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 |
|---|---|
| Cyan Eclipse Haven MCP cyan-eclipse-technologies-llc/cyan-eclipse-haven-mcp The governed Zendesk server: OAuth-first, drafts until approved, and a receipt for every touch. | |
| Cyan Eclipse Ledger MCP cyan-eclipse-technologies-llc/cyan-eclipse-ledger-mcp Eclipse Ledger — betting records, price comparison, and responsible-gambling controls. Not a bookmaker. | |
| Cyan Eclipse Legacy Recon MCP cyan-eclipse-technologies-llc/cyan-eclipse-legacy-recon-mcp Point an agent at a codebase: narrowed-scope architecture map, dependency/EOL risk list, modernization estimate inputs. | |
| Cyan Eclipse Loft MCP cyan-eclipse-technologies-llc/cyan-eclipse-loft-mcp Governed design-to-print authority for agents — signed provenance from model to machine, safety gates. | |
| Cyan Eclipse Marquee MCP cyan-eclipse-technologies-llc/cyan-eclipse-marquee-mcp The live-events agent: it finds the event, watches the price, buys only inside your mandate, and receipts everything. | |
| Cyan Eclipse Meridian MCP cyan-eclipse-technologies-llc/cyan-eclipse-meridian-mcp Governed telehealth operations — jurisdiction-gated encounters, signed-note integrity, PHI access receipts. | |
| Eclipse Muster MCP cyan-eclipse-technologies-llc/cyan-eclipse-muster-mcp Enables governed access to a canonical Customer Graph across CRM and customer-service records, with per-field provenance, propose-only identity merges, field-level masking, records-only reply drafting, tiered policy and kill-switch enforcem | |
| Cyan Eclipse Orbit MCP cyan-eclipse-technologies-llc/cyan-eclipse-orbit-mcp The HubSpot wrap: the vendor's server, under policy — classified tools, approval gates, masking. | |
| Cyan Eclipse Pantry MCP cyan-eclipse-technologies-llc/cyan-eclipse-pantry-mcp The unattended-retail module — reads vending fleets' own telemetry and predicts stock-outs. | |
| Cyan Eclipse Proof MCP cyan-eclipse-technologies-llc/cyan-eclipse-proof-mcp Governed video production — Herald-signed approval pins over exact edit states, hash-pinned assets. | |
| Cyan Eclipse Proving MCP cyan-eclipse-technologies-llc/cyan-eclipse-proving-mcp Governed bench access for agents — signed mandates, pinned artifacts, evidence for every session. | |
| Eclipse Social Core MCP cyan-eclipse-technologies-llc/cyan-eclipse-social-core-mcp Enables canonical social content packages to be ingested, adapted into platform-native variants with classified diffs, and bound to hash-verified owner approvals. It also evaluates engagement policy, tracks accounts and kill switches, and r | |
| Cyan Eclipse Strike MCP cyan-eclipse-technologies-llc/cyan-eclipse-strike-mcp The Coinbase exchange adapter: spot products and books, normalized into the suite's one book. | |
| Eclipse Sunset cyan-eclipse-technologies-llc/cyan-eclipse-sunset-mcp Enables agents to ingest local registry snapshots, detect removed or newly deprecated tools and schema-breaking changes, verify deprecation claims against hash-chained evidence, and generate migration diffs for agent configurations. | |
| Cyan Eclipse Tether MCP cyan-eclipse-technologies-llc/cyan-eclipse-tether-mcp Governed robot task authority — signed mandates, bounded envelopes, evidence for every task. | |
| Cyan Eclipse Thread MCP cyan-eclipse-technologies-llc/cyan-eclipse-thread-mcp On-prem bridges for the legacy software-engineering toolchain, plus the Evidence Weaver that joins them. | |
| Cyan Eclipse Trunk MCP cyan-eclipse-technologies-llc/cyan-eclipse-trunk-mcp The governed Twilio adapter: every call and text under consent + mandate. | |
| Cyan Eclipse Voice Core MCP cyan-eclipse-technologies-llc/cyan-eclipse-voice-core-mcp The Consent Registry and Number Registry every Eclipse telephony adapter obeys. | |
| Eclipse Warranty cyan-eclipse-technologies-llc/cyan-eclipse-warranty-mcp Enables sealing, retrieving, verifying, transferring, and checking transferable warranty claim packs bound to product serials, buyer mandates, and retailer receipts, with tamper detection via local hash seals and chained transfer records. | |
| Cyan Eclipse Zephyr MCP cyan-eclipse-technologies-llc/cyan-eclipse-zephyr-mcp The Bluesky adapter: real public reads over the open AT Protocol, with review-first and house caps. | |
| atlas-mcp-server cyanheads/atlas-mcp-server ATLAS (Adaptive Task & Logic Automation System) is a Model Context Protocol server that provides hierarchical task management capabilities to Large Language Models. This tool provides LLMs with the structure and context needed to manage com | |
| docwriter-mcp-server cyanheads/docwriter-mcp-server A Model Context Protocol server for programmatic creation, modification, and compilation of structured LaTeX documents. | |
| filesystem-mcp-server cyanheads/filesystem-mcp-server A Model Context Protocol server that provides AI agents with secure access to local filesystem operations, enabling reading, writing, and managing files through a standardized interface. | |
| GitHub MCP Server cyanheads/github-mcp-server A Model Context Protocol server that enables LLM agents to manage GitHub repositories, issues, pull requests, branches, files, and releases through a standardized interface. | |
| JinaAI MCP Server cyanheads/jinaai-mcp-server Enables LLMs to read and extract clean, markdown-formatted content from any webpage using the Jina AI Reader API. | |
| mentor-mcp-server cyanheads/mentor-mcp-server Provides LLM Agents with AI-powered mentorship for code review, design critique, writing feedback, and brainstorming using the Deepseek API, enabling enhanced output in various development and strategic planning tasks. | |
| perplexity-mcp-server cyanheads/perplexity-mcp-server An MCP server that enables AI agents to perform search-augmented queries and deep multi-source research using the Perplexity API. | |
| Python MCP Server Examples cyanmage/building-mcp-servers-with-amazon-q-cli-and-python A collection of Python-based Model Context Protocol servers that extend AI assistant capabilities with tools for calculations, AWS services (S3 and RDS), and PostgreSQL database operations. | |
| proofrun cyano88/proofrun Enables budget-bound Binance trading workflows with preview and human approval, durable recovery, receipts, and reconciliation of interrupted orders without resubmission. | |
| CAD Super MCP cyanqx/cad2026codex-mcp Enables Codex or any MCP host to drive a local, writable AutoCAD 2026 with precision drafting, read-back verification, staging, undo, and a safety policy. | |
| Windows-MCP cyanqx/windows11-mcp Enables AI agents to automate Windows desktop via human-like mouse and keyboard input and UI Automation, with post-action verification for reliable control of programs, UI elements, windows, and files. | |
| codex-microsoft-todo-mcp cyanrange/codex-microsoft-todo-mcp A local MCP server that lets Codex and other MCP clients manage Microsoft To Do tasks through Microsoft Graph, supporting listing, creating, updating, and completing tasks. | |
| VibeMath cyanseek/vibemath Enables AI agents to explore an open, evidence-rich map of math problems, AI attempts, partial progress, solution claims, and replay-ready opportunities, with six read-only tools for searching, retrieving, and exporting status and handoffs. | |
| Steam Scout MCP cyanspearfitting4/steam-scout-mcp Enables AI assistants to research Steam games by fetching regional prices, reviews, current player counts, store charts, and news through public endpoints without an API key. | |
| Arcs-MCP cyanty/arcs-mcp A multi-platform one-click article publishing tool for MCP Service. | |
| Gemini Agent MCP Server cybaea/google-search-mcp An advanced MCP server that provides an agentic interface to Google's Gemini 3.1 models via Vertex AI, combining real-time Google Search, URL analysis, and Python code execution to solve complex multi-step research and data tasks. | |
| cloudsql-customers-orders cybage-devops/cloudsql-mcp-server-deepwiki Gives an AI agent read-only access to two tables in a Google Cloud SQL PostgreSQL database, letting it search customers by name and fetch a single customer's orders with an optional status filter. All access goes through fixed, parameterise | |
| cursor-agent-bridge cybas/cybas-agents-bridge MCP server that lets Claude Code or any MCP client delegate coding tasks to the local Cursor Agent CLI, with persistent per-workspace sessions and tools for diffing and pushing changes. | |
| cursor-agent-bridge cybas/cybas-agents-bridge-private Enables MCP clients like Claude Code to delegate coding tasks to the local Cursor Agent CLI, with persistent per-workspace sessions that resume across calls. | |
| indexnow-mcp cyber-kani/indexnow-mcp An MCP server for the IndexNow protocol that lets AI agents instantly submit URLs to Bing, Yandex, Seznam and Naver for fast indexing. | |
| seo-audit-mcp cyber-kani/seo-audit-mcp Enables AI agents to perform instant SEO audits, check robots.txt, sitemaps, and AI crawler access for any URL without API keys. | |
| MCP Hub cyber-lazer-mermicorn/mcp-hub A universal MCP hub that connects any AI agent to any tool, enabling agent interoperability with 50+ pre-built tools, custom tool creation, and tool discovery. | |
| obsidian-guarded-mcp cyber-sami/obsidian-guarded-mcp Enables Claude to securely read, search, and edit Markdown notes across multiple Obsidian vaults with path guards, soft delete, and vault switching. | |
| trello-guardrails-mcp cyber-sami/trello-guardrails-mcp Enables Claude to read and organize Trello boards by name, with archive-only writes and no guessing on ambiguous names. | |
| Chrome Browser Automation MCP Server cyber24bd/chrome-extension-mcp- Enables AI assistants to control Chrome browser for tab management, content extraction, and browser interactions via REST API. | |
| DevDocs MCP Server cyberagiinc/devdocs Integrates with Claude to enable intelligent querying of documentation data, transforming crawled technical documentation into an actionable resource that LLMs can directly interact with. | |
| agents_mcp_chat cyberantonz/mcp-chat Enables AI agents to communicate directly via 1-to-1 chat over MCP, supporting registration, chat creation, and message exchange without human relay. | |
| agent-relay cyberarchitecta/claude-codex-relay Enables running both Claude Code and Codex locally with a shared task board, session resume, cross-agent handoff, and an MCP bridge for inter-client messaging and task/context inspection. | |
| Session Archive cyberarchitecta/session-archive Enables searching and retrieving ChatGPT and Claude conversation exports locally, allowing assistants to fetch handoff context and continue conversations through read-only MCP tools. | |
| moex-mcp cyberash-dev/moex-mcp Provides access to Moscow Exchange data including quotes, trade history, candles, securities info, indices, and currency rates. Enables AI assistants to query financial market data through natural language. |
41,301–41,350 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.