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 |
|---|---|
| random-mcp chrhyne/random-mcp Enables LLMs like Claude to generate genuine random numbers instead of inventing them, covering dice rolls, coin flips, number draws, random selection from lists, and shuffling. It runs as a free-tier Cloudflare Worker using a cryptographic | |
| git-txd chrihop/git-txd Enables AI agents to queue, commit, push, and track durable Git transactions through a shared daemon, preserving other agents' unstaged work and allowing recovery by request ID. | |
| clipforge chriphil70/clipforge-mcp-setup Media processing server for video trimming, MP3 audio extraction, watermarking, and 9:16 vertical re-framing via Apify Actor (budding_retrograde/clipforge). | |
| smart-router chris-asmussen/warden A single MCP server that fronts many downstream MCP servers and Skills, exposing only four tools (search, call_tool, use_skill, admin) so that an agent's context window only ever sees search results on demand. | |
| cPanel WordPress MCP chris-bangmedia/cpanel-mcp Enables managing cPanel accounts including subdomains, files, and WordPress installations via Softaculous from Claude Code using natural language. | |
| code-index chris-carruthers/code-index Enables coding agents to query a local AST-backed index of every git checkout on disk for definitions, callers, references, outlines, imports, and full-text symbol search, returning exact repo/path:line citations in milliseconds. Also suppo | |
| agent-kit chris-dare-dev/agent-kit A provider-neutral MCP server that provides tools for managing skills, agents, references, and artifact memory in a local workspace. | |
| InDesign MCP Server chris-enea/indesign-mcp Enables text manipulation in Adobe InDesign documents via Claude Desktop by providing tools to add, update, remove, and retrieve text content through ExtendScript API. | |
| Remote MCP Server chris-enea/remote-mcp-flodesk2 A Cloudflare Workers-based MCP server that enables deployment of custom tools accessible via the Model Context Protocol without authentication requirements. | |
| py-todoist-mcp chris-jelly/py-todoist-mcp A Python MCP server that enables AI assistants to manage Todoist tasks and projects through the Model Context Protocol. It supports full CRUD operations for tasks and projects, including support for nested projects and Todoist's advanced fi | |
| Role-Specific Context MCP Server chris-june/mcp-server A Model Context Protocol server that enables role-based context management for AI agents, allowing users to establish specific instructions, maintain partitioned memory, and adapt tone for different agent roles in their system. | |
| MCP-Server-Python chris-june/mcp-server-python A sophisticated AI-powered server providing intelligent, context-aware conversational capabilities with role-based advisors, semantic memory, multi-LLM support, and web browsing. | |
| GitLab MCP Server chris-miaskowski/custom-gitlab-mcp-server A custom server implementation that allows AI assistants to interact with GitLab repositories, providing capabilities for searching, fetching files, creating/updating content, and managing issues and merge requests. | |
| mcp-geo chris-page-gov/mcp-geo A research MCP server for UK geospatial and statistical data, enabling AI assistants to query Ordnance Survey and ONS datasets. | |
| okf-ons chris-page-gov/okf-ons Enables discovery and selection of ONS datasets using a frozen metadata bundle, providing bounded access to dataset descriptions, dimensions, and alternatives without making network calls or returning observation values. | |
| commonroom-mcp chris-trag/commonroom-mcp MCP server for integrating Common Room API with Amazon Q CLI and Claude Code, enabling management of activities, segments, and organizations through natural language queries. | |
| pkg-peep chris-trag/pkg-peep Enables querying NPM package download statistics, metadata, and dependency information through natural language. | |
| retail-ops-mcp-kit chris-youngblut-solutions/retail-ops-mcp-kit Provides four MCP servers for retail/CPG operations (ERP, supplier network, email, spreadsheet) with a staged-write safety model that requires human approval for all mutations. | |
| pihole-mcp chris2ao/pihole-mcp An MCP server for managing Pi-hole v6 DNS filtering and ad-blocking. It provides tools for monitoring statistics, controlling blocking, managing domain lists, and performing maintenance operations through a unified interface. | |
| ble-toy-mcp-starter chris30001220/ble-toy-mcp-starter An open-source tutorial and safe code skeleton that enables users to control their own BLE devices from ChatGPT via MCP and Secure MCP Tunnel. | |
| Yahoo Fantasy Baseball MCP chrisarrington/yahoo-fantasy-baseball-mcp Connects Claude to your Yahoo Fantasy Baseball team, enabling lineup management, roster analysis, and free agent scouting through natural conversation. | |
| remote-mcp-server-authless chrisatkinsva/remote-mcp-server-authless A stateless remote MCP server for Cloudflare Workers that requires no authentication, supports custom tool registration, and can connect to clients like Claude Desktop and Cloudflare AI Playground. | |
| MCP Server Template for Cursor IDE chrisboden/mcp_template A simple template for creating custom tools for Cursor IDE using Model Context Protocol, deployable via Heroku, Docker, or directly within Cursor IDE. | |
| OpenCart MCP Server chrisbray85/opencart-mcp Query and edit your OpenCart store from Claude Code. Products, orders, customers, Journal3 modules, SEO URLs, CMS pages — 36 tools, all through natural language. | |
| greenroom chrisbrickey/greenroom An entertainment recommender MCP server that integrates with TMDB to help agents discover films and television shows based on genre, release year, and language. It also includes utilities for comparing multi-agent LLM responses and analyzin | |
| UK Parliament MCP Server chrisbrooksbank/uk-parliament-data-mcp An MCP server that gives AI assistants access to UK Parliament data. Query MPs, Lords, bills, votes, committees, debates, and more through AI assistants like Claude Desktop and VS Code Copilot. | |
| dreamhost-mcp chrisbuildsonline/dreamhost-mcp MCP server for the DreamHost API that enables DNS management (list, add, remove records) and API metacommands. | |
| Game Night chrisbuildsonline/game-night Enables screen-free family play through a voice assistant by secretly generating a solvable whodunnit set in the household's own named rooms, or locking in a yes/no guessing target, and revealing answers only through governed tools. Keeps e | |
| Field Browser Bridge chrisbutler4701-dotcom/agent-browser-bridge Enables AI agents such as Claude, Codex, and ChatGPT to read and control a user's real Chrome browser through a self-hosted MCP broker, with scoped permissions and approval required before final actions. | |
| Ordnance Survey MCP Server chriscarlon/os-mcp A Python-based MCP server that provides access to Ordnance Survey APIs, allowing querying of geographic data through a standardized protocol with features like collection management, feature search, and spatial filtering. | |
| taskqueue-mcp chriscarrollsmith/taskqueue-mcp MCP server for "taming the Claude" with structured task queues. | |
| Switchboard chrischabot/agent-switchboard Enables local discovery, reading, and messaging between running Codex and Claude Code sessions through MCP. | |
| Security Scan MCP Server chrischabot/security-scan-mcp An MCP server that provides CVE-driven security prompts for code review, enabling coding agents to get actionable security checks based on real vulnerabilities. | |
| bridge-probe-mcp chrischall/bridge-probe-mcp Diagnostic MCP server that provides a single tool to fetch a fixed 5 MiB ASCII payload through the browser bridge and report received byte count, truncation, and elapsed time, enabling verification that large responses survive the hosted br | |
| gogcli-mcp chrischall/gogcli-mcp MCP server that gives Claude natural-language access to Google Workspace (Sheets, Docs, Gmail, Calendar, Drive, Tasks, Contacts) via gogcli. | |
| databricks-mcp chrischotw/databricks-mcp A read-only MCP server that enables users to query Databricks SQL, browse metadata, and monitor Delta Lake tables. It also supports tracking Databricks Jobs, DLT Pipelines, and cluster metrics through natural language interfaces. | |
| 1Password-enabled MySQL MCP Server chrisdail/mcp-mysql-1password-server Provides secure MySQL database access using credentials stored in 1Password, enabling AI assistants to query MySQL databases without exposing passwords. | |
| golf-reports chrisdecali/golf-reports Pulls golf data from Arccos, GHIN, and 18Birdies, and generates interactive HTML and PDF round reports with shot maps and stats via local MCP tools. | |
| daggerheart-ai chrisdhanaraj/daggerheart-mcp MCP server for semantic search over the Daggerheart SRD, enabling users to search rules, fetch entries, and query bestiary monsters during DnD session prep. | |
| pd-mcp chrisdonahue/pure-data-mcp Enables agentic interaction with vanilla Pure Data by providing tools for live patch creation, inspection, and manipulation via an MCP server that synchronizes with a Pd bridge patch. | |
| Jules MCP Server chrisgreenx-ctrl/jules-mcp-server-smithery-test Enables AI assistants to interact with Google's Jules coding agent API for autonomous coding tasks, allowing users to delegate bug fixes, refactoring, testing, and feature development with scheduling capabilities and human-in-the-loop appro | |
| Serena chrisgreenx-ctrl/serena A coding agent toolkit that provides IDE-like semantic code retrieval and editing tools, enabling LLMs to efficiently navigate and modify codebases at the symbol level rather than working with entire files. | |
| paperless-mcp chrisguidry/paperless-mcp A read-only MCP server for your paperless-ngx document archive that lets an AI assistant search documents by full text, tags, correspondents, and dates, and read the text of any document. | |
| YNAB MCP Server chrisguidry/you-need-an-mcp An MCP server that provides Large Language Models with access to YNAB (You Need A Budget) budgets, allowing them to fetch budget data including accounts, categories, and category groups. | |
| LocalData MCP Server chrisgve/localdata-mcp Gives LLM agents access to local and remote data via databases, files, graphs, and structured documents, along with a full data science toolkit for analysis and modeling. | |
| SOLVE-IT Workflow MCP Server chrishargreaves/mcp_solveit-workflows Enables Claude Desktop and Claude Code to build, update, inspect, validate and compile workflows for the SOLVE-IT Workflow Builder from natural language, automatically laying out nodes and connections and checking them against the SOLVE-IT | |
| searchconsole-mcp chrishart0/searchconsole-mcp Provides read-only access to Google Search Console data, allowing AI assistants to query site performance metrics like keywords, clicks, and rankings using natural language. It supports listing verified properties, querying search analytics | |
| chuk-mcp-code-raptor chrishayuk/chuk-mcp-code-raptor Deep code intelligence for MCP — an MCP server that gives AI agents semantic understanding of codebases via RAPTOR hierarchical indexing and code property graphs. | |
| Chuk Design System chrishayuk/chuk-mcp-design-system Provides access to a universal design token system with 7 pre-built themes (colors, typography, spacing, motion) and multi-format export capabilities for Canva, Remotion, PPTX, CSS, and W3C JSON. | |
| iOS Device Control MCP Server chrishayuk/chuk-mcp-ios-simulator Enables comprehensive control of iOS simulators and real devices through AI assistants, supporting app management, UI automation, screenshots, media operations, and location simulation for iOS development and testing workflows. |
38,601–38,650 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.