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 |
|---|---|
| ucontrol-mcp codefitz/ucontrol-mcp MCP server for uControl, enabling read and write operations on schema, assets, and uMap via segregated tools with authentication. | |
| OpenContext codeforanchorage/alaska-geoportal-mcp Enables natural-language interaction with geospatial data from the State of Alaska Geoportal, allowing users to query and work with ArcGIS Online resources through an MCP-compatible interface. | |
| Anchorage Open Checkbook MCP codeforanchorage/anchorage-checkbook-mcp Read-only MCP server providing tools over Municipality of Anchorage's expenditure, payroll, procurement, and revenue data, with duplicates filtered by default. | |
| OpenContext codeforanchorage/anchorage-ecode-mcp Enables querying open data platforms like CKAN via natural language. Provides a configurable MCP server with plugins for different data sources. | |
| OpenContext codeforanchorage/anchorage-parcels-mcp An MCP server that connects to open data portals like CKAN and Socrata, enabling natural language querying of datasets via Claude. | |
| San Diego City GIS MCP codeforanchorage/audubon-iba-mcp Enables querying and spatial analysis of City of San Diego GIS layers (zoning, habitats, land use, etc.) via ArcGIS REST services, with tools for search, metadata, and spatial queries. | |
| San Diego Regional GIS MCP codeforanchorage/esri-living-atlas-mcp Enables natural language interaction with SANDAG's regional GIS datasets for San Diego County, supporting discovery, querying, and spatial analysis of layers like parcels, floodplains, and transit. | |
| OpenContext codeforanchorage/esri-uc-mcp Enables interaction with open data portals through a configurable plugin system, supporting CKAN and custom data sources. | |
| Worcester GIS MCP codeforanchorage/sandiego-city-mcp Enables querying and exploring the City of Worcester's open data portal (ArcGIS Hub) through natural language, including dataset search, type filtering, schema inspection, spatial point-in-polygon queries, and geocoding. | |
| San Diego GIS MCP codeforanchorage/sandiego-gis-mcp Serves SANDAG/SanGIS regional GIS data from SANDAG's ArcGIS Enterprise portal, enabling natural-language queries for parcels, floodplains, address points, transit, land use, and hundreds of other layers. | |
| Relay codeforcode111/relay-household Enables explainable household replanning by generating reviewable schedule proposals from constraint solving, with transactional MCP tools for retrieving state, proposing changes, committing approved plans, and undoing previous plans. | |
| OpenDayton codefordayton/opendayton Enables AI assistants to answer questions from curated public datasets about Dayton and Montgomery County, Ohio, with cited sources. | |
| Pinpole MCP Server codeforstartups/pinpole-mcp Enables AI agents to design cloud architectures, run cost/performance simulations, and draw them on a Pinpole canvas directly from Claude Code, Cursor, and OpenAI Codex. | |
| Salesforce CLI MCP Server codefriar/sf-mcp Exposes Salesforce CLI functionality to LLM tools like Claude Desktop, allowing AI agents to execute Salesforce commands, manage orgs, deploy code, and query data through natural language. | |
| ContextAtlas codefromkarl/contextatlas Enables AI coding agents to retrieve and manage code context with hybrid search, project memory, and observability via MCP tools. | |
| sru-mcp codefzer/sru-mcp An MCP server that searches library catalogs worldwide using the SRU protocol, enabling bibliographic search without API keys. | |
| GitHub v3 REST API MCP Server codeglide/google-maps-api Provides access to GitHub v3 REST API functionality through STDIO mode with FastMCP, enabling users to interact with GitHub resources. | |
| CodeGuardian MCP codegoddy/codeguardian_mcp Validates AI-generated code against actual codebases to catch hallucinations, dead code, and API mismatches before runtime. | |
| CodeGraph codegraph-ai/codegraph-vscode CodeGraph — Open-source code intelligence MCP server. Builds a semantic graph of your codebase (functions, classes, imports, call chains) and exposes it through 31 tools. Callers, callees, impact analysis, complexity metrics, unused code de | |
| CodeGraphContext codegraphcontext/codegraphcontext Indexes local Python code into a Neo4j graph database to provide AI assistants with deep code understanding and relationship analysis. Enables querying code structure, dependencies, and impact analysis through natural language interactions. | |
| MCP Hub codehalwell/gradio-mcp-agent-hack A sophisticated research assistant that orchestrates a 5-step workflow of connected AI agents to provide deep research capabilities including question enhancement, web search, summarization, citation formatting, and result combination. | |
| n8n MCP Server codehalwell/n8n-mcp Enables creation, management, and execution of n8n workflows through a secure HTTP API. Provides tools to build workflows with schema validation, activate/deactivate them, and execute automation tasks programmatically. | |
| ts-code-awareness codehead-pl/ts-code-awareness A static-analysis knowledge base for TypeScript/NestJS codebases, served to AI agents over MCP for understanding code without hallucination and excessive token usage. | |
| dev-mcp codeibrah/mcp A local MCP server that gives AI agents access to developer tooling — GitHub (read-only), documentation search, and web research — via stdio transport. | |
| @codeinklingon/browser-mcp codeinklingon/browser-mcp MCP server for headless browser automation via Puppeteer, with stealth anti-detection and Playwright-format ARIA snapshots. | |
| semble-mcp codeintegrity/dsh-semble Enables agents to find code by describing its behaviour rather than guessing file names, returning ranked file:line snippets that cost far fewer tokens than grep-then-read. Also surfaces neighbouring implementations, callers and tests aroun | |
| Share A Bot MCP A2A (agent2agent) Protocol codeislaw101/shareabot-mcp Discover and connect your agents with other agents via A2A protocol. Share resources for free or fee. | |
| SENTINEL codeit-ronit/sentinel A policy enforcement, audit, and evaluation control plane for LLM agents on payment infrastructure, intercepting tool calls at the MCP boundary to classify, redact, and allow/deny/escalate actions before execution. | |
| real-browser-mcp-server codeiva11/real-browser-mcp Enables AI agents to control a hardened, human-like Chromium browser for automation and testing, with ad blocking, natural mouse movements, and Cloudflare Turnstile assistance. | |
| Brave Real Browser MCP Server codeiva4u/brave-real-browser-mcp-server Enables advanced browser automation using real Brave Browser with 49 tools for web scraping, content extraction, video downloads, CAPTCHA solving, and anti-detection features. Includes automatic Brave installation, built-in ad-blocking with | |
| ios-agent-driver codejonesw/ios-agent-driver An MCP server that lets an AI agent drive the iOS Simulator in a loop, enabling tapping, typing, swiping, reading the screen via the accessibility tree, and verifying app state. | |
| suno-mcp codekeanu/suno-mcp Enables AI music generation and management through the Suno API, supporting text prompts, custom lyrics, track status monitoring, and credit management. | |
| hud codeknight314/hud Enables agents and humans to manage local tickets (projects, sub-tickets, dependencies, statuses, comments and decision requests) and monitors that track commands, HTTP endpoints, ports, certificates, cron heartbeats and probes, with thresh | |
| kuik-fileshare-mcp codekuik/kuik-agent-mcp-fileshare Enables KUIK Agent to access on-premise SMB/CIFS shares on a Windows Server using the employee's own credentials, enforcing live ACLs. Supports file operations such as list, read, write, search, move, copy, delete, and upload/download witho | |
| Weclapp MCP Server codelev/weclapp-mcp An MCP server that enables AI to manage parties (companies and individuals) in the Weclapp ERP/CRM platform. | |
| dynamic-shell-server codelion/dynamic-shell-server A Model Context Protocol (MCP) server that enables secure execution of shell commands with a dynamic approval system, audit logging, and command revocation. | |
| SendLit codelitdev/sendlit SendLit, the open-source email platform. Manage contacts, tags, broadcasts, sequences, templates, custom events and stats. | |
| passalong codellyson/passalong Enables AI coding agents to take and progress tasks, hand in completed work with evidence, and enables users to publish, search, and retrieve guides, file bugs, manage inbox/board/activity/logs, and plan tasks over MCP. | |
| Markdown Notes MCP codemaestro78/markdown-notes-mcp Enables managing and searching markdown notes with semantic search, question answering, and note generation, and provides an MCP server for GitHub Copilot integration. | |
| Advanced Unity MCP codemaestroai/advanced-unity-mcp A bridge that enables controlling Unity Editor through natural language commands via AI assistants, allowing users to create materials, build projects, manage scenes, and configure settings without manual interaction. | |
| Filesystem MCP codemaestroai/filesystem-mcp Provides secure filesystem access for AI assistants with optimizations like file reading limits and depth-limited traversal to improve token efficiency. It enables AI models to read, write, and search files within explicitly allowed directo | |
| agentboost codeman008/agentboost Provides coding agents with structured planning, persistent project memory, automated verification, and safety permission controls through MCP tools, enabling better planning, context retention, self-checking, and guarded execution. | |
| anchor-lab-ai codemastercody3d/anchor-lab-ai Enables AI agents to orchestrate multi-system LLM training, quantization, and evaluation workloads across local, Colab, Kaggle, and SSH targets, with persistent monitoring, historical analysis, and visualization via MCP tools. | |
| torch-mcp codemastercody3d/torch-mcp Provides MCP tools to validate ROMs, extract and pack N64 game assets, export code/headers, import modded assets, and render audio sequences via HarbourMasters/Torch. | |
| agentic-knowledge codemcp/knowledge An MCP server that guides AI assistants to navigate documentation using their built-in tools (grep, file reading) instead of traditional RAG. | |
| Codemend MCP Server codemend/mcp Connects AI tools directly to Codemend production error monitoring to list, analyze, and resolve software crashes. It enables users to retrieve AI-generated fixes and automatically open GitHub pull requests to address production issues. | |
| yuki-mcp codemill-solutions/yuki-mcp Connects AI agents to Yuki accounting via SOAP API, enabling management of administrations, relations, invoices, transactions, and documents through natural language. | |
| CodeMind codemind-ai/codemind An AI Security Guardian MCP server that provides real-time vulnerability scanning, secrets detection, and secure coding enforcement for AI-generated code in modern web frameworks. | |
| Search MCP Server codemk/search-mcp A Model Context Protocol (MCP) server for integrating Google Search capabilities into AI applications. | |
| CAD MCP Server codemod3/cad-mcp Enables reading, analyzing, and editing CAD files (DXF and DWG) via natural language, including entity queries, layer management, and safe copy-based edits. |
39,701–39,750 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.