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 |
|---|---|
| pricecharting-api-mcp deansasek/pricecharting-api Enables Claude Code to interact with PriceCharting pricing data, supporting search, product pricing, categories, and group listings across multiple collectible categories. | |
| RS3 Wiki API MCP Server deansasek/rs3-wiki-api Enables Claude to interact with the RuneScape Wiki through search, page retrieval, extracts, and ASCII image rendering. | |
| tcgplayer-api-mcp deansasek/tcgplayer-api Provides access to TCGplayer trading card data, including search, product details, pricing, and market information, enabling natural language queries for card analysis. | |
| claude-peers deansingh/chief-of-staff-mcp Enables Claude Code instances to discover each other on a local machine and exchange messages instantly, with a broker that coordinates triage and delegation across a peer mesh. | |
| Janus MCP deanward/janus-mcp Enables AI assistants to understand and interact with OpenAPI specifications, providing deep insight into API structures for faster and more accurate API integration. | |
| Starbucks MCP Server deanwenstrand/starbucks-mcp-server Enables ordering Starbucks coffee via AI assistant using Playwright browser automation, supporting login, favorites management, custom orders, and manual order confirmation for safety. | |
| balatro-codex-mcp deanxizian/balatro-codex-mcp Allows Codex desktop to control the Steam game Balatro via local STDIO MCP tools, exposing only constrained normal game actions without debugging or cheat capabilities. | |
| arxiv-mcp dear-pi/arxiv-mcp Enables LLM agents to search arXiv, retrieve paper metadata, extract PDF text, and analyze category submission trends through MCP tools, resources, and a literature-review prompt. | |
| Logseq MCP Server dearcloud09/logseq-mcp Enables AI assistants like Claude to directly read, write, search, and navigate your local Logseq knowledge graph, including managing journals, pages, backlinks, and page relationships without manual copy-pasting. | |
| Factor Meals Canada MCP dearlordylord/factor-mcp Enables authenticated subscribers to inspect weekly menus, recipe ingredients, deliveries, order history, and plan quota, and to preview or replace and save weekly main-meal selections with read-back verification. It also preserves add-ons | |
| obs-mcp dearlordylord/obs-mcp Model Context Protocol server for OBS Studio | |
| Codex DSH Bridge dearosmanthus/codex-dsh-bridge Enables Codex to delegate selected tasks to a locally installed DeepSeek Harness through MCP tools for execution, status, planning, and feedback while keeping orchestration local. | |
| iota-agent-mcp dearsealx-blip/iota-agent-mcp MCP Server for the IOTA blockchain that enables AI coding agents to interact with IOTA directly. | |
| tradebox-mcp dearvn/tradebox-mcp Enables AI trading agents to trade safely through any broker MCP server by recording every tool call and reasoning in a local blackbox, while enforing configurable guardrails such as symbol whitelists, order size caps, rate limits, and dail | |
| tele-ux-ui-motion-skill-mcp dearxuan7392/tele-ux-ui-motion-skill-mcp Enables AI agents to browse, search, and read a curated library of 198 UI/UX and animation design skills across 17 categories, distilled from 10 open-source projects, with a progressive 5-step workflow for guidance. | |
| slidev-orchestrator-mcp death-joke/slidev-orchestrator-mcp Orchestrates multiple Slidev presentations by managing dev servers and proxying Slidev's MCP tools for targeted presentations. | |
| local-worker-mcp deatherick/local-worker-mcp Enables any MCP client to delegate a scoped task to a local Ollama model that runs its own tool-calling loop for file operations and web search, with an allow-listed folder security model. | |
| Firefly III MCP Server - Cloudflare Worker deathgun3344/firefly-iii-mcp Enables AI tools to interact with Firefly III personal finance manager through the MCP protocol, deployed globally on Cloudflare Workers for low latency. | |
| jianying-bridge deathknight88/jianying-bridge Compiles a compact JSON edit manifest into a new, editable JianYing Pro draft, safely creating drafts without overwriting existing projects. | |
| Agent Context Token Optimizer MCP Server deathovogod/agent-context-token-optimizer Provides owner-bound secure storage and retrieval of tool outputs via MCP tools, enabling trusted persistence for agents like Claude Code, Codex CLI, and OpenCode. | |
| AlayaCare MCP Server deathracr/alayacare-mcp Bridges the AlayaCare home care platform with AI agents, enabling natural language queries for PSW details, client info, visit schedules, and geo-based proximity analysis. | |
| wikimedia deathrashed/wikimedia Enables MCP-compatible clients to search Commons media, inspect file reuse and licensing details, and retrieve Wikipedia article extracts over local stdio. | |
| OpenAI-Compatible MCP Gateway deathwalker-47/openai-compat-mcp Local MCP server that exposes fixed tools for GPT, Claude, and Gemini while routing to any OpenAI-compatible chat completions backend with independent configuration per target. | |
| Test Generator MCP Server debabhinav1-hub/mcptestgenwithclaude Enables automatic generation of test scenarios from user stories uploaded to Claude desktop. Leverages MCP integration to streamline the test case creation process for development workflows. | |
| ansible-log-mcp debabrata-oss/ansible-log-mcp Enables Claude Desktop to trigger Ansible-driven log scans across an inventory group and retrieve combined results from target hosts. | |
| mssql-explorer-mcp debabsah/mssql-explorer-mcp A read-only MCP server for exploring on-premises, multi-instance Microsoft SQL Server estates from AI clients, with read-only enforcement and Windows authentication support. | |
| sqlproctor debabsah/sqlproctor Enables deterministic semantic verification of agent-generated SQL queries against a git-versioned contract, blocking incorrect queries and returning structured feedback for self-correction. | |
| s3-mcp-server debadatta30/s3-mcp-server A remote, OAuth2-authenticated MCP server that provides read-only S3 tools (list buckets, list objects, check public access, get bucket size) designed to run on ECS Fargate with Auth0 as the identity provider. | |
| Splunk Intelligence MCP Server debaditya-mohankudo/splunk-intelligence Enables AI agents to investigate Splunk exports or live queries using deterministic detectors and an iterative analysis loop, all running locally without data leaving the machine. | |
| Personal AI Assistant MCP debajoycs98/mcp Enables comprehensive personal task management through specialized MCP servers including email sending, PDF reading with OCR, web search, meeting scheduling, pizza ordering, and interactive question handling. Provides a unified chat interfa | |
| MCP FastAPI Multi-Agent RAG System debajyoti02-mac/fast-api-systemetic-mcp-server Enables document-grounded question answering, arithmetic calculations, live weather lookups, and persistent chat history through a ReAct agent with hybrid retrieval. | |
| mcp-sqlserver debanjan29/readonly-mssql-mcp-db Enables AI assistants to connect to Microsoft SQL Server for schema discovery, querying, stored procedures, DDL, performance diagnostics, and developer utilities with configurable security modes. | |
| grr debanjanbasu/grr-cli Google Workspace from the terminal: 401 methods across 14 Google APIs (Gmail, Calendar, Drive, Docs, Sheets, Chat, Tasks…) in one generated command tree, plus an MCP server (grr mcp) exposing the same surface as typed tools — zero-config re | |
| Tavily Web Search MCP Server debanshd/aie7-mcp-session Enables web search capabilities through the Tavily API via the Model Context Protocol. Allows users to perform web searches and retrieve information from the internet through natural language queries. | |
| Remote MCP Expense Tracker debarghanath/expenses-mcp-server Enables LLM clients to manage a financial ledger by adding, listing, and summarizing expenses via a remote MCP server using SSE transport. | |
| TradingView MCP Server debarpan2000/tradingview-mcp Connects AI assistants to TradingView Desktop via Chrome DevTools Protocol for AI-assisted chart analysis, Pine Script development, and workflow automation. | |
| DebateTalk MCP debatetalk-ai/mcp Enables AI assistants to facilitate structured multi-model debates that synthesize multiple perspectives into clear categories like ground truths and blind spots. It provides tools for running real-time debates, checking model health, and m | |
| turbosmtp debba/turbosmtp-mcp-server A simple Node.js MCP (Model Context Protocol) server for sending emails using TurboSMTP | |
| gage-mcp debenlabs/gage-sdk Enables agents to access fixed-cost loan tools over MCP and operate a wallet that signs transactions under spend limits. | |
| HomeKeep MCP Server debg-80/homekeep Enables an agent to access household and appliance data, provide manual-backed checks, prepare and execute demo technician bookings, and close cases after confirmed outcomes. | |
| BetaZero debisoft/betazero Enables coding agents to query a developer's recorded git-derived voice through MCP tools, answering why code is the way it is, asking the developer about work, and identifying who knew about a topic before making changes. | |
| DocFlow MCP Server debjit/docflow Serves documentation for Git repositories via MCP, providing tools to search docs, retrieve feature details, WIP status, and full context. Enables LLM agents to access human and LLM-optimized documentation through stdio or SSE transports. | |
| Microsoft Copilot Studio MCP Server debms123/mcpserver A server implementing the Model Context Protocol (MCP) that delivers jokes upon request, demonstrating how to connect AI models to data sources and tools within Microsoft Copilot Studio. | |
| Jokes MCP Server debms123/newmcp An MCP server that enables Microsoft Copilot Studio to fetch random jokes from multiple sources including Chuck Norris jokes, Dad jokes, and Yo Mama jokes. | |
| Anki Model Context Protocol (MCP) Server debnath-d/anki-mcp-server Enables AI assistants to directly manage Anki flashcards, decks, notetypes, tags, and media, with support for batch operations, searches, and deck exports via file-based input/output. | |
| Flameox deboer6105/flameox Enables coding agents to trace, profile, and investigate performance hotspots in application code, native code, GPU kernels, and inference stacks by coordinating local profilers, benchmark tools, trace processors, and direct capture targets | |
| MCP Jenkins deborahabdullah/mcp-jenkins Enables AI language models to interact securely with Jenkins through the Model Context Protocol, supporting job, build, queue, node, view, plugin, artifact, and Groovy script operations while maintaining data privacy and security. | |
| Pentest MCP deborahhenry6501/pentest-mcp Enables authorized security assessments by exposing tools for host discovery, web probing and fuzzing, template scanning, brute-force checks, traffic capture, and engagement reporting through configurable transports. | |
| SerpApi MCP Server deborahkarahan884/serpapi-mcp Enables searching Google, Bing, Yahoo, DuckDuckGo, YouTube, eBay, and other engines to retrieve real-time web results, weather, stock data, and more. Supports JSON or token-efficient Markdown responses and optional interactive UI tools for | |
| Cinema4D MCP Server deborahp7695/cinema4d-mcp Connects the Cinema 4D 3D modeling application to Claude, enabling prompt-driven creation and modification of scenes, objects, cameras, lights, materials, MoGraph cloners, fields, and dynamics. It also supports Python script execution, scen |
43,201–43,250 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.