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 |
|---|---|
| Valca pranlabs/valca Scans code, IaC and AI-agent config for security problems. Read-only — nothing can be edited. | |
| io.github.prasadabhishek/photographi-mcp prasadabhishek/photographi-mcp Visual Intelligence Command Center: A Local Computer Vision Engine for Photo Libraries | |
| io.github.PrashantBtkl/spresh-mcp prashantbtkl/spresh-mcp Search Facebook ads, decode competitor creative strategy, and track brand ad history. | |
| io.github.prashantsinghmangat/tracebug prashantsinghmangat/tracebug-ai AI agents read TraceBug bug reports (console, network, replay, repro timeline) from local disk. | |
| Altivo Jets prateek7779-maker/altivo-mcp Live private jet empty legs, charter estimates in 12 countries and quote requests. | |
| io.github.prateekg7/context-bridge prateekg7/context-bridge Context portability MCP server for compressing, formatting, and resuming AI conversation handoffs. | |
| Icon MCP pratham-jain33/icon-mcp Lucide icon sets for AI: search 2000+ icons, style them, batch-export SVG. Offline, no key. | |
| Security MCP pratham-jain33/security-mcp Zero-key security toolkit: grade sites A+ to F, check CVE exploits, plain-English attack defenses | |
| io.github.pratikgh0se/instagram-mcp pratikgh0se/instagram-mcp Instagram MCP for creators: publish, schedule, comments, DMs and insights via Meta's official API. | |
| io.github.pratikgh0se/youtube-mcp pratikgh0se/youtube-mcp Search YouTube, manage your channel and read analytics; every change needs your approval. | |
| MacOS Resource Monitor MCP Server pratyay/mac-monitor-mcp Identifies resource-intensive processes on macOS across CPU, memory, and network usage, with tools for detailed process filtering and system overview. | |
| io.github.praveen-ilangovan/pensieve praveen-ilangovan/pensieve Manually-triggered, self-organising personal memory for AI agents; SQLite, no vector DB. | |
| FetchV2 praveenc/fetchv2-mcp-server Fetch and extract web pages, discover links, and read llms.txt documentation indexes. | |
| io.github.praveenc/llmstxt-doc-search praveenc/llmstxt-doc-search BM25 search over llms.txt doc indexes (Strands, Kiro, AWS); sources addable at runtime. | |
| io.github.praveenc/mcp-docs-server praveenc/mcp-docs-server MCP server for searching MCP protocol documentation | |
| reMarkable MCP Server (Read/Write) praveensehgal/remarkable-mcp Read, write, and manage your reMarkable tablet — browse, upload, create folders, move, delete, OCR | |
| ShopTrueProfit Fee & Profit pravinrajv/shoptrueprofit-fee-mcp Etsy, eBay and Amazon FBA/FBM seller fees, profit, margin and target price, with sources. | |
| Solitaire for Agents prdicta/solitaire-for-agents Identity infrastructure for AI agents. Evolving persona, session continuity, self-tuning retrieval. | |
| Précis Finance MCP precis-finance/precis-finance-mcp Public read-only Précis Finance MCP demo with synthetic data; no account or credentials required. | |
| Fantasy Football MCP — Draft, Start/Sit, Waivers predictionmarketspicks/fantasy-draft-mcp Fantasy football for any AI agent: draft board, start/sit, waivers, your Sleeper league. Free. | |
| io.github.pree-dew/mcp-bookmark pree-dew/mcp-bookmark MCP Server for adding bookmarks in openai RAG | |
| io.github.preedew17/mcp-bookmark preedew17/mcp-bookmark An MCP server that provides [describe what your server does] | |
| preflight preflight-dev/preflight An MCP server for Claude Code that catches vague prompts, applies triage and correction pattern learning, and provides semantic search, cross-service contracts, and scorecards to reduce wasted tokens. | |
| Preloop preloop/preloop Open-source AI agent control plane and software factory: govern every tool and model call. | |
| BookMCP prem5123/bookmcp Cited book knowledge for agents working on system design and implementation. | |
| PremAgentic premagentic/premagentic On-premises knowledge retrieval, with the rules you set enforced before anything is retrieved. | |
| CogSession premanand8800/cogsession Session memory for AI coding agents: records decisions and dead ends, flags what went stale. | |
| io.github.prembobby39-gif/uimax-mcp prembobby39-gif/uimax-mcp Frontend expert for Claude Code. Screenshots, Lighthouse, axe-core, code analysis, auto-fix. | |
| PrePublish MCP server prepublish/prepublish-mcp Enables YouTube script QA before recording by auditing drafts for attention risk, authenticity, policy compliance, and runtime, with actionable rewrites. | |
| Presend MCP Server presendapp/presend-source Before an AI agent installs an npm/PyPI package: typosquat, vulnerability and existence checks. | |
| io.github.presidio-v/presidio-hardened-ikigov-assess presidio-v/presidio-hardened-ikigov-assess IKI-Gov AI governance assessment: score AI use cases, check quality gates G0-G5, map to EU AI Act. | |
| io.github.presidio-v/presidio-hardened-x402-mcp presidio-v/presidio-hardened-x402-mcp Pre-payment safety gate for x402 agents: PII screening, spend policy, replay checks before signing. | |
| Pressa - LaTeX to PDF pressa-dev/mcp Compile LaTeX to PDF without installing TeX Live. No API key needed to start. | |
| PressBridge pressbridgesupport/pressbridge Safe, audited Claude access to WordPress sites: secrets hidden, backups, undo, WP-CLI allow-list. | |
| com.presscart/presscart presscart/presscart-mcp Browse 1,700+ publications and manage Presscart media placement campaigns, orders, and articles. | |
| PressGEO pressgeo/pressgeo-mcp Public local AI visibility data, owner-confirmed business factsheets, and newsrooms. | |
| pREST prest/prest-mcp-adapter Stdio MCP adapter bridging AI clients to pREST’s HTTP /_mcp endpoint for PostgreSQL APIs. | |
| Cookie Free Analytics prestonscreekcapital/cookiefreeanalytics-mcp See your website visitors without a cookie banner. 5 MCP tools free on Hobby, 13 on paid. | |
| PriceTrack pricetrack-dev/pricetrack-mcp Live SaaS pricing: current plans, verified price changes, and comparisons for 33,000+ products. | |
| io.github.pricewatcha/pricewatcha pricewatcha/pricewatcha-api Track prices & price history on any online shop, with alerts and an API | |
| debim prida-takon/debim Declarative BIM and Building-as-Code engine for AI agents: model buildings in YAML, compute deterministic QTO and cost estimations, compile to IFC4,
and view interactive 3D WebGL models. | |
| ai.primateintelligence/mcp primate-intelligence/primate-intelligence-mcp Video scene understanding for AI agents via the Primate Vision API. | |
| io.github.primeline-ai/kairn primeline-ai/kairn Local-first knowledge engine for AI agents: memory, graph, and recall over MCP. | |
| io.github.patricktobias86/dynamic-telegram-bot-api-mcp primeupyourlife/dynamic-telegram-bot-api-mcp A dynamic, self-refreshing MCP gateway for the complete Telegram Bot API | |
| PrintFriendly printfriendly/printfriendly-mcp Read clean web pages and create PDF, Word and Markdown documents with a PrintFriendly API key. | |
| io.github.printmoneylab/x402watch printmoneylab/x402watch Wash-filtered intelligence for x402: categories, services, wash analysis, trends. | |
| io.github.printplan3d/ritn3d-mcp printplan3d/ritn3d-mcp Tools for floor plan validation, GLB checks, and 3D-print unit math — Ritn3D companion. | |
| io.github.PrintrFi/printr printrfi/printr-mcp Let AI agents create, discover, and track tokens across chains via Printr. | |
| PrintYourDuck Quote printyourduck/printyourduck-mcp Find and submit local 3D print files for manual PrintYourDuck quote review. | |
| io.github.prismatic-io/prism-mcp prismatic-io/prism-mcp MCP server that wraps Prismatic's Prism CLI tool |
16,651–16,700 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.