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 |
|---|---|
| jev-browser-use aurorapixel/jev-browser-use Enables AI agents to control a persistent Chrome browser through a local daemon, with Jev performing routine actions and the host agent handling reasoning, text, and verification. | |
| human-in-the-loop-mcp-security-workflow aurorashie/human-in-the-loop-mcp-security-workflow Enables authorized web/API security analysis as a stateful, multi-stage workflow with persistent session state, human-controlled validation, candidate versus confirmed finding tracking, and stop conditions. | |
| organon-create-image aurynsinclair/organon-create-image MCP server for generating images using Gemini, supporting multiple aspect ratios and both AI Studio and Vertex AI backends. | |
| web-search-cli ausertdream/bing-search-cli Enables web search using Bing and DuckDuckGo combined, and fetching readable content from web pages, with no API key required. | |
| tg-mcp-tools ausievich/tg-mcp-tools A local MCP server for Cursor and Claude Desktop that reads Telegram subscriptions over MTProto and exposes channel posts for digests and natural-language queries. | |
| Chaos Mesh MCP Server ausium/chaosmesh-mcp Enables chaos engineering on Kubernetes clusters by providing tools to inject faults like network delays, pod kills, and HTTP delays, along with cluster inspection and chaos lifecycle management. | |
| elevenlabs-mcp-experiments auskinimmanuel/elevenlabs-mcp-experiments Enables querying ElevenLabs workspace data, including listing agents and retrieving evaluation runs, through Claude Desktop or any MCP client. | |
| servicenow-mcp ausper-tech/servicenow-mcp A read-only MCP server that enables AI assistants to query ServiceNow instances—incidents, changes, users, CMDB—with malformed query linting and injection protection. | |
| Copilot Memory MCP auspham/copilot-memory-mcp Provides persistent memory for MCP-compatible agents (like Copilot CLI) to save and recall knowledge across sessions, plus long-running monitoring tools. | |
| x402-seller-check-mcp ausrine-labs/x402-seller-check-mcp An MCP server an agent asks before paying an x402 seller: real and repeat customers, the biggest payer's share and the cost to fake the numbers, from public Base chain data (Infoharmoni Atlas). Read-only, never pays. | |
| roomba-mcp auss/roomba-mcp Enables control and observation of a Roomba Combo j9+ through MCP, including mission commands, live status, settings, schedules, maps, history, and consumables over local LSS with cloud fallback. | |
| mcp-highcharts austenstone/mcp-highcharts Enables AI agents to render interactive Highcharts visualizations directly within VS Code chat conversations. It supports over 17 chart types with GitHub Primer styling and advanced features like drilldown and WebGL rendering. | |
| mcp-primer austenstone/mcp-primer An MCP server that enables AI models to render GitHub's Primer React components directly within chat interfaces using a JSON component tree. It provides tools to list available components and display interactive UI elements with full GitHub | |
| ParkAlert MCP austin5374/parkalert-mcp Provides on-demand Disney ride status and standby wait times for supported parks, resolving park and ride names by alias or partial match. | |
| mcp-wiki-server austinabhari/mcp-wiki Enables MCP-compatible clients to search and read local markdown documentation, allowing agents to retrieve relevant doc snippets or full files by path. | |
| Nostr MCP Server austinkelsay/nostr-mcp-server A Model Context Protocol server that enables LLMs like Claude to interact with the Nostr social network, allowing for fetching user profiles, text notes, and zap payment information. | |
| duffel-recovery austinlai22/trip-recovery-agent Enables an AI agent to investigate disrupted flight bookings, price every recovery option with transparent math, and execute rebook/cancel actions only after explicit human approval, using Duffel test mode. | |
| ghl-mcp austinmander/ghl-mcp MCP server for GoHighLevel API v2 that provides 50+ tools for CRM, billing, marketing, and operations workflows, enabling natural language interaction with contacts, opportunities, conversations, and more. | |
| Godot Sentinel MCP austinmander/godot-sentinel-mcp Enables AI assistants to interact with Godot game projects through real-time error detection, automated testing, code analysis, and safe git-based patching. Provides comprehensive project context and development workflow automation for Godo | |
| Things MCP Server austinmoody/things-mcp A Model Context Protocol server that enables AI assistants to interact with the Mac application 'Things' for task management operations through its URL scheme. | |
| BrandMan MCP Server austinnchristensen/brandman Exposes a governed brand brain to any MCP-compatible agent over stdio or an OAuth 2.1-protected Streamable HTTP endpoint, letting agents read brand context (mission, voice, guidelines, personas, policy) and create or edit drafts, campaigns, | |
| blvd-mcp austinntowns/blvd-mcp An MCP server for Boulevard salon and spa operations that monitors shift utilization and manages calendar blocks. It enables users to interact with staff, appointments, and services through natural language via the Boulevard API. | |
| vinance-recipes austinnui/vinance-recipes-skills MCP server providing access to a catalog of reusable React/Next.js component recipes (animations, charts, UI components) with usage examples, props documentation, and architecture notes, enabling AI assistants to generate production-ready c | |
| infomaniak-mcp austinpnguyen/infomaniak-mcp Enables managing Infomaniak kSuite contacts, calendars, and reminders over CalDAV and CardDAV through the Model Context Protocol, with no third-party dependencies. | |
| claude-mcp-tunnel austinryan/claude-mcp-tunnel MCP server that detects project frameworks (25+), starts dev
servers, and creates public Cloudflare tunnels from a single tool call. Text
Claude via Dispatch "start my project and give me a link" and get back an
HTTPS URL you can open on yo | |
| eth-mcp austintgriffith/eth-mcp MCP server that enables AI agents to build and deploy Ethereum applications using Scaffold-ETH. | |
| csibridge-mcp austinulfers/csibridge-mcp Enables an AI assistant to drive a running CSiBridge session by calling its full COM API — building and editing models, reading signatures and enums, running analyses, and reading or editing database tables of definitions and results. Acces | |
| mcp2ws austinwise/mcp2ws Exposes SOAP-based web services as MCP servers by parsing WSDL files. Enables AI assistants to interact with legacy SOAP/WS-\* web services through the Model Context Protocol. | |
| MCP SSH Server austinzq/mcpssh Enables Claude Code to control remote servers via SSH for automated deployment, testing, and operations, including command execution and file transfer. | |
| webmcp authbits/webmcp MCP server for web search and content extraction using DuckDuckGo or SearXNG, with Playwright-based fetching and LLM-powered data extraction. | |
| authensor-mcp-server authensor/authensor Policy enforcement gateway for MCP tool calls, evaluating every tool invocation against declarative YAML policies (allow/deny/escalate-to-human), generating cryptographic hash-chained audit receipts, and including built-in content safety sc | |
| zotero-kb authentic3096/zotero-kb Enables MCP-compatible AI clients to search a local Zotero library using hybrid keyword and semantic retrieval, read specific pages and figure/table captions, and feed back experience so verified references rank higher over time. | |
| Local Machine MCP Server authmeonline/local-machine-mcp Turns your local machine into an MCP server with a GUI, allowing agents to execute file operations, run commands (including admin), manage background processes, and query databases, with optional ngrok exposure. | |
| Authn8 MCP Server authn8/mcp-server Access your team's 2FA codes from AI agents without sharing secrets. List accounts, generate TOTP codes, and maintain full audit trails. Built for DevOps, CI/CD pipelines, and automated workflows that need to authenticate to protected servi | |
| Cloudflare Playwright MCP authorityandbrand/playwright-mcp-example Enables AI assistants to perform web automation tasks such as navigation, typing, clicking, and taking screenshots using Playwright in Cloudflare Workers. | |
| AuthorityPrompt MCP Server authorityprompt/gemini-authorityprompt-mcp Enables Gemini to read verified company facts, sources, provenance, and confidence from AuthorityPrompt for any published company domain. | |
| Find Flights MCP Server authrain-cloud-abdullahformuli/flights-mcp Enables users to search and retrieve live flight information through the Duffel API, supporting one-way, round-trip, and multi-city itineraries with flexible parameters such as dates, cabin class, passenger counts, and connection limits. It | |
| gsc-mcp authrain-cloud-abdullahformuli/gsc-mcp Enables MCP clients to list accessible Search Console properties and query search-analytics data—clicks, impressions, CTR, and position—over date ranges grouped by chosen dimensions, authenticating read-only as the user's own Google account | |
| Watch Skill authrain-cloud-abdullahformuli/watch-skill Gives any agent eyes and ears by indexing video, audio, and screen activity into searchable, timestamped frames, transcripts, and OCR text that answers can cite. It also evaluates frozen verification contracts over file digests, JSON values | |
| Freepik MCP authsoftware-development/freepik-mcp Enables AI assistants to search, download, and generate visual content using Freepik APIs, including icon search, image generation, and resource management. | |
| kitupiikki-mcp autio/kitupiikki-mcp Enables AI agents to read local Kitsas bookkeeping files and prepare draft vouchers for human review and posting. | |
| market-research autkucakan/market-researcher Enables AI agents to conduct local, auditable opportunity discovery by collecting public discussions, tracing claims to exact quotes and source provenance, testing claims with counterevidence, and exporting deterministic evidence packs. | |
| strudel-mcp auto-duan/strudel-mcp Provides Strudel reference documentation as MCP tools for AI coding assistants, enabling function lookup, search, and syntax reference. | |
| mcp-polska auto-mate-pl/mcp-polska Gives Claude direct, keyless access to Polish public registries: it validates NIP checksums, checks a company's VAT status and bank account against the VAT whitelist, pulls KRS court-registry extracts, and fetches the correct NBP exchange r | |
| auto-skill-connector auto-skill/auto-skill-connector Enables Claude to search and install skills from a database of ~200k scraped Claude skills, MCP servers, and plugins. | |
| Junction41 MCP Server autobb888/j41-sovagent-mcp-server MCP server for the Junction41 platform, providing 125 tools for agent lifecycle, jobs, workspace, payments, bounties, and more, enabling LLMs to interact with Junction41. | |
| Project-scoped MCP autobelay/claude-project-scoped-mcp Installs once in Claude Code and automatically discovers the nearest project's mcp.json, launching that checkout's declared MCP servers and forwarding their tools, resources, and prompts through a single connection. Each session keeps its o | |
| Codex Project-scoped MCP autobelay/codex-project-scoped-mcp Enables local Codex sessions to discover the nearest project mcp.json and expose that project’s declared MCP servers and tools through a session-local bridge, without global configuration copying or launch wrappers. | |
| APS MCP Auth Examples autodesk-platform-services/aps-mcp-auth-examples Reference MCP servers that integrate with Autodesk Platform Services, demonstrating various authentication combinations and exposing tools to list projects and folder contents via the Data Management API. | |
| APS MCP Auth0 Example autodesk-platform-services/aps-mcp-auth0-example Example MCP server for Autodesk Platform Services that demonstrates proper OAuth authorization with Auth0 as the first layer and APS 3-legged OAuth as the second layer. Enables querying APS projects and issues through natural language after |
31,751–31,800 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.