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 |
|---|---|
| EVE Online Companion MCP Server 32n1/evemcp An MCP server that provides Claude with direct access to EVE Online character data, market prices, killboard intelligence, wiki knowledge, and game mechanics. It enables natural language interaction for checking skills, analyzing fittings, | |
| Remote MCP Server (Authless) 330667/remote-mcp-server-authless Deploy a remote MCP server on Cloudflare Workers without authentication, enabling connection to custom tools via SSE. | |
| corpus.333.eco 333eco/corpus.333.eco Enables agents to search, retrieve, and list open-licensed documents with verifiable provenance, attaching sha256, DOI, and OpenTimestamps proof to every response. | |
| agent-browser-mcp 335234131/agent-browser-mcp Enables AI agents to directly control your real Chrome browser with full context including login sessions, cookies, and open tabs. It provides tools for page scanning, JavaScript execution, CDP control, screenshots, and physical mouse/keybo | |
| lisa-mcp 33audits/lisa Enables agent harnesses to run autonomous browser-based QA on staging apps, triage and fix found bugs, and re-verify them using the agent's existing model access. | |
| Roblox MCP Server 33jrdd/roblox-mcp Enables AI assistants to interact with running Roblox game instances by inspecting the game hierarchy, reading client-side scripts, and executing Lua code directly within the Roblox client through a WebSocket bridge. | |
| Oli Docs MCP 33may/oli-docs-mcp Local MCP server for querying Oli/LimX documentation via keyword, vector, or hybrid search, with citation support for use in Claude Code or OpenCode/August. | |
| graph-arch 3486038424/neo4j_mcp_controller Neo4j-backed MCP server managing code architecture dependency graphs, enabling AI agents to query impact, submit change intents, and coordinate reactive multi-agent workflows. | |
| defi-yield-scanner-mcp 34t34f3/defi-yield-scanner-mcp Real-time DeFi analytics MCP server for AI agents. Provides token risk analysis, yield scanning, and wallet exposure checking across Base, Ethereum, and Arbitrum. | |
| stripe-webhook-mcp 3598644/stripe-webhook-mcp Enables AI coding agents to capture, inspect, and replay Stripe webhook events into a local handler with valid signatures, returning the handler's status and body so agents can debug failures directly. | |
| FGCLIP-MCP 360cvgroup/fgclip-mcp MCP server for FG-CLIP embedding services enabling multi-modal similarity computation for text and images. | |
| mcp-auth-poc 360xview/mcp-auth-poc A minimal MCP server with token-based authentication and SSE transport, providing greeting and echo tools for testing authentication patterns in remote MCP servers. | |
| Gerent365 MCP Server 365diascollaboration-prog/gerent365-mcp Enables AI assistants to manage Gerent365 restaurant and business operations via natural language, including employees, schedules, payroll, tips, time tracking, customers, products, reservations, and reports. | |
| nanoboy-social-mcp 365diascollaboration-prog/ig-latam-mcp MCP server for Instagram growth in LATAM, enabling automated DM flows, comment management, and account analytics. | |
| Context7 MCP 3737123dush/context7 Provides LLMs with up-to-date, version-specific documentation and code examples directly from library sources, eliminating outdated training data and hallucinated APIs by fetching current documentation at prompt time. | |
| bili-open-mcp 3810220770/bili-open-mcp-bilibili-mcp-server Lets AI agents search 170 Bilibili open-platform docs and 100 endpoints, then build 2.0 HMAC-SHA256 signatures, run OAuth2 flows, plan video uploads, verify webhooks, and call live-room WebSocket protocols. Also handles cookie-based web req | |
| uplus-mcp 3995019608-cyber/uplus-mcp Enables users to patrol QingSoft U+ courses, track homework and experiments, read objective questions into structured briefs for a connected MCP client model to answer, fill and verify selections, and optionally submit, while handing subjec | |
| Fujitsu Social Digital Twin MCP Server 3a3/fujitsu-sdt-mcp Enables LLMs to access Fujitsu's Digital Rehearsal API through natural language, allowing users to run and analyze simulations of human and social behavior in digital space. | |
| Symath-MCP 3akhp/math-mcp A symbolic mathematics MCP server supporting calculus, linear algebra, number theory, statistics, and unit conversion via natural language. | |
| remnawave-mcp 3apa3a-3aho3a/remnawave-mcp Enables Claude Desktop, Cursor, and other MCP clients to inspect a Remnawave 3.x panel through natural-language chat, covering users, nodes, traffic, devices, connections, and GeoCheck, with tools generated from the official backend contrac | |
| Blender MCP Ultra 3bdull4h2008/blender-mcp-ultra Enables AI agents to control Blender through 150+ tools across 24 modules, including modeling, materials, lighting, animation, rendering, mesh quality analysis, and visual feedback, plus expert prompts and goal-first workflow management. | |
| Archicad MCP 3d-mcp/archicad-mcp Enables MCP-compatible assistants to connect to a local Archicad instance through its built-in JSON API, checking connection status, inspecting the current selection, and optionally invoking supported native commands with confirmation. | |
| Blender MCP 3d-mcp/blender-mcp Connects MCP-compatible assistants to Blender to read scene and selection context, and optionally execute user-requested Python through Blender's native API when explicitly enabled. | |
| Revit MCP 3d-mcp/revit-mcp Connects an MCP-compatible assistant running locally to a native Revit session through a pyRevit bridge, exposing document and selection context, status checks, and optionally unsandboxed IronPython scripting that can modify models and file | |
| Rhino MCP 3d-mcp/rhino-mcp It connects MCP-compatible assistants to Rhino 8 for checking status and describing the current selection, with optional explicitly enabled native Python scripting access. | |
| SketchUp MCP 3d-mcp/sketchup-mcp Connects a locally running MCP-compatible assistant to SketchUp desktop, letting it check connection status and describe the current document and selection. Optionally enables explicitly approved, unsandboxed native Ruby scripting for deepe | |
| Code Scalpel 3d-tech-solutions/code-scalpel Enables AI assistants to surgically extract and analyze code, reducing token usage and costs by up to 200x compared to reading entire files. | |
| 3Dawn MCP Server 3dawnrh/3dawn-mcp Enables AI assistants to control the 3Dawn 3D marketplace, including generating 3D models, managing assets, browsing marketplace listings, and viewing earnings, all through natural language. | |
| HoudiniMCP Server 3dprevis/h_c_mcp Connects SideFX Houdini to Claude via the Model Context Protocol, enabling node creation, modification, and code execution through natural language. | |
| AWS API MCP Server 3feet-lim/aws-api-mcp Enables AI assistants to interact with AWS services and resources through AWS CLI commands, allowing management of AWS infrastructure with security controls. | |
| three_api 3godzinyl/mcp-multi-api-worker-gpt-6-astra- Provides read-only access to local AI work center metadata including status, providers, usage, projects, and tasks via MCP. | |
| pixel-composer-mcp 3hoo/pixel-composer-mcp Enables an agent to open Pixel Composer projects, inspect node graphs, edit input values, run console commands, and render all Export nodes. | |
| ms-teams-mcp 3hs-labs/ms-teams-mcp MCP server providing access to Microsoft Teams chats/channels, Outlook emails, calendar events, and SharePoint files via Microsoft Graph API. | |
| spec-drift-mcp 3ii-factory/spec-drift-mcp Enables AI coding agents to verify code against YAML specifications, detecting missing fields, extra fields, and type mismatches to prevent silent drift before commits. | |
| brainlehr 3lehr/brainlehr A local MCP knowledge store that enforces provenance, flags missing citations, and measures retrieval quality, enabling natural language search and management of verified knowledge via SQLite. | |
| Phosphene 3lmglow/phosphene An MCP server for intimate human-AI relationships that enables AI to create and manage daily tasks, challenges, and surprise tasks, with user completion tracking, points, and rewards. | |
| Markdown Memory Context MCP Server 3m1ry33t/markdown-memory-context-mcp Enables AI agents to maintain a structured Markdown or Obsidian memory vault with tools for reading, writing, searching, and organizing notes. | |
| own-computer-use 3mad101c/own-computer-use A self-hosted MCP server that enables AI agents to see and control a Windows PC through screenshots, built-in Arabic/English OCR, mouse, keyboard, clipboard, and application launching, with code-enforced consent and audit logging. | |
| css-tutor 3mdistal/css-mcp-server Acts as a CSS Tutor, providing personalized updates about CSS features by fetching latest news, tracking user knowledge, and guiding AI clients. | |
| K Filesystem MCP 3mzkk/k-filesystem-mcp A tuned filesystem MCP server for Codex-style development, offering fast file operations, bounded output, and safe edits. | |
| Airtable MCP Server 3nuggets/airtable-mcp-server Exposes the full Airtable Web API including document attachment upload and download, runs on Cloudflare Workers with OAuth 2.1 authentication, and supports file staging via R2 for unlimited attachment sizes. | |
| ArchitectGBT MCP Server 3rdbrain/architectgbt-mcp Provides AI model recommendations, cost estimates, and code templates directly in the IDE via MCP tools, enabling developers to browse 50+ models, get personalized suggestions, and integrate production-ready code without leaving Cursor or C | |
| M3S Councils 3rts0n/m3s-councils Enables a business decision to be pressure-tested by five distinct AI perspectives — Counterparty, Contrarian, CFO, Operator, and Precedent — each examining a different constraint. Returns a compact brief with a recommendation, its stronges | |
| Make MCP Server 3rzy/make-mcp-integration-issue An integration server that allows Claude Desktop to communicate with Make (formerly Integromat) automation platform through the Model Context Protocol, enabling scenario management and execution via natural language. | |
| SOLVE-IT MCP Server 3soos3/mcp-solve-it This MCP server wraps the SOLVE-IT digital forensics knowledge base, enabling LLMs to query techniques, weaknesses, mitigations, and their relationships through a set of MCP tools. | |
| MCP Gateway 3thanol4/mcp-agent-showcase Enables AI agents to discover and invoke enterprise tools like web search, document parsing, meeting scheduling, and email through a unified Model Context Protocol server that aggregates and routes across multiple backends. | |
| market-screening 3vgen/market-screening Enables an LLM to search grocery products across Russian retail chains, compare comparable items by unit price, and compute the cheapest basket either in one store or split across several. | |
| Domain Checker MCP Server 3viky/mcp-domain-checker Enables AI agents to check domain availability, perform batch domain lookups, and generate intelligent domain name suggestions across multiple TLDs using WHOIS integration. | |
| MCP Domain Checker Price 3viky/mcp-domain-checker-price Provides domain registration pricing from Joker.com and generates affiliate purchase links. Supports both static pricing data for instant responses and optional real-time API pricing with smart caching. | |
| GitLab CI MCP Server 3viky/mcp-gitlab-ci Enables AI agents to monitor and debug GitLab CI/CD pipelines by providing tools to list pipelines, retrieve job logs, and analyze failure root causes. It features automated error pattern extraction and failure analysis to streamline pipeli |
22,101–22,150 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.