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 |
|---|---|
| io.github.temurkhan13/openclaw-upgrade-orchestrator-mcp temurkhan13/openclaw-upgrade-orchestrator-mcp AI runtime upgrade safety + provider-side regression detection (snapshot diff + fingerprint). | |
| io.github.temurkhan13/silentwatch-mcp temurkhan13/silentwatch-mcp MCP server for cron silent-failure detection across crontab, systemd, and OpenClaw schedulers. | |
| Temway temway/mcp-server Visual email & layout builder that turns AI assistants into a Temway authoring studio. | |
| Tencent Lexiang MCP Server tencent-lexiang/lexiang-mcp-server Tencent Lexiang AI knowledge base MCP server for searching, managing entries, and editing docs. | |
| CloudBase MCP tencentcloudbase/cloudbase-ai-toolkit Bridges AI IDEs with Tencent CloudBase for seamless deployment, enabling users to go from AI-generated code to live applications with automatic cloud resource configuration, database setup, and intelligent debugging. | |
| Tengence GEO Agent tengence-team/tengence-geo-agent GEO/SEO content pipeline MCP: plan, write, gate-check, publish, submit, monitor AI visibility. | |
| AI Business System Advisor tenkai2018/ai-business-system-advisor-mcp Find the safest first AI workflow before investing in AI agents or automation. | |
| declaude tenkenco/declaude Rewrites Claude-English into plain English, preserving meaning, code and structure. | |
| io.github.tenlean/claude-checkpoint-mcp tenlean/claude-checkpoint-mcp MCP server that checkpoints Claude Code session context to survive crashes and token limits | |
| SWT3 AI Witness tenova-labs/swt3-ai Cryptographic AI governance and audit. 75 tools, 84 frameworks. EU AI Act, NIST, CMMC, MCP Top 10. | |
| Tenpace Review Router tenpace-app/review-router-setup Human-authenticated setup for routing GitHub pull requests into the right Slack channel. | |
| Tently tently-team/tently-mcp Tently, the AI PR reviewer for GitHub: agents check team decisions before they write code. | |
| io.github.TeodorMCP/universal-connector-mcp teodormcp/universal-connector-mcp Security-first MCP server that connects any OpenAPI, GraphQL, gRPC or SOAP API to AI agents. | |
| intelica-mcp teodorofodocrispin-cmyk/intelica-mcp Competitive intelligence for AI agents — analyze any URL or company description and get structured JSON with positioning, pain points, competitors, and unique market angles. Payments via x402 protocol ($0.05 USDC on Base mainnet), no accoun | |
| trustboost-pii-sanitizer teodorofodocrispin-cmyk/trustboost-api PII sanitization layer for autonomous AI agent pipelines. Detects and redacts emails, phone numbers, national IDs, private keys, and financial data before text reaches LLMs. Supports EN, ES (LATAM), PT (BR/PT), DE, JA. | |
| VeraData teodorofodocrispin-cmyk/veradata Verified LATAM data for AI agents: sanctions, entity, rates, KYB. Pay via x402. | |
| Tera Ads teralabsx/meta-ads-mcp Meta Ads in your AI: approval before changes, undo for pauses and budgets, profit after returns. | |
| Jira Delivery teransarathchandra/jira-mcp-server Jira Cloud delivery layer: ticket briefs, acceptance-criteria checks before the PR, QA handoff. | |
| Tereno on Base tereno-xyz/tereno-mcp Check a Base contract, transaction or web page before you act. Free pricing, paid per call in USDC. | |
| FormVault terjetyl/formvault-mcp Create and manage GDPR-compliant, EU-hosted forms from any MCP-compatible AI assistant. | |
| eyeot ERP termi24/erp-by-eyeot-software ERP français avec serveur MCP natif : plus de 1 800 actions métier auto-générées via OpenAPI. | |
| io.github.terradeed/terradeed-mcp-server terradeed/terradeed-mcp-server TerraDeed MCP server — x402 web scraping & structured extraction. Pay-per-call with USDC on Base. | |
| Terranode Geospatial API terranode-co/mcp-server-terranode Point-in-polygon, nearest feature, spatial join, and distance tools for US geospatial datasets | |
| celiums-memory terrizoaguimor/celiums-memory Cognitive memory engine for AI agents with 5,100+ knowledge modules, circadian rhythm awareness, emotional state tracking (PAD model), and hybrid semantic search. Supports persistent per-user memory, project-scoped contexts, and multi-proto | |
| TestChimp testchimp/testchimp-mcp-client QA platform for agents: coverage signals, in-repo test plans, verified tests and release governance. | |
| TestDino MCP testdino-hq/testdino-mcp Connects TestDino test management platform to AI agents, enabling users to check test runs, analyze failures, upload Playwright test results, and manage test cases through natural language commands. | |
| TestOptim testoptim-ai/testoptim-mcp Run AI QA test runs on your web app and read the bugs they find, with steps to reproduce. | |
| io.github.tesults/tesults-mcp tesults/tesults-mcp Ask your AI agent why your tests are failing. Instant analysis on failures and regressions. | |
| ACR — Agent Composition Records tethral-inc/agentregistry Interaction profile registry for AI agents. Log interactions, query behavioral lenses. | |
| LinkPilot tetracorehq/linkpilot-mcp Send a password or API key as a link that opens once. Encrypted client-side, so we cannot read it. | |
| Tetrees MCP tetreesex/tetreesagent_ex Own, grow and trade portable agent intelligence via TAIP/1 Packs and MCP. | |
| io.github.teunlao/vidin teunlao/vidin Turn a screen recording into agent-readable annotated keyframes. MCP server + CLI on ffmpeg. | |
| homeassistant-mcp tevonsb/homeassistant-mcp Access Home Assistant data and control devices (lights, switches, thermostats, etc). | |
| io.github.Texan-NXTassist/nr-mcp texan-nxtassist/nr-mcp MCP server for Node-RED — safe deploy, optimistic locking, smart search, 13 tools | |
| Bugsnag MCP Server tgeselle/bugsnag-mcp Enables interacting with Bugsnag to investigate and resolve errors via natural language. Supports browsing organizations, projects, errors, stacktraces, and exception chains. | |
| sketch/design — System Design Interview Board tghattas/sysdesign-board Hand-drawn whiteboard for system design mock interviews; your AI watches, asks and gives feedback. | |
| RunLater thachp/runlater Let agents make HTTP requests later: schedule, retry, cron, watch jobs, receive webhooks. | |
| io.github.ThaiTrevor/gold-mcp thaitrevor/gold-mcp MCP server for XAUUSD gold market data + 4-tier trading toolkit (TA, backtest, SMC, risk). | |
| gov.br APIs MCP thalisantunes/govbr-apis-mcp A catalog-driven gateway over Brazilian government APIs, loading OpenAPI specs on demand. | |
| Thalovant MCP thalovant/thalovant-mcp Connect MCP clients to Thalovant control-plane and hub runtime APIs over stdio or Streamable HTTP. | |
| LLMSlim memory thanatos9404/llmslim Long-term memory and context fitting for agents, with no LLM in the loop. Local SQLite. | |
| Subagent MCP thang1710/subagent-mcp Let Codex orchestrate external coding agents through their native harnesses. | |
| SQL Server MCP (macOS) tharanabope/sql-mcp-mac-windows SQL Server MCP with RAG capabilities for macOS (Docker SQL Server support) | |
| EnCarAPI - Korean & Chinese used cars thatmojo/encarapi-mcp Live used car listings from South Korea (Encar, KB Chachacha, K Car) and China (Dongchedi, Che168). | |
| NZ Open Banking (Akahu) thatskiff33/nz-openbank-mcp Ask about your NZ bank accounts via Akahu open finance. Read-only by default, consent per write. | |
| io.github.thatsrajan/vidlens-mcp thatsrajan/vidlens-mcp Video as a queryable local asset for AI agents — 47 tools for YouTube, social, and local media. | |
| Alexandria the-40-thieves/alexandria-mcp Search, read, and cite across 152 libraries: 11 tools, 3 prompts, and a full-text resource. | |
| Squad the-basilisk-ai/squad-mcp Decision intelligence for product teams. Turn scattered feedback into signal you can act on. | |
| io.github.hellosg/coderegistry the-code-registry/mcp-server Enterprise code intelligence for M&A, security audits, and tech debt. Hosted server with 200k free. | |
| Doxa MCP the-doxa-way/doxa-mcp-schema Christian AI for any question, in any season. Bible (BSB), grace + truth. faith.tools 5/5. |
19,351–19,400 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.