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 |
|---|---|
| Menta crossmint/menta MCP server that lets AI assistants buy, book and order online at real stores by delegating checkouts to a Crossmint browser agent, including answering store questions and surfacing receipts inline. Payments stay under user control, with spe | |
| HCM-LLM MCP Server crosstraffic/highway-capacity-manual-mcp A FastAPI-based server that enables AI assistants to perform Highway Capacity Manual (HCM) transportation engineering calculations and semantic searches over HCM documentation. It provides specialized tools for complete Chapter 15 two-lane | |
| unraid-mcp-server crouchingmuppet/unraid-mcp-server Enables AI assistants to manage Unraid OS via Docker, system calls, and file system access for automating array, share, and container operations. | |
| Agent Library croutoncreations/agent-library Enables agents to read and write Markdown documents, HTML pages, data files, PDFs, screenshots, and videos through a standard remote MCP server with OAuth, per-agent revocable project permissions, version history, and stable artifact links. | |
| CrowdCent MCP Server crowdcent/crowdcent-mcp Enables AI assistants to interact with CrowdCent's prediction challenges, allowing them to access challenges, download datasets, submit predictions, and monitor submissions through natural language commands. | |
| Mega Admin MCP crowdedleopard/mega-admin-mcp Enables Copilot Studio agents to run any Microsoft admin REST call as the signed-in admin across Graph, Azure, Power Platform, Dataverse, Power BI, Fabric, and Office 365, with built-in FinOps and AI tokenomics tools. It previews writes for | |
| crowdsec-local-mcp crowdsecurity/crowdsec-local-mcp Generates, validates, and deploys CrowdSec WAF rules and scenarios through natural language. | |
| thinkingdata-readonly crownjoker07/thinkingdata-mcp Local read-only MCP server for ThinkingData 5.0 that provides 10 tools for event analysis, retention, funnel, path, distribution, and SQL queries over stdio. | |
| 2D6 MCP crowterliam/2d6mcp An AI GM assistant for tabletop RPGs that provides dice rolling, rules queries, and AI-powered rulings across multiple game systems including sci-fi, fantasy, and d20. | |
| Advanced HWP MCP Server crowwan/hwp-mcp-advanced-custom Enables comprehensive control of Korean Hangul (HWP) documents with 59 features including document manipulation, text editing, formatting, table operations, PDF export, and advanced automation capabilities like template filling and document | |
| PAL MCP crowx01/hermes-mcp-server Enables AI assistants to orchestrate multiple models from different providers within a single conversation, supporting collaborative code review, planning, debugging, and implementation workflows with full context continuity. | |
| SkullRender-Agents MCP Server crozzbite/skullrender-agents Enables declarative agent manifest management and deterministic brief validation for the Presentador→Orquestador flow, with tools to list/get manifests and validate brief schemas. | |
| stickers-mcp crsel/stickers-mcp MCP server that converts PNG stickers to HEIC, uploads to Firebase Storage, and manages sticker categories via Remote Config, enabling automated sticker pack publishing workflows. | |
| btdiag crsuraj1/btdiag Enables AI agents to control Bluetooth audio devices via MCP tools, including battery status, connect/disconnect, find-my, and snoop decoding. | |
| Cordon crsvt/cordon Gives agent teams a crash-safe shared memory on FalkorDB, where writes from a team that has lost its lease are fenced instead of overwriting current state. Late or conflicting life-safety reports are kept, linked to what they contradict, an | |
| LockRe crsxmd/lockre-mcp LockRe prevents file edit collisions among multiple AI agents and allows surgical revert of each agent's changes line-by-line, without affecting others' work. | |
| Rewindex crsxmd/rewindex Auto-snapshot tool for AI agents. Reduces the risk of AI agents breaking your code by automatically saving a snapshot of every file change locally. Rewind sessions, audit code changes, and inspect diffs directly from your AI chat or the bui | |
| MCP Medium Accelerator crtdaniele/mcp-medium-accelerator A Claude Desktop MCP server that extracts and summarizes Medium articles from specified URLs, with support for Italian language summaries and local storage for future reference. | |
| OneClickLM crthehills/oneclicklm A robust MCP server for NotebookLM that provides auto-healing authentication, zero-config setup, and tools to list, query, create notebooks, and manage sources. | |
| Project Memory crtormo/project-memory An intelligent personal CRM that processes WhatsApp conversations to build a searchable knowledge base about contacts using diarization, transcription, and PII sanitization. It exposes MCP tools for semantic search, contact summaries, and r | |
| AIO MCP crtypubg/aio-mcp Unified control plane and runtime for the Model Context Protocol ecosystem, enabling plugin management, configuration, permissions, and API gateway services. | |
| Crude Code MCP Server crude-code/mcp-app An oil & gas data-analytics MCP server that enables guarded SQL queries, well valuation, and map rendering within chat apps. | |
| Flightdeck MCP Server cruglobal/flightdeck-mcp-server Enables AI clients to manage Flightdeck projects, work items, cycles, modules, and comments via the Flightdeck REST API. | |
| CruiseFeed cruisefeedio/cruisefeed-mcp Query cruise sailings, fares, price drops & ship specs | |
| freellmpool cruiz13/freellmpool Publishes an MCP server that pools 178 enabled free chat routes and 443 cataloged models behind one OpenAI-compatible endpoint, letting MCP clients and coding agents query many providers with automatic failover, latency-aware routing, and p | |
| Langfuse Prompt Management MCP Server cruiz13/mcp-server-langfuse Enables clients to list, retrieve, and compile Langfuse prompts with variable arguments, and exposes compatible tools for prompt discovery and access. | |
| Slack Browser MCP cruizba/slack-browser-mcp Enables agents to read and write Slack through an ordinary browser session cookie, covering channel and thread history, full-text search over a local archive, and approved posting. It also supports an "agent forum" channel where agents of d | |
| Crumbtrail MCP Server crumbtraildev/crumbtrail-cli Retrieves captured bug context and evidence for coding agents, enabling progressive disclosure of sessions, manifests, and window correlations to diagnose and fix issues. | |
| MCP Devcontainers crunchloop/mcp-devcontainers An MCP server that enables interaction with development containers through the devcontainers CLI, allowing users to start, run commands in, and execute arbitrary shell commands inside devcontainers. | |
| MCP Teamtailor crunchloop/mcp-teamtailor A Model Context Protocol server that enables integration with the Teamtailor API, allowing users to list, filter, and retrieve candidate information from their Teamtailor recruitment platform. | |
| mcp-ashigaru crunchtools/ashigaru An MCP server that enables autonomous code development by pulling GitHub issues, fixing them in a sandboxed environment, running tests, opening PRs, and promoting to production upon human approval. | |
| MCP GitHub CrunchTools crunchtools/mcp-github A secure MCP server for interacting with GitHub issues, pull requests, repository files, and search, supporting both github.com and GitHub Enterprise Server. | |
| mcp-metsuke-crunchtools crunchtools/mcp-metsuke Serves as a durable catalog for report definitions and gathered outputs, enabling agents to save findings with source URLs and retrieve the freshest output to compile cited reports. | |
| mcp-nagios-crunchtools crunchtools/mcp-nagios Enables secure interaction with Nagios Core for querying host and service status, acknowledging problems, adding comments, scheduling forced checks, and reading notification history. | |
| mcp-pcloud-crunchtools crunchtools/mcp-pcloud Enables secure OAuth-based access to pCloud cloud storage, letting users browse, search, read, and manage files and folders through the Model Context Protocol. | |
| MCP RHHI CrunchTools crunchtools/mcp-rhhi Enables agents to explore the Hummingbird / Red Hat Hardened Images catalog read-only through its public API — searching images, streams, variants and tags, and inspecting container config, SBOM package lists, release history and CVE exposu | |
| mcp-syslog crunchtools/mcp-syslog Enables secure search, tail, grep, and correlation of centrally collected infrastructure logs, turning blind restarts into informed remediation decisions. | |
| io.github.crunchtools/systemd crunchtools/mcp-systemd Enables full lifecycle management of systemd units over D-Bus, including status, start/stop/restart, unit file authoring, journal queries, timers, and system/session information. | |
| io.github.crunchtools/airlock crunchtools/trentina Secure MCP server for quarantined web content extraction with two-layer prompt injection defense, enabling safe fetching of URLs and reading of files via sanitized markdown output. | |
| Home Assistant MCP crunchypancake1/home-assistant-mcp Exposes a Home Assistant instance as an MCP tool set, running as a stateful agent on Cloudflare Workers, enabling clients to read entity states, call services, run scripts and automations, and send commands to phones. | |
| Joplin MCP crunchypancake1/joplin-mcp Exposes a Joplin note collection as a tool set to MCP clients, running on Cloudflare Workers. It enables semantic search over indexed notes, notebook browsing, and creating/updating/deleting notes and notebooks via the Joplin Data API. | |
| Linkwarden MCP crunchypancake1/linkwarden-mcp This MCP server connects to a Linkwarden instance, enabling semantic search, filtering, and management of bookmarks through natural language. | |
| nirog-mcp crusher-058/nirog-mcp Turns Alexa+ into a telehealth intake front door: it records symptoms described in a patient's own words, recalls earlier complaints that meant the same thing differently, flags recurrences and red-flag symptoms with triage advice, and read | |
| sagrada-mcp cruxia-labs/sagrada-mcp MCP server for tracking and verifying AI reasoning state, with signed action receipts, repo-history records, and preflight gating for tool calls. | |
| Cruxible Core cruxible-ai/cruxible Deterministic decision engine with DAG-based receipts. Build entity graphs, query with MCP, get auditable proof. | |
| whoop-ai-mcp cruz467/whoop-mcp Enables read-only access to WHOOP recovery, sleep, HRV, strain, workout, and race-performance data so assistants like Claude, Codex, and GitHub Copilot can answer personal health questions, compare trends against personal baselines, and aud | |
| Express REST API and MCP Server Framework cruz48118/express-rest-api-and-mcp-server-framework Exposes every generated Express service to LLM clients over HTTP as MCP tools (create, update, delete actions) and resources (list and get-by-id context), so AI assistants can discover and manipulate application data without raw HTTP calls. | |
| oh-my-cassette cruz48118/oh-my-cassette Enables users to edit raw video clips through natural-language chat in AI coding agents, turning footage into finished montage videos with beat-synced cuts, music matching, subtitles, transitions, and picture-in-picture. | |
| jev-browser-mcp cruz62/jev-browser Enables MCP clients to drive a real browser by stating one outcome at a time, with Typesafe System One (Jev) deciding which element, action and value to use while Playwright executes it. Exposes tools to open and settle pages, read or check | |
| autobat-v3 cruz636/autobat-v2 FastMCP server for automating AutoCAD via COM on Windows, enabling drawing creation, entity drawing, and drawing management through natural language commands. |
40,851–40,900 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.