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 |
|---|---|
| Deslop MCP Server collin-ho/deslop-mcp Detects and automatically removes AI-generated code slop patterns like redundant comments, verbose logging, and unnecessary error handling across multiple programming languages. | |
| Virtual Care MCP collinbentley1/virtual-care-mcp Enables portable synthetic virtual-care visits through MCP Apps and browser, allowing users to prepare appointments, rehearse consultations, simulate insurance and self-pay billing, and export FHIR records. | |
| Block MCP Server collindex/block-mcp Enables AI agents to interact with multiple blockchain networks to check wallet balances, gas prices, and transaction history on the Frax network. It also includes tools for real-time cryptocurrency conversion and sending automated notifica | |
| Manas collindjohnson/manas Enables interaction with a local knowledge repository via MCP, providing tools for capturing, indexing, and searching Markdown notes with Git version control and optional semantic search. | |
| south-valley-weather-mcp-server collinpfern/south-valley-weather-mcp-server Enables deploying a stateless remote MCP server on Cloudflare Workers without authentication, with tools that can be connected to Cloudflare AI Playground or local clients via mcp-remote. | |
| mcp-rls-auth-pattern collinprice-commits/mcp-rls-auth-pattern Enables MCP access to multi-tenant PostgreSQL data where tenant isolation is enforced by row-level security instead of application-layer filters, removing the need for per-handler tenant checks and service-role keys on the request path. | |
| Luma MCP collins1150/luma-mcp Enables AI coding models without native vision to analyze images such as screenshots, error messages, UI layouts, and documents through a single image_understand tool. Supports multiple vision LLM providers including GLM-4.6V, DeepSeek-OCR, | |
| Mercury Enhanced MCP collinsb1/mercury-enhanced-mcp A custom MCP server for the Mercury banking API that uses personal API tokens to avoid session expiry. It provides 15 tools for managing accounts, transactions, recipients, treasury, and more. | |
| Zotero MCP Bridge colobas/zotero_mcp_plugin Enables LLM clients to browse and query your Zotero library through tool calls. Provides access to Zotero-specific functions like listing open tabs, searching items, and browsing collections via a local MCP server running inside Zotero. | |
| Blueprint colofabrix/blueprint-mcp Blueprint is an MCP server that enables AI assistants to create C4 software architecture diagrams from structured data. | |
| graphql-mcp colofonbrigade/linear-graphql-mcp Exposes any GraphQL API as a single tool for executing queries and mutations with authentication support. | |
| Canvas MCP Server colombo41/mcp-canvas-lms Enables interaction with Canvas LMS through its API, supporting course, assignment, enrollment, grade, discussion, file, and account administration workflows for students, instructors, and administrators via MCP clients. | |
| rack-mcp colonelkernel/vcv-rack-mcp Enables MCP clients to discover running VCV Rack instances, inspect and validate patches, apply structured changes atomically with confirmation, manage patch files with checkpoints, and read signal telemetry via a secure local loopback brid | |
| Manent colopisalvatore/manent MCP server that turns a git-versioned Markdown vault into a queryable memory for AI agents, providing tools like brain_search, brain_read, and brain_neighbors. | |
| sigma-mem coloradored13/sigma-mem Provides persistent identity and shared team memory for AI agents, enabling context-aware retrieval and coordination across sessions via a HATEOAS state machine. | |
| sigma-verify coloradored13/sigma-verify Enables Claude Code agents to cross-check findings against OpenAI, Google Gemini, and Ollama-served models, tagging every result with provider and model provenance and reporting cross-model agreement. | |
| cloakbrowser-mcp colorsource/cloakbrowser-mcp Stealth browser automation for AI agents, using source-patched Chromium to bypass bot detection systems like Cloudflare, reCAPTCHA, and FingerprintJS. | |
| Drex MCP colt2822/drex-mcp Enables MCP-compatible agents to submit a question, explicit choices, and optional evidence to Nace.AI Drex and receive a selected choice with probabilities, while leaving action decisions to the agent. | |
| carrel coltonbearden/carrel Enables local file search, packing into LLM-ready context, and inspection via an MCP server on stdio. | |
| docket-mcp coltonshawproctor/docket-mcp Enables LLM agents to search Regulations.gov federal dockets, retrieve docket abstracts and metadata, and list rulemaking documents, giving read access to federal regulatory data. | |
| WebMiliastra Nodes Editor MCP Server columbina-dev/webmiliastranodeseditor-mcpserver Enables AI agents to create and manage node graphs and projects for Genshin Impact's Miliastra Wonderland system. Provides tools for reading, writing, and validating GraphDocument JSON files, managing project folders, and accessing node def | |
| Monarch Money MCP Server colvint/monarch-money-mcp An MCP server that provides access to personal financial data from Monarch Money, allowing users to retrieve account information, transactions, budgets, goals, and net worth through natural language queries. | |
| pywebview-mcp com55/pywebview-mcp Playwright-style MCP server for pywebview apps that lets AI assistants see, control, and debug Python desktop web UIs without modifying source code. | |
| 공시읽어주는AI comb0815/gongsi-ai-mcp A personal investment assistant MCP that selects and translates disclosures and news for your watchlist and sends daily KakaoTalk briefings. | |
| regcite combax/regcite-mcp Serves verified register data extracted from chip datasheets to AI coding agents, enabling register lookup, bit-field decode/encode, errata checks, document search, and init sequence retrieval. | |
| MSSQL MCP Server combiz/mssql-mcp-server Enables AI assistants to interact with Microsoft SQL Server databases through a standardized interface. Supports executing SQL queries, browsing database schemas, and viewing table data with flexible authentication options for both local an | |
| calculadora-combustivel comeca-ai/calculadora-combustivel Enables calculation of the most economical fuel (gasoline, ethanol, or natural gas) based on prices and vehicle consumption, following the 70% rule for ethanol and 60% for GNV. | |
| dsh-docker-desktop-mcp comecaramelos/dsh-docker-desktop-mcp Connects the Docker Desktop MCP gateway as an MCP server, enabling profile discovery, selection, and reconnection from the DSH web GUI. | |
| mcp-server-project comejia/mcp-server-project A collection of MCP servers for database management and Gmail integration, allowing AI agents to perform database queries and email operations. | |
| Better Prompts MCP comeonzhj/better-prompts-mcp Automatically extracts actionable methodologies from articles and URLs, stores them in a vector database, and retrieves relevant methods to enhance user prompts for more effective AI interactions. | |
| 即梦AI图片生成 MCP comeonzhj/jimengpic-mcp A MCP server that generates high-quality images using Volcano Engine's JiMeng AI API, supporting various aspect ratios and compatible with different MCP clients. | |
| Comet ML MCP Server comet-ml/comet-mcp Enables interaction with Comet ML's experiment tracking platform through the Model Context Protocol, providing tools for experiment management, project organization, and advanced search. | |
| my-mcp-template comet0322/mcp A generic FastMCP server template for building CLI coding agent tools, with example tools, authentication, and a comprehensive test suite. | |
| remote-mcp-starter comet32/remote-mcp-starter Enables wrapping a SaaS API as a hosted, stateless MCP server over Streamable HTTP, with OAuth 2.1 brokered login, CIMD/dynamic client registration, scope checks, and upstream tokens kept server-side. Write tools default to dry-run previews | |
| gpt-image-mcp cometa-kaito/gpt-image-mcp MCP server that exposes OpenAI image generation and editing as tools, focused on creating consistent character expressions by compositing edited regions onto a stable base image. | |
| Dappier MCP Server cometdev312/dappier-mcp-server-real-time-web-market-data-for-ai-agents Enables fast real-time web search and access to premium data from trusted sources including news, financial markets, sports, and more. Supports AI agents with live data and curated content from various domains. | |
| Cometix Indexer cometixai/cometix-indexer A local indexing and retrieval service that enables semantic code search by wrapping Cursor's backend RepositoryService. It provides tools for indexing local workspaces and performing incremental semantic searches with automatic synchroniza | |
| Obsidian MCP Second Brain Server comfucios/second-brain-mcp Enables read-only access to Obsidian vaults with semantic search, tag filtering, and metadata queries. Provides secure, intelligent note retrieval and summarization for LLMs without modifying your vault. | |
| iitc-mcp comicchang/iitc-mcp Bridge between IITC and MCP agents, enabling AI assistants to interact with Ingress Intel: view map, count portals, track players, and communicate via COMM without manual input. | |
| Composio MCP Server comigor/composio-mcp-server Exposes Composio tools and actions (Gmail, Linear, etc.) as MCP-compatible tools for language models to interact with in a structured way. | |
| comind-mcp comind-pro/comind-mcp A gateway that connects MCP servers and REST APIs, allowing you to curate tools into groups and expose them as virtual MCP servers for agents. | |
| GatewayMCP comindspace/gateway-mcp Enables AI coding and operational assistants to securely access company systems through a single MCP endpoint, with OAuth authentication, scoped resource grants, audit logging, secret isolation, and corporate memory. | |
| Portfolio MCP Server comlyboy/corneliusokeke-ai-portfolio Enables AI assistants to discover and retrieve professional portfolio information including profile, experience, skills, projects, and contact details through MCP tools. | |
| pipedrive-mcp comma-compliance/pipedrive-mcp MCP server for Pipedrive CRM providing 88 tools for full CRUD on deals, persons, organizations, activities, and more, with custom field resolution and safety guards. | |
| mcp-servicefusion commair-tools/mcp-servicefusion-public Enables AI-assisted field service management through the Service Fusion API, including job lookup, customer management, dispatch, invoicing, and equipment tracking. | |
| Cimon-MCP commander17x/cimon-mcp Offline MCP server with runbooks for high-volume logs, metrics, traces, and event streams. Search and diagnose symptoms without external dependencies. | |
| discord-admin-mcp commanderbiz/discord-admin-mcp Enables Discord server administration through MCP, providing tools for role management, member moderation, channel operations, and message purging. | |
| Leetcoder commanderturtle/leetcoder Enables Hermes agents to delegate bounded coding tasks to persistent oh-my-pi sessions with isolated git worktrees, live steering, and durable follow-ups, requiring explicit user confirmation before each task. | |
| weight-mcp commandertvis/weight-mcp A personal calorie and protein counter MCP server for use inside claude.ai, enabling users to log meals from photos or text, track weight, and view an interactive dashboard. | |
| Walrus Memory MCP commandosslabs/walrus-memory-mcp-plugin Enables MCP clients to connect to Walrus Memory for persistent memory operations like remember, recall, analyze, and restore, with browser-based wallet login and local credential storage. |
40,051–40,100 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.