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.Opafex/mcp-approval-queue opafex/opafex-mcps Human approval gate for AI agents: risk-scored requests that only a person can approve | |
| io.github.Opafex/mcp-enrichment opafex/opafex-mcps Multi-source entity enrichment: company data, contacts, email verification, and phone validation | |
| io.github.Opafex/mcp-file-processor opafex/opafex-mcps Text extraction, keyword extraction, language detection, and chunking for RAG | |
| io.github.Opafex/mcp-web-research opafex/opafex-mcps Web search (Brave) and SSRF-safe page fetching, extraction and comparison for agents | |
| io.github.opcastil11/mcp-prowl opcastil11/agentdir Discover, evaluate, and compare SaaS APIs. Agent-verified scores and metrics. | |
| Apuchat opcastil11/apuchat-cli Real-time chat for AI agents. Claude Code, Cursor, Cline and Codex join channels over MCP. | |
| RogerRat opcastil11/rogerrat Real-time chat hub for AI agents — Claude Code, Cursor, Cline, Codex over MCP or REST. | |
| io.github.Open-Cosmic-Software/nyxmix open-cosmic-software/nyxmix Agent-first multitrack audio editor: edit sessions live with a human watching. | |
| Mizuki open-covenant/covenant Fixed-price maintenance for public GitHub issues, paid in USDC on Solana. | |
| io.github.open-deltat/deltat open-deltat/tap Give an agent a calendar it can book without double-booking: find, hold, then commit atomically. | |
| Leash open-leash/leash-plugin Hosted remote MCP for protected account access, permissions, activity history and supported undo. | |
| OpenSysML MCP server open-mbee/opensysml SysML v2 and KerML for coding agents: workspace diagnostics and edits, execution, REPL sessions. | |
| OpenMetadata open-metadata/openmetadata Official OpenMetadata MCP: 21 read and write tools for search, lineage, data quality, governance. | |
| Oliver's mTOR Atlas open-mtor-atlas/atlas Evidence-labelled mTOR research: studies, entities, pathway claims, contradictions, open questions. | |
| SalesBlink Cold Email open-salesblink/skill Cold email sequences, leads, templates, senders, inbox, and analytics via the SalesBlink API. | |
| OpenAgenda openagenda/oa-public Search, analyze and manage events on OpenAgenda. | |
| OpenAthlete openathleteorg/openathlete Endurance training: activities, load, zones, and workouts sent to Garmin, COROS and Suunto watches | |
| OpenDeviceDB opendevicedb/opendevicedb Check 21,000+ devices with open firmware or protocols before reverse engineering one. | |
| io.github.openenterprise-info/oe-mcp openenterprise-info/open-enterprise-ai-mcp-server Connect Claude Code, Cursor & Windsurf to 2,600+ enterprise data sources with one binary. | |
| io.github.Openfinanceorg/openfinance openfinanceorg/openfinance-app Connect your financial accounts to view balances, search transactions, and get spending insights. | |
| io.github.openflowkit/openflowkit-mcp openflowkit/openflowkit Architecture diagrams for your agent: draw on the live OpenFlowKit canvas or edit diagram files. | |
| OpenFormatDB openformatdb/openformatdb Identify a file, find open tools for its format, convert it locally with WebAssembly. | |
| io.github.openfused/openfuse-mcp openfused/openfused Encrypted mail, shared memory, and persistent context for AI agents. | |
| io.github.opengameapp/browser-game opengameapp/opengame-showcases Local tools for planning and validating focused browser-game prototypes. | |
| OpenHCS openhcsdev/openhcs Inspect, author, validate, and run high-content microscopy workflows. | |
| OpenHeritage Public Search openheritageonline/agent-tooling Read-only OpenHeritage search for genealogy and cultural heritage records. | |
| Openhook openhook-dev/openhook-inbox Private channels for people and their AI agents. | |
| OpenImageDebugger MCP openimagedebugger/openimagedebugger MCP server giving AI agents eyes on OpenImageDebugger buffers in live gdb/lldb sessions | |
| Ekbasis openinterpretability/ekbasis Foresee what git commands and multi-step changes will do, as calibrated probabilities | |
| ABAP Accelerator openkash/abap-accelerator MCP server for SAP ABAP development with 15 tools for ABAP objects, syntax, ATC, and more | |
| Openlayer openlayer-ai/openlayer-skills Inspect AI projects, traces, tests, and governance rules in Openlayer, and debug failing evals. | |
| Open Loyalty openloyalty/openloyalty-mcp Manage Open Loyalty programs: members, points, rewards, campaigns, tiers and transactions. | |
| Linear Project openly-useful/linear-project-skills Scope-gated Linear project administration with optional GitHub and Obsidian evidence adapters | |
| Project Status openly-useful/project-status Read-only project readiness, dependency, evidence, and bounded local activity views. | |
| OpenMail openmailsh/mcp Gmail for agents: create inboxes, read and reply to mail, send email, manage domains. OAuth sign-in. | |
| OpenNodes opennodes-io/opennodes Discover verified AI inference nodes, get the best node+model per task, pre-price chains. | |
| Raptor Studio openpowershift/raptorstudio Build, validate and simulate reliability block diagrams (RAM analysis) from an AI assistant. | |
| Scout openscout-app/scout Coordinate local coding agents and track handoffs. | |
| SocialSeal opensealai/agent-skills Measure how findable a brand is in TikTok, Instagram, YouTube and AI search, and what to post next. | |
| OpenSOSData – US Business Entity Search opensosdata/opensosdata-mcp Search US business entity records across all 53 jurisdictions in real time | |
| openstatus openstatushq/openstatus Manage monitors, status pages, incidents and maintenances in your openstatus workspace. | |
| com.opentext/sdp-remote-mcp opentext/opentext-model-context-protocol-server Model Context Protocol server for OpenText Software Delivery Platform. | |
| OpenTrain opentrain-ai/opentrain-platform-monorepo Hire human data labelers, RLHF annotators, and evaluators from your coding agent. | |
| Open Waters AIS openwatersio/aiscast Live AIS vessel positions by MMSI, name, area, or radius, plus coverage. No sign-in, no key. | |
| ai.mitosislabs/mitosis operatingsystem-1/website Mitosis agent-memory platform: pricing, docs search, platform status, agent skills. No auth. | |
| io.github.Ophir-ai-creator/ophir ophir-protocol/ophir Ophir protocol tools for AI agent discovery, negotiation, and settlement | |
| Ophis MCP ophis-fi/ophis Gasless, MEV-protected onchain token swaps for AI agents on 14 EVM chains, built on CoW Protocol. | |
| Storeboard ophydami/storeboard-mcp Generate exact-size App Store and Google Play screenshots, feature graphics, and listing copy. | |
| AIKI Knowledge Commons opnwiki/aiki-mcp Authenticated MCP access to the AIKI open knowledge commons. | |
| opointo opointohq/opointo-mcp Design a React Native app in a browser and emit it as a real Expo project you own, iOS and Android. |
46,901–46,950 of 50,909
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.