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 |
|---|---|
| ComputeGauge MCP computegauge/mcp Provides cost intelligence and a reputation scoring system to help AI agents optimize spending through smart model selection and local-to-cloud routing. It enables real-time cost tracking and rewards agents for making efficient, high-credib | |
| claude-delegate-local-mcp computersaysnull/claude-delegate-local-mcp Enables Claude Code to hand off bulk, mechanical, read-heavy tasks to a local model, including agentic loops that can read, write, and run commands sandboxed at zero cloud token cost. | |
| MCP-BOE computingvictor/mcp-boe Enables LLMs like Claude to query the official Spanish BOE API for consolidated legislation, daily summaries, and auxiliary government tables. | |
| CENDOJ MCP Server computingvictor/mcp-cendoj Enables users to search Spanish judicial rulings and extract text from resolutions using natural language queries. | |
| Prometheus Alertmanager MCP Server comqx/alertmanager-mcp Enables interaction with Prometheus Alertmanager to retrieve, filter, and manage alerts and silences through natural language commands in Claude AI. | |
| fortnox-automation-mcp comr4d3b451l/fortnox-automation-mcp Enables MCP clients to read Fortnox invoices and customers, validate receipts, and optionally perform approved write operations with strict safety controls. | |
| Beit-MCP comrade-e/beit-mcp Local MCP server that indexes documentation from URLs/files into a vector database, enabling coding agents to search and use up-to-date library and API documentation. | |
| open-greenhouse-mcp comradery64/open-greenhouse-mcp Production-ready MCP server for Greenhouse ATS that provides comprehensive recruitment tools—screening, pipeline analytics, search, and safe write operations—across read-only, recruiter, and full profiles. | |
| counterparty-credit comtechai/counterparty-credit An MCP server that scores the credit health of public energy companies using public data, providing a 0-100 score and factor breakdown. Enables agents to assess financial soundness of utilities, generators, and energy marketers. | |
| Action1 MCP Server comtom777/action1-mcp-server Enables AI assistants to query an Action1 RMM tenant for organizations, endpoints, groups, missing updates, vulnerabilities, automations, reports, users, and roles, and to build custom PowerShell-based reports whose results can be requeryed | |
| YouTube Ultimate Toolkit MCP comzee/youtube-ultimate-toolkit-mcp A comprehensive MCP server that provides Claude AI with full access to YouTube content, including searchable transcripts, metadata, comments, and playlists. It uniquely supports capturing video screenshots and extracting audio clips for ana | |
| UK Infrastructure and Ground Data MCP cona8888/uk-data-mcp-servers Enables discovery and querying of UK public data for infrastructure, geology, and preliminary ground investigations, including boreholes, environmental monitoring, planning, mapping, and traffic, plus cited desk studies and ground-investiga | |
| Cloudflare Remote MCP Server (Authless) conacts/remote-mcp-server-authless-v0 A deployable Model Context Protocol server for Cloudflare Workers that enables AI models to use custom tools without requiring authentication. | |
| mcp-legal-ar conaedivulgacion-lab/legal Unifies 14 Argentine legal connectors (JUBA, SCBA, CSJN, SAIJ, PJN Jurisprudencia, BORA, BOPBA, InfoLEG, Normativa PBA, PTN, TFN, PJN Consulta, Portal PJN, JusCABA) into a single MCP server for Claude Desktop, enabling local, read-only acce | |
| mcp-nrepl conao3/python-mcp-nrepl Connects to nREPL servers to evaluate Clojure code interactively, enabling AI assistants like Claude to run Clojure code in real-time. | |
| mcp-uuid conao3/python-mcp-uuid A Model Context Protocol server that generates random UUIDs (v4) for MCP-compatible clients like Claude Desktop. | |
| yandex-messenger-mcp conarti/yandex-messenger-mcp MCP server for Yandex Messenger that enables reading chats, searching, downloading attachments, and sending messages via agent, using a web session with Playwright and a reverse-engineered protocol. | |
| App Store Connect MCP Server concavegit/app-store-connect-mcp-server Enables interaction with Apple's App Store Connect API through natural language to manage apps, beta testing, localizations, analytics, sales reports, and CI/CD workflows for iOS and macOS development. | |
| v0-mcp-ts conce-ai/v0.dev MCP server that bridges design and code by generating UI components, layouts, and themes from text prompts using v0.dev, with features like code refactoring and accessibility auditing. | |
| clair concensure/clair-mcp-server An MCP server that reduces token usage by lazily loading skills and tools only when needed, and routing repetitive subtasks to ML backends instead of the LLM. | |
| reaper-dev-mcp conceptual-machines/reaper-dev-mcp Provides reference documentation for REAPER development, including ReaScript API, JSFX programming, and ReaWrap API, with tools to search and query function information to prevent redundant token usage. | |
| tracktion-engine-mcp conceptual-machines/tracktion-engine-mcp Enables AI assistants to search and retrieve detailed documentation for Tracktion Engine classes and APIs. | |
| CommLab Agent conchlikewater/commlab-agent Enables agents to conduct evidence-driven communication experiments (BPSK/QPSK + AWGN) through Sionna-based probes, statistical verification, and controlled diagnosis via MCP tools. | |
| Concrete CMS MCP Server concrete5-community/concretecms-mcp-server Enables interaction with Concrete CMS sites through the Concrete CMS REST API, allowing content management, user operations, and file uploads via natural language. | |
| forge-mcp concurrence-hq/forge-mcp Prototype MCP server enabling coding agents to manage Amigo Agent Forge operations, including org credentials, entity configurations, conversation simulations, and version sets. | |
| mcp-email-server concurrent2024/mcp-email-server Enables sending and receiving email over generic IMAP and SMTP, with tools for searching, reading, drafting, attaching files, managing folders, and waiting for new messages. | |
| conda-meta-mcp conda-incubator/conda-meta-mcp An MCP server that exposes authoritative, read-only Conda ecosystem metadata for AI agents, enabling package search, dependency resolution, and other packaging queries without side effects. | |
| garmin-claude-mcp condecodecycl/garmin-claude-mcp Enables Claude to read recent activities and wellness data, then design, create, update, and delete structured workouts that sync through intervals.icu to Garmin Connect and the user's watch. | |
| clockify-mcp-server condensetech/clockify-mcp-server Enables logging time entries to Clockify via LLM agents, supporting bulk creation, project lookup by name, and local timezone handling. A local stdio MCP server that converts natural language time requests into Clockify API calls. | |
| iterm-mcp condorcommodore/iterm-mcp An MCP server that exposes iTerm2 tab control as native tools, designed for the conductor pattern where one Claude/Codex session drives sibling tabs. | |
| linkedin-local-mcp condr-at/linkedin-local-mcp Enables local-only use of LinkedIn's official API to authenticate via OAuth, publish text posts, and read or reply to comments with explicit confirmation. Keeps access tokens in the OS keychain and avoids scraping or browser automation. | |
| Conductor MCP Server conductor-oss/conductor-mcp Enables AI agents to create, execute, and analyze workflows on a Conductor instance through natural language. | |
| Nano-Banana-MCP conechoai/nano-banana-mcp A Nano Banana MCP server, which you can integrate to cursor/claude code and any mcp client | |
| Nchan MCP Transport conechoai/nchan-mcp-transport A high-performance WebSocket/SSE transport layer and gateway for Anthropic's MCP, enabling real-time, scalable AI integrations with LLM agents like Claude. | |
| Redshift MCP Server conectcardata/redshift-mcp Enables LLMs and AI agents to securely query and interact with Amazon Redshift databases with configurable access modes (readonly, readwrite, admin) for safe data exploration and management. | |
| Conekta MCP Server conekta/mcp-server Enables interaction with the Conekta payment API to manage orders, customers, subscriptions, and financial transactions. It provides a comprehensive suite of tools for core payment operations like processing refunds, creating checkouts, and | |
| redash-mcp-server conekta/redash-mcp-server Enables querying and managing Redash data sources, queries, dashboards, alerts, and users through the Model Context Protocol. | |
| MindMeister MCP Server conexaoarteiro/mindmeister-mcp Connects Claude to the MindMeister API v2, enabling AI-powered mind map management including viewing, listing, exporting, and sharing maps directly from Claude. | |
| junos-mcp-server conexon-connect/junos-mcp-server Enables MCP-compatible clients such as Claude Desktop to interact with Juniper Junos network devices, exposing tools for running operational commands, applying and committing configuration changes with guardrails, and managing device connec | |
| MCP Mortgage Server confersolutions/mcp-mortgage-server Enables AI assistants to parse and analyze mortgage documents (Loan Estimates & Closing Disclosures), converting them into structured MISMO-compliant JSON and checking for TRID compliance violations. | |
| AgentStore confidantduk/agentstore Provides agent-scoped persistent storage with namespace isolation and TTL-based retention tiers. Includes a full audit trail and is backed by a single SQLite file. | |
| Confident AI confident-ai/confident-mcp-server Connects AI-powered tools to the Confident AI platform for evaluating, observing, and iterating on AI quality, enabling cloud evaluations, dataset management, prompt versioning, production tracing, and human annotations directly from editor | |
| jev-ultrafast-mcp confident-christmasfactor2015/jev-ultrafast-mcp Enables completing entire browser tasks in a single tool call, automatically handling clicks, typing, navigation, and page verification without step-by-step instructions. | |
| confirm-mcp confirm-ai/confirm-mcp Provides a human-approval tool for MCP-compatible agents, pausing execution until a human approves or edits the action, with every decision logged. | |
| conformi-search conformi-eu/conformi-search-mcp Installable MCP server for EU legal research with verifiable CELEX citations from the EUR-Lex corpus (DE/EN/FR). | |
| LinkedIn Ad Library MCP Server confortistefano/linkedin-ads-library-mcp Enables AI assistants to search LinkedIn's Ad Library for sponsored ads, job postings, and paid endorsements, providing insights into competitor strategies and hiring signals. | |
| failure-memory congbao/failure-memory Failure Memory provides AI coding agents with a shared local memory of failures, enabling them to record, recall, and learn from mistakes across sessions. | |
| plurk-mcp congcongfu/plurk-mcp A secure Model Context Protocol server for interacting with Plurk, allowing agents to read account context, post updates, and manage replies. It includes built-in safety guardrails such as daily post limits and reply cooldowns to ensure con | |
| MCP PostgreSQL Secure Query Server congdinh2008/chatbot-ai-mcp-demo Provides secure, read-only PostgreSQL database access via MCP tools like query_inventory and get_top_sales. Blocks dangerous SQL commands while allowing AI to execute controlled SELECT queries. | |
| mlx-serve-mcp congenital/mlx-serve-mcp Enables MCP clients to generate images, speech, music, video, and 3D meshes via a remote mlx-serve instance on Apple Silicon. |
40,151–40,200 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.