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 |
|---|---|
| czid-mcp appvantagelabs2-a11y/czid-mcp Enables AI agents to look up Czech companies, VAT status, entity KYC snapshots, address standardization, and Czech identifier validation via official ARES data. | |
| FinDB Reporting MCP Server appwrite-community/finance-mcp-demo A read-only MCP server for the FinDB demo database, exposing customer, account, card, and transaction reporting tools over stateless Streamable HTTP. | |
| Recall appwrite-community/memory-mcp A remote MCP server for personal memory, enabling AI tools like Claude Code to save and search memories with user permission, built on Appwrite. | |
| TaskFlow appwrite-community/taskflow-mcp An MCP server that lets AI tools read and manage a user's tasks via Appwrite, using OAuth2 consent for secure, revocable access. | |
| Appwrite Docs MCP Server appwrite/mcp-for-docs Enables IDEs like Cursor, Windsurf, and Claude Code to access and query Appwrite documentation through a vector-powered search system. Provides developers with contextual Appwrite documentation directly within their development environment. | |
| QuantXData MCP Server appydam/quantxdata-mcp MCP server that exposes QuantXData's institutional crypto market data APIs to AI assistants, enabling natural language queries for trades, order books, OHLCV, options, and more across 120+ exchanges. | |
| context-capsule apraba05/context-capsule Allows coding agents to securely retrieve curated, sealed Slack message bundles (capsules) via MCP, with full audit and expiration controls. | |
| ecfr-cartography-mcp apraba05/ecfr-cartography-mcp An MCP server that turns the US Code of Federal Regulations into an agent-navigable citation graph, enabling traversal of regulatory references and detection of stale citations via structured tools. | |
| fastmcp-linux-desktop apravint/fastmcp-linux-desktop Enables AI agents to control Linux desktops and compositors, including Hyprland/Wayland window management, PipeWire audio routing, systemd diagnostics and self-healing, notifications, screenshots, and optional agent memory. | |
| Dakota Marketplace MCP Server aprem01/dakota-mcp-server Enables AI clients to query Dakota Marketplace data by integrating directly with Salesforce via OAuth and PKCE. Users can search and retrieve detailed profiles for fund managers, allocators, and funds while maintaining native Salesforce sec | |
| admin-mcp aprezcuba24/odoo-mcp MCP server for Odoo administration, enabling customer listing and search via connected service, resource, and tool layers. | |
| Kagi MCP Server apridachin/kagi-search-mcp Allows the use of Kagi's API for web searching and content enrichment through methods like fastgpt, enrich/web, and enrich/news. | |
| ico-mcp apriori3d/ico-mcp Enables agents to search and compose typed operators into validated, runnable pipelines, propose missing operators or types as drafts, and crystallize proven drafts into stable operators through a human-reviewed GitHub pull request. | |
| local_computer apsidd/local-computer-mcp Enables AI assistants to access files and terminal of a local computer via a public HTTPS endpoint, secured with GitHub OAuth. | |
| log-essence apsion/log-essence Enables LLMs to analyze logs by extracting patterns, redacting secrets, and providing token-efficient summaries from files, Docker containers, or journald. | |
| Trading 212 MCP apsogos4ever/mcp-server Enables MCP clients to interact with Trading 212 trading services through a stateless Cloudflare Workers endpoint. | |
| dbeaver-mcp apsolut/dbeaver-mcp Enables AI agents to query local Postgres databases through saved DBeaver Community connections, including SSH-tunnelled ones, without exposing credentials. | |
| Fathom AI MCP Server apspan/fathom-ai-mcp Exposes the Fathom AI meeting intelligence API to Claude, allowing users to list meetings, fetch transcripts, and retrieve summaries. It also enables management of teams and members through the Model Context Protocol. | |
| zhipu-vision-mcp apsuadwf/zhipu-vision-mcp Provides vision capabilities to text-only models (like DeepSeek) via Zhipu free vision models, enabling image analysis, OCR, and image comparison through natural language. | |
| Aptabase MCP Server aptabase/aptabase-mcp Enables AI agents to query Aptabase analytics through MCP, including metrics, top events, countries, sessions, and more. Uses the dashboard's cookie-authenticated endpoints, so it requires an Aptabase auth session cookie. | |
| blender-mcp apteryx-t/blender_mcp_test Enables Claude AI to interact with and control Blender for 3D modeling, scene creation, and manipulation. | |
| aptible-mcp aptible/aptible-mcp Enables interaction with the Aptible API for managing Aptible resources such as accounts, apps, and databases through natural language. | |
| runmeter aptica-solutions/a-mcp-runmeter An MCP server that provides cost and reliability observability for LLM and agent workflows. It records model calls and allows querying and aggregating telemetry data through MCP tools. | |
| Aptos NPM MCP aptos-labs/aptos-npm-mcp Enables users to manage API keys and perform Aptos Build actions through MCP-compatible interfaces like Claude and Cursor. This server facilitates development workflows on the Aptos blockchain by integrating directly with the Aptos Build pl | |
| Superset MCP Integration aptro/superset-mcp MCP server enabling AI agents to programmatically connect to and control Apache Superset instances, allowing users to manage dashboards, charts, databases, datasets, and run SQL queries through natural language interactions. | |
| Zerodha MCP Integration aptro/zerodha-mcp Integrates Zerodha's trading platform with Claude AI using the Multi-Cloud Plugin framework, allowing users to interact with their Zerodha trading account directly through Claude for stock trading and mutual fund operations. | |
| SEODesk MCP Server apurv00001/seodesk-mcp-server Exposes SEODesk SEO tools (analyze_website, keyword_research, backlink overview, etc.) to MCP clients like ChatGPT via Streamable HTTP and OAuth 2.1. | |
| memroam apurv101/memory-vault Portable AI memory that roams with you across models and harnesses — one shared memory for Claude Code, Codex, Cursor, Gemini CLI and more, stored as plain markdown files you own. Per-project spaces plus a shared layer, vault-wide search; r | |
| sarvam-tools apurv428/setu-agent An MCP server providing tools for speech-to-text, translation, language detection, question answering, and text-to-speech using Sarvam AI models, enabling multilingual voice agents. | |
| Student Assistant MCP Server apurva8255/student-assistant-mcp Enables AI assistants to calculate CGPA, view assignment deadlines, filter deadlines by subject, and search local subject notes. | |
| google-maps-mcp apurvaumredkar/google-maps-mcp A TypeScript MCP server that exposes Google Maps Platform APIs as tools for LLMs, providing real map data like directions, transit routes, place search, address validation, photos, and elevation. | |
| tenet-ui-mcp apurvkhare/tenet-ui-mcp Serves design-system context and judgment from versioned tenet-ui snapshots, letting agents query component catalogs, tokens, guidelines, and baselines while writing and checking their own code. | |
| gdocs-mcp apurwa/gdocs-mcp MCP server for Google Docs and Sheets that enables AI assistants to read, create, edit, style, export, and collaborate on documents using local OAuth authentication. | |
| APVISO MCP Server apviso/apviso-mcp Enables interaction with the APVISO AI-powered penetration testing platform to manage targets, initiate scans, and retrieve vulnerability findings. It allows developers to integrate security testing workflows directly into MCP-compatible to | |
| DaVinci Resolve MCP Server apvlv/davinci-resolve-mcp Allows AI assistants like Claude to directly interact with and control DaVinci Resolve through the Model Context Protocol, providing capabilities for project management, timeline manipulation, media management, and Fusion integration. | |
| Logseq MCP Tools apw124/logseq-mcp A Model Context Protocol server that enables AI agents to interact with local Logseq knowledge graphs, supporting operations like creating/editing pages and blocks, searching content, and managing journal entries. | |
| GitHub PR Review MCP aq35/mcp_tool An MCP server that collects Pull Request comments from private GitHub repositories, including issue comments, review comments, and review summaries. | |
| agent-memory MCP server aqa03009-ux/agent-memory Enables AI agents to search and manage a local Markdown memory vault over stdio, including hybrid search, note retrieval and addition, session handoff claiming, and status checks without holding a model in memory. | |
| ariadnet aqalalwa/ariadnet Enables MCP clients and AI agents to solve interdependent-variable domains deterministically by deriving implied values, catching contradictions, planning the smallest set of inputs to ask for, and explaining every result with provenance. | |
| Tenable OT Security MCP Server aqamahn/mcp-server-tenable-ot-v2 Connects AI clients to Tenable OT Security, exposing OT/ICS asset inventory, vulnerabilities, events, policies, and findings as read tools, with an opt-in dry-run write layer for asset edits and policy management. | |
| MySQL MCP Server aqara-docs/mysql-mcp-server Enables AI applications to interact with MySQL databases through a secure interface, allowing database exploration, querying, and analysis with proper error handling and logging. | |
| MySQL MCP Server aqaranewbiz/mysql-aqaranewbiz Enables interaction with MySQL databases through the Model Context Protocol, allowing users to execute queries, manage records, and inspect table schemas. | |
| Wixzel Voice aqeelshamz/wixzel-voice-sdks Build AI voice agents that answer and place real phone calls over your own carrier, on any voice engine (Gemini Live, Sarvam, OpenAI, ElevenLabs and more) with one API key. Create agents, connect SIP trunks and numbers, run call campaigns, | |
| securitytrails-mcp aqhmal/securitytrails-mcp Enables LLM agents to query SecurityTrails for DNS history, subdomain enumeration, WHOIS (current and historical), SSL certificates, and IPv4 intelligence via 17 read-only tools. | |
| Whatsender MCP aqibmohd271/whatsender-mcp Enables MCP-compatible AI clients to work with self-hosted, linked WhatsApp accounts by exposing eight tools for listing sessions, chats, contacts and groups, reading message history, checking numbers, inspecting account details, and sendin | |
| FastAPI + FastMCP + Gemini Integration aqibqureshi786/mcp-server-using-fast-mcp Enables natural language interaction with FastAPI applications through Google's Gemini AI using MCP tools. Provides CRUD operations for user management and application health monitoring through conversational prompts. | |
| skilljit aqibsidd/skilljit Enables on-demand discovery and loading of skills and MCP tools through a fixed set of routing tools, minimizing token overhead. | |
| Alexa+ Enterprise Hub aqillz/alexa-enterprise-hub Enables small shopkeepers to manage inventory conversationally, tracking daily burn rates, predicting stockouts and spoilage, generating supplier-grouped purchase orders, planning reorders under budget constraints, creating near-expiry clea | |
| goose-herdr aquaherd/goose-herdr Enables goose to control the Herdr terminal workspace manager, allowing AI agents to inspect and manipulate workspaces, tabs, panes, run commands, and manage agent states. | |
| veyra-bookmarks aquariosan/veyra-bookmarks Bookmark manager for AI agents with tags, categories, and full-text search. Reads are free, writes require Veyra commit mode. |
30,001–30,050 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.