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 |
|---|---|
| Meetbot poolside-ventures/meetbot-mcp Meet.bot is AI-native scheduling for people and agents. Check real calendar availability and book meetings on Google and Microsoft calendars through scheduling pages — and pay per meeting booked, not per user or seat. Actions: Book Meeting, | |
| io.github.pooriaarab/aigentify pooriaarab/aigentify Audit and generate agent-native product surfaces | |
| io.github.pooriaarab/vibedate pooriaarab/vibedating Dating by tokens, matched by usage league across agentic CLIs. Local-first. | |
| io.github.pooriaarab/vibedonate pooriaarab/vibedonate BitTorrent-style mesh for AI inference across agentic CLIs. Local-first. | |
| io.github.pooriaarab/vibelive pooriaarab/vibelive Multiplayer for agentic coding terminals: live cursors, presence, chat. | |
| io.github.pooriaarab/vibeshare-live pooriaarab/vibeshare Share a live agent coding session by URL. Spectate or invite in. | |
| LeBonFoin pop24/lebonfoin-mcp First MCP for the European hemp & CBD market: real French CBD catalogue, producers, FR/EN wiki | |
| Popcraft popcraft-ai/popcraft-mcp AI video, images, music & SFX: Seedance 2.5, Veo 3.1, Kling 3.0, Nano Banana Pro, 20+ models. | |
| PopNow API popnow-ai/popnow-api-mcp Developer MCP for PopNow: run any AI image, video and audio model with an API key, billed in USD. | |
| PopNow popnow-ai/popnow-mcp AI image, video, music and speech generation: text-to-video, image-to-video, effects and upscaling. | |
| Portainer MCP portainer/portainer-mcp Official Portainer MCP server | |
| io.github.Portaltocoding/second-brain-mcp portaltocoding/second-brain-mcp Second brain en Obsidian: notas, conceptos como nodos, resurfacing y salud del grafo. En castellano. | |
| 🐴 Gulltoppr portdeveloper/gulltoppr Resolve any EVM contract ABI (even unverified, via decompilation), read, simulate, prepare txs. | |
| POS.DO MCP Server posdo-io/mcp-server Discover 356K+ restaurants in 20 countries: search, reviews, cultural context, time-based offers. | |
| PT Application Inspector MCP posidev-community/ptai-mcp Standalone launcher and agent integration for the PT Application Inspector MCP proxy. | |
| PositionGuard positionguard/positionguard-mcp Ask who in your groups is at an area like home or school. Members opt in. Never coordinates. | |
| PostalDataPI MCP Server postaldatapi/postaldatapi-mcp Global postal code lookups, validation, and city search for 240+ countries with timezone, admin region, and elevation metadata. Sub-10ms responses at $0.000028/query with 1,000 free queries on signup. | |
| Postbase postbasehq/mcp Schedule social posts, threads and video to X, LinkedIn, Bluesky, Mastodon and YouTube from your AI. | |
| postcardbot-mcp-server postcardbot/mcp-server Send real physical postcards worldwide via AI agents. Supports single and bulk send (up to 500 recipients), balance checking, delivery tracking, and volume pricing from $0.72/card. | |
| io.github.Postcept/mcp postcept/mcp Verify agent actions against the system of record and get signed completion receipts. | |
| PostLake postlake/postlake-mcp Post, schedule, reply and measure across X, LinkedIn, Instagram, TikTok, YouTube, Threads, Bluesky | |
| Postproxy postproxy/postproxy-mcp Publish, schedule, and manage social media posts across major platforms via the Postproxy API. | |
| PostPulse postpulse/mcp-server-postpulse Social media scheduler for Instagram, Facebook, YouTube, TikTok, LinkedIn, X, Bluesky, and Telegram. | |
| io.github.postraid/mcp-server postraid/mcp-server MCP connector for Postraid brands, saved social content and editable carousel drafts for review. | |
| Potarix Enricher potarix/potarix-mcp Find company websites and verified business emails through the Potarix Enricher API. | |
| Weasley DeepMind potatohoney-p/weasley-deepmind Secure, fragment-based long-term memory for MCP-compatible AI agents. | |
| Postgres (read-only transactions) poudel0/postgres-mcp-safe Drop-in replacement for @modelcontextprotocol/server-postgres that is actually read-only. | |
| bstorms.ai — Free Execution Playbooks + Agent Brainstorming pouria3/bstorms-skill Free execution-focused playbooks. Brainstorm with other agents. Tip if helpful. | |
| llmledger pouriaetab/llmledger Which AI model to use and what it costs: LiteLLM's price catalogue with every price change since 2023 and Arena ratings by task. Tools to find and compare models, estimate a job's cost and time, show price history and pick local or cloud; n | |
| mcp-my-site pournasserian/mcp-my-site Search and fetch tools for one website, served from an index you build with the mcpmysite crawler. | |
| io.github.pouyahasanamreji/continuum pouyahasanamreji/continuum Shared memory + orchestration for your coding agents. Local-first MCP, vector RAG. | |
| SuzieQ MCP Server povedaaqui/suzieq-mcp This project provides a Model Context Protocol (MCP) server that allows language models and other MCP clients to interact with a SuzieQ network observability instance via its REST API. | |
| io.github.powergridiq/pgiq-mcp powergridiq/pgiq-mcp Power-market ratings, delivered cost, claims and gaps for siting a large electricity load. | |
| Apier powerlaunch/apier-mcp Machine-verifiable Norwegian company authority: status, roles and coded signing authority. | |
| MindThread ppcvote/mindthread-mcp Threads scheduler for AI agents: write, schedule and publish posts, review replies, read insights. | |
| UltraProbe ppcvote/misp-mcp-server MISP (Malware Information Sharing Platform) MCP server with built-in prompt injection defense via prompt-defense-audit | |
| ppl - Personal CRM for AI Agents ppl-crm/ppl ppl: the personal CRM for AI agents. Structured relationship memory over hosted MCP. | |
| io.github.ppop123/knowuswell-mcp ppop123/knowuswell-mcp Host the KnowUsWell friendship quiz: 16 behaviour questions, four-letter roles, 16 pair types. | |
| Aviationstack MCP Server pradumnasaraf/aviationstack-mcp An MCP server using the AviationStack API to fetch real-time flight data, including airline flights, airport schedules, future flights and aircraft types. | |
| mcp-server-webcrawl pragmar/mcp-server-webcrawl Bridge the gap between your web crawl and AI language models. With mcp-server-webcrawl, your AI client filters and analyzes web content under your direction or autonomously, extracting insights from your web content.
Supports WARC, wget, I | |
| io.github.pragneshbagary/memex pragneshbagary/memex Persistent session memory for Claude Code. Local SQLite, no LLMs, no network. | |
| Agent Interop Runtime praket7/agent-interop-runtime Coordinate coding agents through a local MCP server while keeping accounts and workspaces separate. | |
| LinkedIn MCP Server prakharagarwal-dev/linkedin-mcp-server Find LinkedIn jobs and people, research companies, manage network, posts, and messages with MCP. | |
| Databricks MCP Server pramodbhatofficial/databricks-mcp-server 263 tools for Databricks: Unity Catalog, SQL, Compute, Jobs, Serving, and more. | |
| io.github.PramodDutta/browserbash pramoddutta/browserbash Plain-English browser tests for AI agents: real Chrome, deterministic verdicts. Free, no API keys. | |
| MQ-Sentinel pramodreddyboddu/mq-sentinel Read-only IBM MQ diagnostics for AI agents. Cited root cause, never destructive. | |
| sf-intelligence — Salesforce org intelligence for AI agents pranavnagrecha/salesforce-intelligence Offline, read-only MCP knowledge base for one Salesforce org's metadata, deps & impact. | |
| Garmin Workouts MCP pranciskus/garmin-workouts-mcp Manage Garmin Connect workouts, including strength workouts with mapped exercises. | |
| NewsMCP — World news for AI agents pranciskus/newsmcp Real-time news events, clustered by AI from hundreds of sources, classified by topic and geography, ranked by importance. | |
| io.github.praneethravuri/pitstop praneethravuri/pitstop F1 MCP server: live timing, telemetry, standings, news, and a queryable 1950-present database. |
16,601–16,650 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.