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 |
|---|---|
| Graph Memory MCP brikerman/graph-memory-mcp Enables AI agents to build and query a persistent knowledge graph with entities, relationships, and observations. Features a core index system that ensures critical information is always accessible across all memory operations. | |
| lightpanda-mcp-server brilhante29/lightpanda-mcp-server MCP server for Lightpanda headless browser enabling ultra-fast HTML extraction, markdown conversion, and JavaScript execution with 16x lower memory footprint than Chrome. | |
| Local Agent Automation MCP brili99/automation-mcp Enables MCP clients to manage SQLite-backed TODOs and schedule durable coding-agent jobs over stdio, with persistent job memory, run history, and a read-only dashboard. | |
| consulting-mcp-server brinkv3/consulting-mcp-server Exposes RAG and document intelligence pipelines as 8 composable tools for MCP-compatible clients, enabling querying, indexing, classifying, extracting, and assessing documents. | |
| Commerce Cloud MCP Server brinzl/commercecloud-mcp-server Connects AI applications with Salesforce Commerce Cloud for product management, order analysis, custom object operations, and content asset management. | |
| reprox-mcp bristinwild/reprox-mcp Enables coding agents to search and retrieve persistent repository memory created by Cliper, providing context, gaps, architecture, and timeline information via MCP tools. | |
| Britive MCP Server britive/mcp-server Enables AI agents and users to interact with the Britive platform for dynamic access, query configurations, reporting, and access activity. | |
| vibe-school britov/vibe-school Enables Claude to run a structured learning program by selecting topics, delivering lectures to a local site, reading and grading answers, tracking progress, and closing completed topics. It also serves a localhost website for viewing the c | |
| bolt-mcp brittainknight/bolt-mcp Enables coding agents to surgically harvest licensed upstream code, scaffold adapters behind canonical contracts, audit seams, verify live behavior, and promote or mount proven components while preserving the host architecture. | |
| Deep Code Reasoning MCP Server brittanyblake72399/deep-code-reasoning-mcp Enables a multi-model workflow where Claude Code escalates complex code-analysis tasks to Gemini for large-context tracing, cross-system impact analysis, performance bottleneck detection, and hypothesis testing. | |
| multiCAD-mcp brittanypersson84450/multicad-mcp Enables AI assistants like Claude for Desktop or Cursor to control Windows CAD applications (AutoCAD, ZWCAD, GstarCAD, BricsCAD) through natural-language instructions, exposing unified MCP tools for drawing, layers, blocks, entities, proper | |
| niblet brittanys5005/niblet-skill-mcp Enables coding agents to ground UI work in real product screens by returning inline screenshots of concrete layouts, states, and interactions, plus fonts and icons with their recorded licenses. It also serves a bundled design workflow that | |
| P4 MCP Server brittanysenturk4896/p4mcp-server Enables AI assistants to securely read and write Perforce version-control data such as files, changelists, shelves, workspaces, jobs, reviews, streams, and server metadata. Also supports P4 DAM asset search, metadata retrieval, review manag | |
| competitive-intel brittanyslay/competitive-intel Autonomous competitive intelligence tracking competitors across LinkedIn, news, reviews, job postings, and regulatory signals, generating executive briefs and sales battlecards. | |
| WooCommerce MCP Server brivera862/woocommerce-mcp-server Enables interaction with WooCommerce stores through the WordPress REST API, supporting management of products, orders, customers, shipping, taxes, coupons, reports, settings, and related store data. | |
| promptlint brixsoftworks/promptlint Enables AI coding agents to automatically lint and auto-fix their generated prompts before running them, helping improve prompt quality, security, and cost efficiency. | |
| resume-admin briznap/resume-ai-mcp Enables querying admin sign-in data from resume.naplab.org, such as last sign-in and sign-in counts, via natural language. | |
| dbt-cloud-migrate brjan/dbt-cloud-migration-tool Audits dbt Core projects for migration blockers and generates actionable guidance for migrating to dbt Cloud, including auto-fixing deprecated syntax. | |
| GENTAHAX MCP brk08/gentahax-mcp Enables AI assistants to query an offline, binary-verified GENTAHAX Lua API knowledge base (functions, hooks, structs, packet types, variants, 6832 real item IDs), analyze Lua code for ban risk, and — via a deployable in-game file-IPC bridg | |
| Türkiye Vergi MCP brkazmn/vergimcp Enables Turkish tax research, calculation, and document management using official GİB resources, including legislation search, tax computation, invoice validation, and circular drafting. | |
| pty-mcp brkhrdt/pty-mcp Enables AI agents to start and manage pseudo-terminal sessions, run shell commands and interact with REPLs programmatically. | |
| tidbits-memory brkhrdt/tidbits-memory Enables AI agents to record and rank learnings, facts, and methods through a collaborative voting framework. It provides tools for agents to surface the most useful information across sessions using persistent memory storage. | |
| Jev MCP Server brknx/antigravity-typesafe-jev Exposes four System 1 decision tools — categorical choice, rubric scoring, binary probability assertions, and a pre-execution guardrail — over stdio JSON-RPC. This enables agents to make sub-second routing, triage, and safety decisions with | |
| sts2-mcp-bridge brmarcosbr/sts2-mcp-bridge Enables an MCP agent to observe and command Slay the Spire 2 game state via HTTP, and optionally autopilot combat with a local deterministic policy, without LLM in the critical path. | |
| AstroConsultant brmh/astromcp An AI astrology MCP server providing 49 tools for Western and Vedic astrology calculations, including natal charts, dashas, transits, and compatibility analysis, powered by Swiss Ephemeris. | |
| Meta Ads MCP Server brmh/meta-mcp A comprehensive MCP server for managing and analyzing Meta Ads (Facebook/Instagram) with over 80 natural-language tools for AI agents like Claude Desktop. | |
| Project Planner MCP brnbio/project-planner-mcp MCP server for structured Laravel project planning. Scans projects, creates tickets, and exports as JSON. | |
| brandomica-mcp-server brndmk/brandomica-mcp-server Stdio-based MCP server with 12 tools for brand name availability and safety checks. Returns structured JSON for domains (with pricing), social handles, USPTO/EUIPO trademarks, app stores, package registries, safety scoring, batch comparison | |
| Fabric MCP Server brneto/fabric-mcp-server Provides access to Daniel Miessler's Fabric AI prompts (patterns and strategies) through MCP, automatically syncing with the upstream repository to enable powerful prompt templates in AI workflows. | |
| Remote MCP Server (Authless) brnndnn/lbk-mcp Allows deploying a Model Context Protocol server on Cloudflare Workers without authentication, enabling AI assistants to access custom tools through the MCP standard. | |
| Todocko MCP Server brnt-cz/todocko-mcp Enables AI assistants to manage Todocko application data, including tasks, projects, worklogs, and attachments. It supports comprehensive project management operations such as tracking activity, managing Kanban boards, and handling shared p | |
| MyOTPApp brntech/myotp-agentkit Send and verify one-time passcodes over SMS, WhatsApp and Telegram from any MCP client. Ten tools: send, verify, extend, delivery status, account, usage report, and agent account creation with credit top-ups over a 402. Hosted endpoint or r | |
| jev-ra brnyxx/jev-ra Enables browser automation for coding agents via MCP, allowing them to open pages, search, extract data, click, type, and complete multi-step tasks with fast single-round-trip decisions. | |
| SVG Canvas MCP brnyxx/svg-canvas-mcp An MCP server for Claude Code that enables the creation and manipulation of professional-grade SVG graphics using features like layer management, complex path drawing, and animations. It includes AI-assisted design capabilities for color su | |
| Memory Custom bro3886/mcp-memory-custom A customized MCP memory server that enables creation and management of a knowledge graph with features like custom memory paths and timestamping for capturing interactions via language models. | |
| io.github.morluto/flameox brobert3335/flameox Enables coding agents to coordinate local profilers, benchmark tools, trace processors, and direct targets, turning explicit artifacts or commands into bounded runtime evidence with provenance, coverage, and limitations. Exposes named analy | |
| SandMail — Disposable Email API for AI Agents brobin002/sandmail-mcp Create disposable email inboxes, extract OTP codes in 15 languages, and receive webhooks — all from your AI agent. One call: create inbox → wait for email → get the verification code. Supports 7 domains, email forwarding, and HMAC-signed we | |
| notebooklm-mcp brock-run/notebooklm-mcp MCP server for Google NotebookLM enabling notebook, source, and audio overview management with hybrid metadata storage. | |
| weather-mcp-server brockly/weather-mcp-server Provides weather alerts and forecasts for US locations using the National Weather Service API. | |
| Whimsical MCP Server brockreece/whimsical-mcp-server Enables programmatic creation of Whimsical diagrams from Mermaid markup generated by AI models like Claude through the Model Context Protocol. | |
| Open Census MCP Server brockwebb/open-census-mcp-server Enables natural language queries of U.S. Census Bureau data, translating plain English questions into proper API calls and returning demographic, economic, and housing statistics with proper statistical interpretation and context. | |
| connectivity-diagnostics brocla/connectivity-mcp-server Enables AI assistants to perform real network diagnostics on the local machine, including ping, traceroute, DNS lookups, TLS checks, and more. | |
| Brode brode-io/brode-mcp Brode.io - Convert any image into machine embroidery files (DST, PES, JEF, VP3, EXP, U01, XXX) or vector graphics (SVG, PDF, EPS, DXF) — hosted remote server with a free tier, by the maker of the Brode web app. | |
| memory-autopsy-mcp brodewa369/memory-autopsy Enables MCP clients to lint stored agent facts for duplicates, contradictions, and staleness (including implicit conflicts found via local embeddings), and to gate a new fact for admission before it is persisted. It runs read-only over stdi | |
| Excel LSP brody900/excel-lsp-for-ai-agents An MCP server that provides a semantic index and 14 bounded tools for AI agents to navigate Excel workbooks by symbols, references, and diagnostics, avoiding the need to read entire rows. | |
| Rally Desk brodyga45/rally-desk-mcp-20261020 Enables a local MCP client to coordinate club-night doubles play by proposing next rounds, rotating resting players, recording completed results, and correcting scores without erasing history. It provides transactional retries, session stat | |
| MCP Weather Server broerjuang/mcp-weather A containerized server that provides weather tools for AI assistants, allowing them to access US weather alerts and forecasts through the National Weather Service API. | |
| MCPServerL2 broflotsky/mcpserverl2 Enables users to run a modular TypeScript MCP server that communicates over STDIO and exposes tools for summing numbers and greeting users. | |
| OpenAPI MCP Server broisnees/openapi-mcp Exposes an MCP server over HTTP that allows searching and executing OpenAPI operations from any OpenAPI spec URL, with session variable storage. | |
| @registry/mcp broisnees/registry-mcp Unified MCP server for searching, analyzing, and managing packages across npm, JSR, Deno, and multiple CDN providers with auto-detection. |
35,651–35,700 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.