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.IvanBBaev/facebook-mcp ivanbbaev/facebook-mcp Facebook Pages MCP server for the Meta Graph API — publishing, insights, moderation, messaging | |
| io.github.IvanBBaev/servicenow-mcp-ai ivanbbaev/servicenow-mcp-ai ServiceNow MCP server — 100 tools over the full REST surface, every auth method, flows, diagrams. | |
| io.github.IvanBBaev/x-mcp-ai ivanbbaev/x-mcp Safety-first X (Twitter) API v2 MCP server: 41 typed tools across 12 packages, policy-gated. | |
| io.github.IvandeMurard/paris-compass-mcp ivandemurard/paris-compass Paris commercial premises from open data: shopfront history, street turnover, sourced figures. | |
| io.github.ivanlai/primer-mcp ivanlai/primer-mcp A Jira-lite MCP server that guides planning-first workflows for AI-assisted development. | |
| SONAR: KYB due diligence ivanolegvak/getsonar-mcp KYB checks on any company: registries, sanctions, PEP, ICIJ Offshore Leaks, adverse media. | |
| Lucius MCP ivanostanin/lucius-mcp MCP server for managing Allure TestOps tests, launches, plans, defects, and metadata. | |
| io.github.IvanRublev/keyphrases-mcp ivanrublev/keyphrases-mcp An MCP server to extract keyphrases from a text with the BERT model | |
| UNLAV Shopify CSV Catalog Check ivansky1/unlav-shopify-catalog-check-mcp Paid Shopify CSV diagnostics for duplicate SKUs, malformed variants, and import risks. | |
| MCP Server for Odoo ivnvxd/mcp-server-odoo An MCP server that enables AI assistants like Claude to interact with Odoo ERP systems through natural language, allowing users to search, create, update, and manage business data in their Odoo instance. | |
| contentful-mcp ivo-toby/contentful-mcp Update, create, delete content, content-models and assets in your Contentful Space | |
| Postgram ivo-toby/postgram Self-hosted memory for AI agents with hybrid search, knowledge graphs, tasks, and document sync. | |
| CubeLife ivy-innovation/cubelife Give your AI agent a persistent pixel-art character that reflects its state in real time. | |
| LINE WORKS AiNote (unofficial) iwaohig/lineworks-ainote-mcp Unofficial read-only access to LINE WORKS AiNote meeting notes: list, search, summaries, transcripts | |
| IWE (iwe.md) iwe-org/iwe Markdown knowledge base as agent memory. Runs against the notes directory it is started in. | |
| codebase-synapse iwiels/codebase-synapse Indexes codebase into a local knowledge graph with 40+ AI tools and codebase-guard. | |
| io.github.iworkist/btcmcp iworkist/btcmcp An MCP server that provides Bitcoin price data from Binance API | |
| tokenchit iyashjayesh/tokenchit Reads the Claude Code, Codex and OpenCode usage logs already on your machine and reports token totals, per-day and per-hour activity, a per-agent and per-model breakdown, and a year-in-review recap. It makes no network request at all — a te | |
| Money Lover iyongbudiarso/moneylover-mcp Unofficial Money Lover MCP server: read wallets, categories and transactions, opt-in writes. | |
| GraceDB izabelamaria24/gracedb-mcp LIGO/Virgo/KAGRA gravitational-wave alerts (GraceDB), open data (GWOSC) and GCN follow-up. | |
| io.github.Izyuusya/japan-data-mcp izyuusya/japan-data-mcp 日本の公的データ（統計・法人・不動産）にAIからアクセスするMCPサーバー。e-Stat統計API・法人番号Web-API・不動産情報ライブラリAPIの3API統合。全国約1,700市区町村対応。 | |
| Izzet Yildirim izzet/mcp Ask your AI agent about Izzet Yildirim's research, papers, CV, and availability. | |
| Aggregate izzy-gottz/aggregate-finance Finance MCP server for your banks, cards, books and payroll. Records money, never moves it. | |
| GuildControl MCP j-256/guildcontrol Safety-first MCP server for Discord with privacy-safe reads, audits, and reviewed administration | |
| Clip Studio MCP j-acks0n/clipstudio-mcp Hosted MCP for Clip Studio public products — same plan as the website. | |
| Agent Workpad j-fidel/agentworkpad Low-context public task coordination for software agents. | |
| io.github.J-MaFf/s2-netbox-mcp j-maff/s2-netbox-mcp MCP server for LenelS2 S2 NetBox access control via the NBAPI. Read-only by default. | |
| io.github.j-sulliman/hopgraph j-sulliman/hopgraph-mcp Verify ANZ businesses against government registers. Surfaces cross-jurisdictional findings. | |
| Code Lens j0hanz/code-lens Gemini-powered MCP server for code analysis. | |
| Cortex MCP — Multi-Level Reasoning Server j0hanz/cortex-mcp Multi-level reasoning MCP server with configurable depth levels | |
| Fetch URL MCP Server j0hanz/fetch-url-mcp An MCP server that fetches web pages and converts them to clean, readable Markdown. | |
| Filesystem MCP j0hanz/filesystem-mcp Filesystem MCP server for AI assistants. | |
| dev.mcphost/mcphost j0yen/mcphost Hosted MCP runtime where your agent publishes its own tools by tool call and keeps working. | |
| Agent jobs at jeremydevos.fr j2vos/agent-jobs Apply as an autonomous agent: pick a role, prove work, pass a test, get missions. | |
| mcp-server-sql-analyzer j4c0bs/mcp-server-sql-analyzer Provides SQL analysis, linting, and dialect conversion using SQLGlot, enabling validation, transpilation, and extraction of table/column references. | |
| Recall j4ckxyz/recall Private, encrypted memory about you, shared by all your AI agents. Self-hosted; runs on a Pi. | |
| slim-sheet j4flmao/slim-sheet Spreadsheet MCP for any agent: reads xlsx/xls/ods/csv, SQL, cleaning, formulas, safe edits | |
| dep-rank j7an/dep-rank Rank a GitHub repo's dependents by stars or trust heuristic, and search their code | |
| io.github.j7an/nexus-mcp j7an/nexus-mcp Delegate tasks to coding agents (Claude, Codex, Antigravity) from any MCP client | |
| AWS Payment Cryptography j8k3/aws-payment-cryptography-mcp AWS Payment Cryptography via MCP — keys, PIN/MAC/CVV/ARQC, PCI guards, HSM migration analysis. | |
| MCPVetter jaablon/mcpvetter Audit your MCP servers for poisoned tools and leaked secrets, and check AI-generated code for flaws. | |
| ProposalCraft jabbawocky/proposalcraft An MCP server for freelancers and agencies that drafts client proposals and business emails — quotes, invoices, follow-ups, scope changes, and more — in your own voice, running locally with no API key or cloud. | |
| StatusCraft jabbawocky/statuscraft Live operational status for 2,400+ major software services — AWS, GitHub, Stripe, OpenAI, Cloudflare, and more — pulled from each provider's official status page and returned as a normalised up / degraded / down result for any service you a | |
| WWDC MCP jabbertones-cloud/wwdc-mcp-server Apple developer intelligence for agents: WWDC26, docs, HIG, Swift, App Review, and app audits. | |
| Signathing e-signature jacejb/signathing-mcp Send PDFs for e-signature from AI agents, with a public hash-chained evidence log anyone can verify | |
| Polish Open Data (unofficial) jaceksmi/polishopendata Polish registers: KRS, VAT, bank checks, parcels, geocoding, property prices (RCN), optional REGON. | |
| VibeLawyer jack-mi/vibelawyer Local MCP for Chinese criminal dossier review; Word notes + Excel catalogs stay on-device. | |
| Moxie Docs jackalope-dev/moxie-docs-mcp Living docs and MCP context for GitHub repos — conventions, gaps, and source-cited pages on merge. | |
| SecureNote.link MCP Server jackalterman/securenote-link-mcp-server Enables AI agents to create end-to-end encrypted, self-destructing notes that can be securely shared via a one-click link, ensuring secrets are never stored in plain text in chat history. | |
| io.github.jackdark425/aigroup-mdtoword-mcp jackdark425/aigroup-mdtoword-mcp 本地 Markdown 到 Word 文档转换工具，支持最新 MCP 协议特性、完整的页眉页脚页码功能、增强的表格功能、数据导入和数学公式支持，修复本地相对路径图片嵌入问题 |
9,451–9,500 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.