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 |
|---|---|
| web-exposure-mcp perufitlife/web-exposure-mcp An MCP server that lets an AI agent probe a live URL and confirm whether sensitive files (e.g., .git, .env, source maps) are genuinely served by fetching and validating the content, avoiding false positives. | |
| io.github.perzianhq/mantis perzianhq/mantis The web as short, numbered text for AI agents: a lean browser interface over Playwright. | |
| io.github.petalframework/petal-components-mcp petalframework/petal-components-mcp Phoenix LiveView component schemas from petal_components, exposed to AI coding assistants. | |
| UniFi Gateway pete-builds/mcp-unifi Safe-by-default UniFi MCP: Network + Protect + Access, multi-site, dry-run, audit log. | |
| Oncofiles peter-fusek/oncofiles AI-powered medical document management for cancer patients. Google Drive, Gmail, Calendar via MCP. | |
| Semantic API peter-j-thompson/semanticapi-mcp Natural language API discovery MCP server. Search 700+ API capabilities across 163 current providers, get, exact endpoints, auth setup, and code snippets. Supports auto-discovery of new APIs. | |
| Guarded WhatsApp peter-tnc-453/guarded-whatsapp-mcp Security gate for agent-driven WhatsApp: allowlist, secret scan, rate limit, audit log. | |
| io.github.PeterAtPondo/kit-memory-demo peteratpondo/kit-demo-mcp Continuity for agents: a live memory you can read and cite right now, outliving the context window. | |
| us.thistripbtw/trips peterbartsch/thistripbtw-mcp Hand someone a complete trip as a private, editable map link. No account, no API key, no card. | |
| Parsley - Buyer Intent Signals peterjduffy/parsley-mcp Query buyer intent signals, MEDDIC qualifications, and lead scores from Parsley. | |
| Ableton for AI peterkolbe/ableton-for-ai Bridge between Ableton Live and AI. Inspect, analyze audio, and control mixing via MCP. | |
| Nynch peterod99/nynch-mcp-server Nynch, the AI CRM for consultants and fractionals: contacts, deals and relationship intelligence. | |
| MCP Light Memory peterpirog/mcp-light-memory Local-first persistent memory for coding agents and MCP clients. | |
| io.github.Peterwong666/basepilot peterwong666/basepilot 面向企业交付的飞书多维表格 MCP Server —— 让 Claude Code / Cursor 安全读写业务台账 | |
| Soluble(s) — Podcast de journalisme de solutions petitsolu/soluble-mcp Solutions journalism podcast (FR): ecology, climate, society. Search, transcripts, junior versions. | |
| MCP API Guardian petrovicistefan/mcp-api-guardian Local OpenAPI contract and breaking-change checks for AI agents. | |
| MCP Cost Optimizer petrovicistefan/mcp-cost-optimizer Local-first LLM cost analysis and model-switch savings estimates for AI agents. | |
| MCP Database Doctor petrovicistefan/mcp-database-doctor Offline PostgreSQL query, migration and EXPLAIN diagnostics for AI agents. | |
| io.github.petrovicistefan/mcp-dealfinder petrovicistefan/mcp-dealfinder Search affiliate product feeds from any network and return tracked buy links with a disclosure. | |
| MCP Dependency Doctor petrovicistefan/mcp-dependency-doctor Read-only npm dependency diagnostics for AI coding agents. | |
| MCP SEO Auditor petrovicistefan/mcp-seo-auditor Read-only static SEO audits and bounded crawling for AI agents. | |
| io.github.PetShopBros/lowdown-proxy petshopbros/lowdown-proxy Look up MCP Registry declarations, npm package status, and daily observations of MCP servers. | |
| io.github.peureka/agentlookup-mcp peureka/agentlookup-mcp Search, discover, and register AI agents in the public registry at agentlookup.dev. | |
| SkillTotal pezhik/skilltotal Deterministic security scan of MCP servers, agent skills and npm/PyPI packages. Runs locally. | |
| io.github.pfeilisolana/scry-mcp pfeilisolana/scry-mcp Keyless MCP bridge to Scry Solana wallet intel: free coverage check, catalog, x402 paid endpoints. | |
| TokenSqueezer LLM Token Compressor pgalyen1987/nodeproxy x402-gated LLM token compressor: strip filler, collapse JSON, densify prose. Paid in USDC. | |
| io.github.pgEdge/postgres-mcp pgedge/pgedge-postgres-mcp Enterprise PostgreSQL MCP server with NL queries, hybrid search (pgvector+BM25), and web UI | |
| EDGAR + Entity: US Company Research pgeneralpl/edgar-entity-mcp SEC EDGAR filings, XBRL financials, Form 4 insider trades + state business-entity registry lookups | |
| PGYER pgyer/pgyer-mcp-server Upload Android, iOS and HarmonyOS apps to PGYER and manage their apps and versions. | |
| Trendzeist – Google Trends for content ideation phalkmin/trendzeist-mcp Free Google Trends MCP: ranked breakout/rising/evergreen topics for content ideas. No API key. | |
| Pharaoh pharaoh-so/pharaoh-mcp Codebase knowledge graph — architectural awareness for AI coding agents via MCP | |
| Palinode phasespace-labs/palinode Inspectable, correctable project memory in git-versioned Markdown for AI agents. | |
| MCP DB Connect phatngoit/mcp-db MCP server for Oracle, MSSQL, PostgreSQL, MySQL, SQLite, MongoDB, and Qdrant vector search access. | |
| io.github.phdwight/pse-edge-mcp phdwight/pse-edge-mcp Philippine Stock Exchange data via PSE Edge: EOD quotes, price history, disclosures, financials. | |
| Spot AI MCP (Unofficial) phil-bryant/spot-ai-mcp Unofficial community MCP server for the Spot AI camera and video-intelligence REST API. Read-only. | |
| PhilForms philforms/philforms-mcp Find, fill and verify official Philippine government forms: BIR, SSS, PhilHealth, Pag-IBIG, CSC. | |
| Philidor DeFi Vault Risk Analytics philidor-labs/philidor-mcp Search 700+ DeFi vaults, compare risk scores, analyze protocols. No API key needed. | |
| io.github.phillipboesger/polarion-mcp phillipboesger/polarion-mcp Polarion ALM MCP server for requirements, LiveDocs, work items, traceability and test management. | |
| io.github.phillipclapham/anneal-memory phillipclapham/anneal-memory Two-layer memory for AI agents with an immune system. Zero dependencies. | |
| LocalTry AI CRM philly88r/localtry-mcp Operate and customize one tenant-isolated LocalTry CRM. ChatGPT plugin coming soon. | |
| Anno philmingdao/anno Local-first HTML review, editing, and annotation for AI coding agents. | |
| io.github.philo-kim/openharness philo-kim/openharness Lets AI coding agents discover and reference each other's recent sessions. | |
| io.github.philpof102-svg/biii philpof102-svg/biii Fail-closed safe-to-pay verdicts on Base: known-bad wallets, look-alike tokens, repeat rug funders. | |
| io.github.philpof102-svg/lawbor philpof102-svg/lawbor Reputation-gated messaging + job negotiation for Base AI agents. Descriptor-only, nothing signs. | |
| io.github.philpof102-svg/mainstreet philpof102-svg/mainstreet Reputation oracle for AI agents on Base: SAFE/CAUTION/BLOCK + 0-100 score before you pay. x402+MCP | |
| io.github.philpof102-svg/xsignal philpof102-svg/xsignal x402 pay-per-call data tools for Base agents. Flagship get_intent ABSTAINS instead of guessing. | |
| Phocinae MCP phocinae/phocinae-mcp Local Phocinae decision-engine MCP stdio server: fail-closed approval gate + classify/route/score. | |
| io.github.phoenice-labs/universal-test-framework phoenice-labs/universal-test-framework Polyglot MCP test generation with 8-section contract enforcement across Python, TS, Java, Go, C++. | |
| Alive2 phongndo/alive2-mcp Prove or refute LLVM IR transformations with Alive2, and read or create alive2.llvm.org links | |
| Carbon Voice phononx/cv-mcp-server Access your Carbon Voice conversations and voice memos—retrieving messages, conversations, voice memos, and more as well as send messages to Carbon Voice users. |
14,601–14,650 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.