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 |
|---|---|
| AUX brian-mwirigi/aux-mcp An MCP server that turns your AI into a Spotify DJ, enabling mood-based playback, auto-DJ, party rooms, and playlist roasting. | |
| cobble-mcp brian-mwirigi/cobble-mcp Enables AI assistants to connect to Minecraft servers as a bot, allowing cooperative building, movement, combat, and chat in the same world. | |
| ptlab brian-mwirigi/packet-tracer-mcp Enables headless creation, parsing, and grading of Cisco Packet Tracer .pkt/.pka lab files, including CCNA activity scoring, through MCP tools without requiring Packet Tracer to run. | |
| @mcp-apps/streamable-ui-kit brian-mwirigi/streamable-ui-kit Enables developers to host an MCP server over Streamable HTTP on Node with corrected response framing, client elicitation capability reporting, and lightweight SSE parsing for progress and mid-stream elicitation events. | |
| model-routing brian-plummer/model-routing Routes subagent tasks across Claude and OpenAI lanes by task kind and quota state, deciding whether to spawn a single model, run a duel of both vendors, or run both and ship the merge. It records duels with attested proof-of-run session ids | |
| Dependency Security MCP brian03021/mcp-cve-scan Enables asynchronous OWASP Dependency-Check vulnerability scanning of allowlisted repositories via three narrow tools for starting scans, checking status, and retrieving structured findings. | |
| MCP Knowledge Bridge brian20040323/mcp-knowledge-bridge MCP-compatible knowledge bridge with tools, resources, prompts, local BM25 KB, and a token-guarded HTTP companion for Cursor and custom agents. | |
| Bitbucket MCP brian54825/bitbucket-mcp Enables AI assistants to work with Bitbucket Cloud and Server through authenticated REST API access, including listing and inspecting repositories and fetching or creating pull requests with pagination controls. Read-only by default, with o | |
| benepass-mcp brian7989/benepass-mcp Enables read-only access to Benepass employee-web API, allowing users to view HSA accounts, investments, transactions, documents, and benefits without write operations. | |
| Health Coach MCP brian7989/fitness-mcp A personal health and fitness MCP server that provides tools for managing profile data, goals, body measurements, nutrition, workouts, sleep, check-ins, life events, analytics, and coach memories via Supabase Postgres. | |
| AWS FinOps MCP Server brianandre60341/aws-finops-mcp-server Enables users to query and analyze AWS cloud costs, audit accounts for wasted resources, and check budget status through natural language across multiple profiles and regions. Runs locally using existing AWS CLI credentials, so sensitive ke | |
| FHIR MCP Server brianbastian01/fhir-mcp-server Provides safe read-only access to synthetic healthcare data via FHIR R4, enabling AI assistants to search patients, retrieve vitals, and summarize conditions using a public sandbox. | |
| keepsake brianbolze/keepsake Enables agents to search a local saved-post library with keyword, semantic, and deep queries, retrieve individual records by ID, and inspect status through stdio MCP tools. | |
| Charity MCP Server briancasteel/charity-mcp-server Enables AI assistants to look up IRS nonprofit data, verify tax-deductible charity status, and search for organizations by name or location using the CharityAPI database. | |
| memory-mcp brianchilders/memory-mcp Multi-tier memory system for AI assistants, integrating semantic, episodic, time-series, and spatial memory with pattern detection and MCP tools. | |
| hol-lsp-mcp briancmlee/hol-lsp-mcp Enables coding agents to drive HOL4's built-in hol lsp language server against individual SML script files, exposing proof diagnostics, goal states, evaluation, hover, definitions, symbols and completions as concise text tools. It manages s | |
| Bruno MCP Server brianconway/bruno-mcp Enables API development directly from MCP clients by creating and editing collections, running requests through the real CLI, generating documentation, and starting mock servers. | |
| dev-tools briancox730/dev-tools-mcp Enables coding agents to run Playwright e2e tests, validate Supabase RLS policies with role-based SQL, typecheck TypeScript, execute npm scripts with parsed test output, and validate Next.js builds, all through a structured MCP interface. | |
| Sharepoint MCP Server briancusack/mcpsharepoint Provides access to organizational Sharepoint documents through the Microsoft Graph API, enabling search and retrieval of Sharepoint content for AI assistants. | |
| io.github.morluto/flameox briandabrowski64376/flameox Enables coding agents to turn explicit artifacts or commands into bounded local runtime evidence from profilers, benchmarks, trace processors, and direct targets, with typed provenance, coverage, and optional durable preservation. It expose | |
| daqmx-mcp briandavidcouch/daqmx-mcp A safety-bounded MCP server for discovering data-acquisition devices and performing finite analog-voltage and digital-input reads through NI's nidaqmx Python package. | |
| codex-in-claude briandconnelly/codex-in-claude Call OpenAI Codex from Claude Code for independent second opinions, structured code review, and delegated coding tasks through a FastMCP plugin that drives the codex CLI safely. | |
| moonbridge briandconnelly/moonbridge Enables compatible MCP clients to invoke Kimi Code for second opinions, code reviews, and delegated coding tasks with structured results. | |
| opendata-atlas briandconnelly/opendata-atlas Lets AI assistants discover public Socrata open-data portals, search their datasets, inspect schemas, and run bounded read-only SoQL queries to answer questions with live government data. All access is strictly read-only and results come st | |
| orb-cloud-mcp briandconnelly/orb-cloud-mcp Enables Orb Cloud device management, including listing organizations and devices, retrieving telemetry, triggering speed tests, and configuring temporary data push through natural language. | |
| seattle-open-data briandconnelly/seattle-open-data Enables agents to discover, inspect, and query municipal open datasets from data.seattle.gov through Socrata SODA2, with bounded reads, aggregates, and reference guidance. | |
| azure-utils-mcp briandeacon/azure-utils-mcp An MCP server for Azure development and operations, enabling Cosmos DB queries, Service Bus messaging, and PIM role activation. | |
| cosmosdb-mcp briandeacon/cosmosdb-mcp MCP server for Azure Cosmos DB enabling listing accounts, databases, containers, running SQL queries, and reading/writing/deleting documents. | |
| Azure Service Bus MCP Server briandeacon/servicebus-mcp MCP server for Azure Service Bus that enables sending messages, inspecting queues and subscriptions, and purging test data. Complements the built-in Azure MCP server by adding write operations. | |
| Bluesky MCP Server brianellin/bsky-mcp-server A Model Context Protocol server that enables AI assistants to interact with Bluesky/ATProtocol, providing authentication, timeline access, post creation, and social features like likes and follows. | |
| X Search One brianference/x-search-one MCP server that enables searching X (Twitter) via the X API v2, with tools, security model, and install documentation. | |
| ComfyUI MCP Server briangan/comfyui-mcp-server Enables MCP clients to connect to and interact with ComfyUI for workflow execution and image generation. | |
| api-mock-sandbox briangtrxx/api-mock-sandbox Enables Claude to create local, persistent mock REST APIs on demand from plain-language descriptions, with data written to disk so it survives restarts. | |
| nvim-mcp-server brianhuster/nvim-mcp-server A Model Context Protocol server for Neovim that provides LSP-based symbol tools, enabling AI language models to perform code analysis and manipulation such as symbol lookup, renaming, and body replacement via Neovim's built-in LSP. | |
| gedcom-mcp brianjbeach/gedcom-mcp-server Reads and searches GEDCOM 5.5.1 files, enabling AI agents to look up individuals, families, sources, and multimedia references in a family tree. | |
| airflow-dev-mcp brianlondon/airflow-dev-mcp An MCP server that enables AI coding assistants to interact with a local Airflow cluster via its REST API for triggering DAG runs, monitoring status, reading logs, and diagnosing errors. | |
| ai-mcp-server brianmacao/ai-mcp-server A local MCP bridge that registers multiple AI API endpoints, enabling agents to automatically discover and route to models based on capabilities like chat, vision, reasoning, embedding, image generation, TTS, STT, and rerank. | |
| Fusion BIP MCP Server brianmakarewicz/fusion-bip-mcp-server MCP server for Oracle Fusion BI Publisher that lets AI agents run queries, reports, and manage catalog objects via a secure, scoped interface. | |
| RecallForge brianmeyer/recallforge Local-first MCP server enabling cross-modal search across text, images, documents, video, and audio transcripts. Provides 26 tools for ingesting, searching, and navigating local file systems with a 3-stage pipeline including reranking. | |
| dhis2-mcp brianmituka/dhis2-mcp Enables read-only interaction with DHIS2 health data by searching indicators and querying compact analytics results, designed for small local models. | |
| mcp-gdrive-cf brianmoney/mcp-gdrive-cf Remote MCP server for Google Drive and Sheets running on Cloudflare Workers, providing 11 tools for file and sheet operations with full OAuth 2.0 and PKCE support for secure authentication. | |
| Aurea Orchestrator MCP brianmontero18/dev-mcp-tools Production-ready MCP server for enforcing git/PR/Jira workflows with atomic, composable tools. Enables automated branch creation, conventional commits, PR generation, and Jira ticket operations with safety guardrails. | |
| Windows AppShots brianmulder/windows-appshots MCP server that captures a Windows application's pixels and bounded UI Automation tree with provider-exposed text for Codex inspection. It supports capture, listing, retrieval, and watcher control commands. | |
| GIS MCP Server briannag1692/gis-mcp-server Enables AI assistants to perform geospatial analysis, spatial data processing, vector and raster operations, coordinate transformations, spatial statistics, mapping, and access to climate, satellite, and other geospatial data through MCP-co | |
| withings-mcp brianokelly1/withings-mcp Read access to Withings scale data, including weight and body composition metrics, through a local MCP server. | |
| mcp-developer-portal brianpelow/mcp-developer-portal MCP server wrapping Backstage — query service catalog, fetch TechDocs, and scaffold services via AI agents. | |
| mcp-evidence-ledger brianpelow/mcp-evidence-ledger An MCP server providing an append-only, hash-chained evidence ledger for agent actions, where every record is a tamper-evident receipt cryptographically bound to all prior records and persisted as human-readable JSONL local state. It expose | |
| mcp-app-ui brianpmccullough/mcp-app-ui This MCP server provides the current server time through a basic resource and tool, following the MCP Apps quickstart. | |
| EndOfLife MCP Server brianprost/endoflife-mcp Provides access to the endoflife.date API to query support and end-of-life information for thousands of software products. It enables users to retrieve detailed release schedules, lifecycle data, and product categories through natural langu | |
| mcp-server-starrocks brianqureshi3349/mcp-server-starrocks Enables AI assistants to interact with StarRocks databases by executing SQL, exploring schemas and tables, retrieving metrics and overviews, and generating Plotly charts from query results. |
35,551–35,600 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.