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
Set up the Beacon MCP server for me so you can check MCP servers and agent skills against Beacon Intel before I install them. Beacon Intel is a free security index of the MCP servers and skills public registries list. It needs a free Beacon account; there is no API key. - Server name: beacon-managed - Transport: Streamable HTTP - URL: https://mcp.beacon.sh - Auth: OAuth (sign in through the browser when prompted) Add it the way you normally add MCP servers (your CLI command or your MCP config file), walk me through the browser sign-in, then confirm it connects and lists its Intel tools: beacon_intel_lookup, beacon_intel_get_artifact and beacon_intel_check. To finish, use beacon_intel_lookup on one MCP server I already have installed and summarize its risk for me.
Paste this into any coding agent. It adds the server with its own MCP setup.
| Name | Risk |
|---|---|
| io.github.labarilem/brainfaq-mcp labarilem/brainfaq-mcp MCP server for the BrainFuck programming language | |
| Labelixa labelixa/labelixa-mcp Thermal label MCP server: render, validate, debug and convert ZPL, EPL, TSPL and CPCL labels. | |
| Copilot Memory MCP labforgedev/copilot-memory-mcp Persistent semantic memory for AI agents using local ChromaDB vector search. No cloud required. | |
| Labs64/NetLicensing-MCP labs64/netlicensing-mcp The official NetLicensing MCP Server is a natural language interface that enables agentic applications to manage the full software licensing lifecycle in Labs64 NetLicensing 👉🏼 without writing a single API call. | |
| Revit Converter MCP labsfuture/revit-converter-remote-mcp-release Convert Revit files to XKT, IFC, or DWG and query BIM data via natural language. | |
| Fanout labstack/fanout Investigate OpenTelemetry traces, metrics, and logs, and manage personal dashboards. | |
| io.github.labtools-studio/fetchmcp labtoolsstudio/fetchmcp Drop-in fetch MCP: clean Markdown from any URL, with JS rendering and anti-bot. | |
| LoreConvo labyrinth-analytics/loreconvo Local-first persistent session memory for Claude Code and other agents. SQLite + FTS5, no cloud. | |
| Datamuse MCP lacausecrypto/datamuse-mcp MCP server for Datamuse word-finding API | |
| mcp-belgium lacausecrypto/mcp-belgium Single MCP server for Belgian public transport, statistics, open data, and geospatial services. | |
| io.github.lacausecrypto/mcp-nbb lacausecrypto/mcp-nbb MCP server for the National Bank of Belgium SDMX statistical API (221 dataflows). | |
| io.github.lacausecrypto/mcp-new-caledonia lacausecrypto/mcp-new-caledonia MCP server for New Caledonia open data (data.gouv.nc) | |
| PoetryDB MCP Server lacausecrypto/mcp-poetrydb Classic poetry search and discovery via PoetryDB. | |
| Sophon lacausecrypto/mcp-sophon Honest token economics for MCP agents. 68% tokens saved, zero-ML Rust binary. | |
| com.dethboy/vedetta lacryptorina/vedetta-mcp FREE route+korra; funnel $0.07; desk $0.01-$0.09 USDC on Base. NFA. | |
| Laddro Career laddro-app/laddro-career-mcp Tailor resumes, generate cover letters, render CVs as PDF, and browse 22+ templates. | |
| io.github.laf-rge/quickbooks-mcp laf-rge/quickbooks-mcp MCP server for QuickBooks Online API integration | |
| cascade-img laffeyp/cascade-img LLM-operable Midjourney pipeline: 21 MCP tools to compose, generate, curate with vision, and log. | |
| Laguna Pools lagunapools/laguna-pools-mcp AI sales manager for composite swimming pools — recommendations, pricing, BIM/CAD, dealers | |
| Claim by Ouroboros Apps lahutchins91/claim-mcp Approved brand claims, offers, proof, and banned phrases for AI-written marketing copy | |
| Continuity by Ouroboros Apps lahutchins91/continuity-mcp Story continuity, novel memory, and series bible for fiction writers, shared with AI assistants | |
| Deposit by Ouroboros Apps lahutchins91/deposit-mcp Freelance deposit and payment schedule for AI assistants | |
| Desk by Ouroboros Apps lahutchins91/desk-mcp Customer support answers, refund rules, and escalation limits for AI assistants | |
| Invoice by Ouroboros Apps lahutchins91/invoice-mcp Freelance invoice line items, rates, due dates, and late terms for AI assistants | |
| Milestone by Ouroboros Apps lahutchins91/milestone-mcp Freelance project milestones and acceptance criteria for AI assistants | |
| Papers by Ouroboros Apps lahutchins91/papers-mcp Research paper search with real citations and reference formatting for AI assistants | |
| Patent by Ouroboros Apps lahutchins91/patent-mcp USPTO patent search and prior art lookup. Not legal advice | |
| Rank by Ouroboros Apps lahutchins91/rank-mcp SEO rankings and traffic from Google Search Console for AI assistants, read-only | |
| Scope by Ouroboros Apps lahutchins91/scope-mcp Freelance scope of work, rates, deadlines, and change orders for AI assistants | |
| ScholarFetch laibniz/scholarfetch Multi-engine scholarly research server for search, traversal, full text, and reading lists. | |
| io.github.LakeLogic/lakelogic-mcp lakelogic/lakelogic-mcp Validate, lint, test-run and explain Open Lakehouse Contracts with LakeLogic, from any AI assistant. | |
| agentsapi-sec-filings lakesky/agentsapi-sec-filings Enables agents to retrieve SEC EDGAR 10-K, 10-Q, and 8-K filings with pay-per-call USDC micropayments on Base via x402, requiring no API key or signup. | |
| io.github.lakshgk/distill-mcp lakshgk/distill-mcp Convert PDF, DOCX, XLSX, PPTX, HTML, audio to token-efficient Markdown for any MCP client. | |
| Credence — Epistemic Guard lakshmi-chakradhar-vijayarao/credence-ai Epistemic guard for AI coding: tracks uncertain values and blocks writes until verified. | |
| Trove lalwanipalash/trove-mcp Fail-closed academic research server: search, full text, citations across open scholarly APIs. | |
| kaeru memory lamantinai/kaeru Memory for LLM agents: a local graph where the agent keeps decisions, tasks, hypotheses and reasoning between sessions, and gets a summary of what is open and overdue on every return to a project. Works with Claude Code, Codex, Cursor and o | |
| LeanGate lambdabypi/leangate Checks agent-written Python against your repo: duplicate helpers, error handling, security. | |
| io.github.lambdasec/frame-mcp lambdasec/frame-mcp MCP server for the Frame security scanner: scan, verify, fix, exploit, packs and separation logic. | |
| TestMu AI (formerly LambdaTest) lambdatest/mcp-server-guide Agentic AI quality engineering: run, debug and triage tests on real browsers and devices | |
| mcp-server-multiverse lamemind/mcp-server-multiverse A middleware server that enables multiple isolated instances of the same MCP servers to coexist independently with unique namespaces and configurations. | |
| Landed landedjobs/landed-mcp Search AI-native jobs, inspect application forms, and fetch free interview-prep resources. | |
| Open Task Relay lanekingsbery/open-task-relay-public Open Task Relay provides free, bounded public-good tasks that autonomous AI agents can discover, complete, submit, and independently verify. Its public TypeScript source runs locally with a Cloudflare Workers-compatible runtime and SQLite/D | |
| io.github.langcare/langcare-mcp-fhir langcare/langcare-mcp-fhir An MCP FHIR server written in Go for EMR systems like Epic and Cerner | |
| Langfuse Prompt Management MCP Server langfuse/mcp-server-langfuse Facilitates access and management of Langfuse prompts through the Model Context Protocol, enabling prompt discovery, retrieval, and integration within clients like Claude Desktop and Cursor. | |
| Roslyn Workbench MCP lantean-code/roslyn-workbench-mcp Bring Visual Studio-style C# fixes and refactorings to your AI agent with local Roslyn Code Actions. | |
| io.github.lanternrow/facebook-pages-mcp lanternrow/facebook-pages-mcp Facebook Pages organic analytics, post management, and insights via Meta Graph API v25.0. | |
| io.github.lanternrow/namecheap-api-mcp lanternrow/namecheap-api-mcp Namecheap API — domains, DNS, contacts, registrar lock, SSL listing, and pricing. | |
| io.github.lanternrow/tiktok-organic-mcp lanternrow/tiktok-organic-mcp TikTok organic analytics — video performance, engagement metrics, and profile insights. | |
| io.github.lanternrow/youtube-organic-mcp lanternrow/youtube-organic-mcp YouTube organic analytics — channel stats, video performance, watch time & audience insights. | |
| laogu-mcp laogu-caibao/laogu-mcp 老谷拆财报 MCP Server：21 个 A 股财经 skill 的程序化数据层（零 key、纯公开接口）。 |
10,751–10,800 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.