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 |
|---|---|
| Google Search MCP Server calandrel/google_search_mcp Enables performing Google searches using the Custom Search Engine API with support for various parameters like date restriction, site search, and file type. Returns search results in a conversational format. | |
| mcp-mux calandrel/mcp-mux A dynamic MCP server orchestrator and multiplexer that routes requests to multiple remote and local sub-MCP servers, with hot-reload config, SSE/Streamable HTTP support, and a summary endpoint to reduce context token usage. | |
| Trafilatura MCP Server calandrel/trafilatura_mcp Enables web scraping and content extraction from URLs using the Trafilatura library. Extracts main text content and metadata (title, author, date) from web pages with configurable options for comments and tables. | |
| mcpgateway calasdan-sketch/mcpgateway Fronts many downstream MCP servers through one session, presenting a unified tool namespace with collision resolution, fleet-wide allow/deny/hide policy, per-tool rate limits, centralized audit logging, Prometheus metrics, and bearer-key au | |
| claude-bridge calasdan-sketch/monomem Exposes one SQLite-backed notes store over both stdio and an HTTPS/SSE endpoint, letting Claude Code, Claude Desktop, Claude web, and Claude mobile read and write the same shared state with full-text search. Provides write, read, search, an | |
| OneMemory calasdan-sketch/onememory-clean Enables multiple AI agents and clients to share a self-hosted memory store over MCP or REST, supporting note creation, search, change tracking, and optional semantic retrieval from desktop, web, or mobile. | |
| CalcsLive MCP Server calcslive/calcslive-mcp-server Enables AI agents to perform unit-aware engineering calculations with automatic unit conversion, dependency resolution, and access to 500+ units across 75+ categories through the CalcsLive calculation engine. | |
| finagent-mesh-mcp caldeirav/finagent-mesh-mcp Enables financial agent workflows to perform agentic retrieval over SEC filings, rank filing types and passages, and synthesize answers from evidence using MCP tools, with MLflow tracing and FinAgentBench evaluation. | |
| mcp-mrtr-devops-demo caldeirav/mcp-mrtr-devops-demo Enables stateless human-in-the-loop DevOps automation, demonstrating MCP SEP-2322 multi-round trip requests for emergency database migration authorization. | |
| Continuum calderbuild/continuum An autonomous AI showrunner for serialized vertical micro-drama that generates episodes with consistent characters and style using a series bible and multi-agent pipeline. | |
| Open Food Facts MCP Server caleb-conner/open-food-facts-mcp Enables AI assistants to access the Open Food Facts database to query detailed food product information, nutritional data, and environmental scores. Supports product lookup by barcode, smart search with filtering, nutritional analysis, prod | |
| Canvas MCP caleb-media-studio/canvas-mcp Enables MCP clients to connect to a self-hosted Canvas LMS account to read courses, assignments, grades, modules, files, discussions, announcements, and Inbox messages, and to submit work or perform teacher actions with confirmation safegua | |
| skyward-mcp caleb-media-studio/skyward-mcp Enables students and educators to connect ChatGPT, Claude, or another MCP client to the Skyward account they are already authorized to use, through a self-hosted deployment they control. It exposes read-only tools for report cards, gradeboo | |
| Twilio Call Service MCP Server caleb-overbay4/mcp-server Enables AI-driven interaction with Twilio call services, including initiating outbound calls and retrieving call history via FastMCP tools. | |
| darktable-mcp caleb68864/darktable-mcp Enables Claude to edit photos in darktable via natural language, adjusting sliders, applying styles, and organizing the library in real time through the MCP protocol. | |
| Harrier caleb68864/harrier A disciplined OSINT collection server for LLM agents that wraps free open-source reconnaissance tools behind a normalized schema, enabling automated, deterministic collection of public intelligence with confidence scoring and graceful degra | |
| mcp-server-splunk-oncall calebcall/mcp-server-splunk-oncall This server provides a full API interface for the Splunk On-Call (VictorOps) platform, allowing comprehensive interaction with incident management tools. It enables users to manage incidents, configure organizational structures, and view on | |
| hmesh-mcp calebchen941028/harness-mesh Enables a controller harness to dispatch and monitor cross-harness coding tickets with isolated worktrees, quota-aware failover, shared project context, and paged resource access through 13 tools. | |
| Memoreei calebchristiansen/memoreei An open-source MCP server that gives AI assistants a searchable memory of your entire personal communication history by ingesting messages from multiple platforms and indexing them with hybrid search. | |
| Bardo calebe/bardo An identity & continuity platform for AI agents. | |
| company-investigator-mcp calebeprates/company-investigator-mcp Enables LLM clients to investigate Brazilian companies by CNPJ or name, mapping corporate relationships and gathering structured, source-attributed public evidence from official registries, news, social profiles, judicial proceedings, and P | |
| mcp-taskflow calebgerman/mcp-taskflow A local MCP server that gives AI agents structured task planning, execution tracking, and guided research workflows. | |
| claude-duet-bridge calebgrimes/claude-duet-bridge Connect Claude Duet to Claude Code: an MCP connector that lets Duet start Claude Code sessions, talk to your open terminal windows, and get answers back. Remote MCP server on Cloudflare Workers + a Claude Code channel. | |
| YNAB MCP Server calebl/ynab-mcp-server A Model Context Protocol server that enables AI-powered interaction with YNAB (You Need A Budget) data, allowing users to query their budgets through conversational interfaces. | |
| file-system-mcp-server calebmwelsh/file-system-mcp-server A comprehensive MCP (Model Context Protocol) server for file system operations, providing Claude and other AI assistants with access to local files and directories. | |
| Podcast MCP calebn/sharecut-studio Enables podcast producers and agents to manage multitrack projects, run per-track transcription, perform transcript-driven edits, process audio via FFmpeg, and inspect a read-only DAW timeline over MCP. | |
| Atlas UI calebsjames/atlas-ui-mcp MCP server that gives Claude deep awareness of your frontend codebase by scanning components, hooks, services, routes, and data flow for React or Vue projects. | |
| OrdiscanMCP calel33/ordiscan-mcp-v1 An HTTP server implementation that provides direct access to the Ordiscan API with 29 integrated tools for Bitcoin ordinals, inscriptions, runes, BRC-20 tokens, and rare sat data. | |
| ssh-mcp-dynamic calevi-consulting/ssh-mcp-dynamic A minimal MCP server that lets an MCP client run shell commands on remote hosts over SSH, with host, key, user, and port chosen per call. | |
| Poke PC calganaygun/poke-pc Provides a Dockerized MCP worker that gives Poke AI assistants persistent terminal control and filesystem access on your machine, with automatic tunnel connection and optional command notifications. | |
| curl-mcp calibress/curl-mcp Provides a structured HTTP client tool for making web requests with full HTTP method support, detailed response metadata, and error handling. Enables AI assistants to interact with any web API or endpoint through the curl_request tool. | |
| Memtech MCP Server california-memtech/mcp MCP server that enables AI assistants to semantically search Memtech's memory-ASIC engineering knowledge base (RTL, lab logs, DFM rules) stored in a Qdrant vector database. | |
| CloudDesk MCP Server calinrus-dev/clouddesk Enables MCP-compatible AI agents to browse, search, transfer, organize, pause, resume, and cancel files and folders across O2, Drive, OneDrive, and Google Photos accounts using the same local service and transfer queue as the desktop app. | |
| Github Copilot VScode MCP Server calisweetleaf/mcp A server that likely facilitates integration between GitHub Copilot and Visual Studio Code, though the README lacks specific details about its functionality. | |
| x402-image-api calivvvv/x402-image-api Enables coding agents to generate AI images directly through MCP tools, handling payment via the x402 protocol with USDC on Base and no API keys. | |
| feedbin-mcp calk16/feedbin-mcp Enables MCP clients to authenticate with Feedbin, poll unread articles, fetch and cache full entry bodies in SQLite, and list or retrieve cached entries through the Feedbin v2 API. | |
| McpEye 智守 call123x/mcpeye-zhishou A Linux server inspection MCP system that allows managing servers via web backend, performing SSH-based health checks, and querying server status through natural language. | |
| server-monitor-mcp call123x/server-monitor-mcp Server Monitor MCP is a Linux server inspection service with web backend and MCP interface. It allows you to manage SSH hosts and query server metrics via natural language. | |
| MCP-Airflow-API call518/mcp-airflow-api Monitor and manage Apache Airflow clusters through natural language queries via MCP tools: DAG inspection, task monitoring, health checks, and cluster analytics without API complexity.
* Guide: https://call518.medium.com/mcp-airflow-api-a- | |
| MCP-Ambari-API call518/mcp-ambari-api Manage and monitor Hadoop clusters via Apache Ambari API, enabling service operations, configuration changes, status checks, and request tracking through a unified MCP interface for simplified administration.
* Guide: https://call518.mediu | |
| MCP-OpenStack-Ops call518/mcp-openstack-ops A comprehensive MCP server providing OpenStack project management and monitoring capabilities with built-in safety controls and single-project scope. | |
| MCP PostgreSQL Operations call518/mcp-postgresql-ops Enables comprehensive PostgreSQL database monitoring, analysis, and management through natural language queries. Provides performance insights, bloat analysis, vacuum monitoring, and intelligent maintenance recommendations across PostgreSQL | |
| FA-Technician-Brain-MCP callen-assetworks/fa-technician-brain-mcp Provides structured knowledge about the Technician Portal module in FleetFocus FA/EAM, enabling AI agents to query pages, workflows, APIs, and more without live connections. | |
| CallHub callhub/callhub-mcp CallHub MCP is a Python-based tool that allows you to interact with the CallHub API through Claude. This tool provides a comprehensive set of functions for managing contacts, phonebooks, agents, teams, campaigns, and other CallHub resources | |
| Remote MCP Server Authless callie84/remote-mcp-server-authless Enables deploying a remote MCP server without authentication on Cloudflare Workers, and connecting to it from Cloudflare AI Playground or Claude Desktop. | |
| mcp-tudu callipog/mcp-tudu MCP server that lets AI assistants create projects, epics, and tasks in the TuDu app through natural conversation. It securely connects over local HTTP with token authentication and requires on-screen confirmation before writing anything. | |
| @callirra/mcp callirra-ai/mcp Enables MCP-compatible agents to discover models, generate images and videos, use Prompt Studio, upload references, poll tasks, and check balances via the Callirra API. | |
| nous-portal-mcp callisto-syn/nous-portal-mcp Portable, read-only MCP server for Nous Portal capabilities, providing configuration status, route derivation, and OAuth device code authentication without invoking paid tools. | |
| discord-mcp callmegautam/discord-mcp Lets an AI assistant inspect a Discord server through your own bot, exposing read-only tools for guilds, channels, roles, and members. | |
| site-kg callmehfk/site-kg Turns any website URL into a crawled markdown corpus and knowledge graph, then exposes it to AI agents over MCP. Enables full-text search, full page retrieval, subgraph neighbor expansion, and site statistics so agents can answer questions |
36,501–36,550 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.