlled interface. Supports SQL query execution, table schema inspection, and optional write operations with safety controls. | |
| Uber Eats MCP Server ericzakariasson/uber-eats-mcp-server A proof-of-concept Model Context Protocol server that enables LLM applications to interact with Uber Eats, allowing AI agents to browse and order food through natural language. | |
| todo-demo ericzcz/learn_mcp Provides todo management capabilities, allowing AI agents to add, list, and complete tasks via MCP tools, resources, and prompts. | |
| dtrpg-mcp erik-saltwell/dtrpg_mcp Enables searching your DriveThruRPG library and the public catalog for tabletop RPG products, returning structured details like title, description, publisher, and game system. | |
| Charlotte erik8174/charlotte Enables AI agents to browse and interact with web pages through a token-efficient, structured representation of each page rather than raw accessibility-tree dumps. Agents get compact page orientations, targeted element queries, and full int |
48,451–48,500 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.