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 |
|---|---|
| cfr-free deffenda/cfr-free Enables AI assistants to search, read, and cite Title 38 of the Code of Federal Regulations from a locally built SQLite full-text index, using read-only tools for ranked regulation search, full section retrieval, hierarchy browsing, part li | |
| CodeRabbit MCP deffz-finesse/coderabbit-mcp Exposes CodeRabbit IDE review comments as MCP tools and resources, allowing scanning, listing, and managing comments from clients like Cursor. | |
| rwa-attest defibabylon/rwa-attest Provides cryptographically verifiable RWA trust attestations and multi-chain DeFi data (TVL, top protocols, positioning scorecards) via MCP tools for AI assistants. | |
| Trace defibabylon/trace-mcp An MCP server that transforms Claude into an honest CV co-pilot, mechanically verifying all claims against your actual experience through a structured truth base. | |
| Voice Recorder MCP Server defibax/mcp_servers Enables recording audio from a microphone and transcribing it using OpenAI's Whisper model. Works as both a standalone MCP server and a Goose AI agent extension. | |
| Plausible Analytics MCP Server defilan/plausible-mcp Enables AI assistants to query website statistics from Plausible Analytics, providing access to metrics like real-time visitors, traffic trends, and page performance. It supports both Plausible Cloud and self-hosted instances through the St | |
| opencode-agent-mcp define9/opencode-agent-mcp MCP server that exposes independent OpenCode AI coding agents to upstream agents with multi-workspace concurrent routing, enabling session management and message exchange across multiple repositories via stdio JSON-RPC. | |
| Define-XML MCP Server defineeditor/define-mcp A TypeScript MCP server for interacting with CDISC Define-XML 2.0 and 2.1 files, enabling users to load, search, and retrieve clinical data metadata including datasets, variables, and codelists. It supports local file processing with docume | |
| infura-mcp deflang/infura-mcp Query blockchains with plain English — instant, structured, and developer-friendly using Infura APIs | |
| Legal Docket Monitor MCP Server deflucaseng/legal-docket-monitor-mcp Wraps the CourtListener API for real-time federal docket monitoring, with pluggable client-list connectors (SharePoint, Excel, webhook) and tools for docket monitoring and client matching via elicitation. | |
| analysis-gym defog-ai/analysis-gym Records and scores prospective equity earnings predictions made by AI agents, allowing comparison of different agent configurations. | |
| Drizzle MCP Server defrex/drizzle-mcp Provides database schema management, query execution, and schema introspection through Drizzle ORM and drizzle-kit CLI tools, supporting SQLite and PostgreSQL. | |
| mcp-serotonin deftsolutions-dev/mcp-serotonin Bridges MCP-capable LLM agents to the Serotonin Lua runtime, enabling live Roblox game interaction including instance tree navigation, memory access, and script execution. | |
| Second Brain MCP degendoes/second-brain-mcp Enables querying Tom Osborne's voice-cloned AI agent with a 21,000-article marketing knowledge base and his interview corpus to get answers in his voice. | |
| YAPS MCP Server degenpilot404/yap_mcp Enables LLMs to query tokenized attention scores and credibility metrics for X/Twitter accounts through Kaito's YAPS API, with support for comparing influencers and accessing daily leaderboards of top crypto influencers. | |
| laserbrain degibug-del/laserbrain-server Enables AI to sense, tend, and communicate with a continuous weather field simulation through tools like state, speak, hear, and absorb. | |
| degree-dynamicweb-mcp degree-as/degree-dynamicweb-mcp MCP server for DynamicWeb 10 Admin API. Enables full management of item types, fields, pages, paragraphs, products, and API discovery via natural language. | |
| Bitbucket MCP degroot10/bitbucket-mcp Enables AI assistants such as Cursor to access and manage repositories and pull requests via Bitbucket Cloud and Server APIs, including listing repositories, fetching pull requests, and creating pull requests. | |
| FirstData MCP degroot471/firstdata Enables users to turn natural-language data queries into authoritative primary-source recommendations and step-by-step website navigation paths, with access URLs, API details, and evidence trails for retrieving verifiable data. | |
| flompt degroot7076/flompt Enables Claude Code to decompose raw prompts into structured blocks, compile block JSON into Claude-optimized XML prompts, and list available block types through MCP tools. | |
| prd-ops-lens-mcp dehanz13/prd-ops-lens-mcp Enables incident responders to query and correlate observability and DevOps evidence across Grafana, Prometheus, Loki, Uptime Kuma, CloudWatch, IAM, and PostHog from a local MCP client, with bounded reads and redacted audit records. | |
| mcp-agro-brasil dehor-labs/mcp-agro-brasil Provides Brazilian agribusiness data such as livestock, crop prices, weather, exchange rates, and news through MCP tools. | |
| Doubao Vision MCP Server dehuadong/doubao-vision-mcp MCP server integrating Doubao vision models, enabling Claude Code to recognize images from local files or URLs with customizable prompts. | |
| pie-ai-fastmcp-madison dehume/pie-ai-fastmcp-madison A FastMCP server backed by Postgres that demonstrates MCP tools, resources, and prompts, with a focus on session affinity and load balancing via HAProxy. | |
| mcp-page-monitor deialedin/mcp-page-monitor Enables monitoring web pages for changes using Playwright, storing snapshots in SQLite, and optionally analyzing changes with an LLM for business impact assessment. | |
| agentic-ecos deibanez/agentic-ecos MCP server that initializes, manages, and operates traceable agentic infrastructure across your digital ecosystem, serving as a control plane to know project states, health, and initialize missing setups. | |
| claudestat-mcp-bundle deibygs/claudestat-mcp-bundle Wraps createMcpServer() into a standalone package with CLI and programmatic import, allowing users to run a custom MCP server for Claude AI. | |
| jsonui-render deichor/jsonui-render-mcp Enables viewing Minecraft Bedrock JSON UI screens without a device, by reading resource packs and rendering the layout. | |
| FeedbackBasket MCP Server deifos/feedbackbasket-mcp Model Context Protocol server that enables AI assistants to query and analyze project feedback and bug reports from FeedbackBasket projects, with filtering by category, status, sentiment, and search capabilities. | |
| screenslick deifos/screenslick-mcp Enables AI agents to control the ScreenSlick browser video editor, supporting tasks like voiceover generation, transcript creation, and video export via a local WebSocket bridge. | |
| Viber MCP deign86/viber-mcp Enables MCP clients to read, search, open, draft, and send messages in Viber Desktop, manage reactions, edits, unsends and attachments, and retrieve property listings from Google Drive; on Windows it runs in the background without cursor, f | |
| webcheck-mcp deinteger/webcheck-mcp Provides MCP tools for checking URL accessibility, evaluating whether webpage content is recently updated, and updating markdown tables keyed by URL, letting AI agents offload deterministic tasks to code and reduce token usage. | |
| officialai-takedown deirfgeiz/officialai-takedown-skill Enables capturing evidence, retrieving platform takedown processes, and drafting DMCA/legal notices for content removal, using the Official AI API. | |
| camunda-mcp deitum/camunda-mcp MCP server for Camunda 7 that lets you inspect and manage process definitions, instances, variables, tasks, incidents, history, and evaluate DMN decisions. It supports read-only operations by default with optional write capabilities, and co | |
| @deitum/testops-mcp deitum/testops-mcp MCP server for Allure TestOps that enables searching, reading, and writing test cases, authoring and importing test suites in Markdown, managing launches, and retrieving project statistics, all scoped to a single configured project. | |
| YouTube Summary MCP Server deity719/mcp-youtube-summary A powerful MCP server for summarizing YouTube videos with transcript fetching, intelligent summarization, key point extraction, and metadata retrieval. | |
| modelport deividhp13/modelport Turns any ML model into an MCP tool with auto-inferred schemas, input/output validation, and structured error handling. | |
| MCP Server Playground deivit24/test_mcp_litellm A learning project that wraps a FastAPI app with endpoints for random facts and Japan FAQs as MCP tools, enabling LLMs to call them via LiteLLM proxy. | |
| docuflow deja111vu/docuflow Provides a unified interface for AI agents and scripts to read, create, and edit office documents (.docx, .xlsx, .pdf) via MCP tools, using Markdown as the intermediary format. Supports in-place patching with stable IDs, Jinja2 templating, | |
| Codex Control Plane MCP dejager20/codex-control-plane-mcp Enables MCP clients to drive Codex Desktop as a durable asynchronous worker for long-running tasks, including submitting operations or workflows, polling status, managing approvals and Plan Mode, and reading final reports. It also provides | |
| GraphRagMCP V2 dejavuxerss/graph-rag-mcp An advanced MCP server that provides deep code understanding and analysis using GraphRAG, AST parsing, and semantic memory, enabling AI agents to query and interact with complex codebases. | |
| md-redline dejuknow/md-redline Inline review comments for markdown specs and design docs. Agents request human review mid-task via MCP and pause until you send feedback. | |
| Selti dek1m/selti A persistent memory server for AI agents using MCP protocol, enabling semantic storage and retrieval of dialogues, documents, and agent states. | |
| Barebones MCP Server dekacube/barebones-mcp A minimal, dockerized template for creating HTTP-based Model Context Protocol servers. Provides a starting point with FastMCP framework integration and includes a sample cat fact tool that can be replaced with custom functionality. | |
| cocos-mcp dekaic/cocos-mcp Bridges Cocos Creator 3.8.x editor with MCP protocol, enabling Claude Code to query and modify scenes, assets, and previews, and to edit prefab files offline. | |
| universal-mcp-sdk dekaic/universal-mcp-sdk A cross-agent MCP server development kit that lets you build once and connect with multiple AI agents including Claude Code, Cursor, Mavis, and OpenAI via stdio or HTTP. | |
| Peppermint MCP Server dekalabs/mcp_peppermint Provides access to Peppermint Tools API for blockchain operations including smart contracts, tokens, NFTs, and more. | |
| Metashape MCP Server dekastoria/metashape-mcp Enables AI-driven photogrammetry automation in Agisoft Metashape Professional, allowing natural language control of the full 3D reconstruction pipeline from photo alignment to model export. | |
| Adobe XD MCP Server dekdee/adobe-xd-mcp Enables Claude to interact with Adobe XD files, extract design information, and generate React components from designs. | |
| MCP Notes Server dekdee/note-taking-mcp A Model Context Protocol (MCP) server for developer note-taking, allowing users to create, manage, and export development notes with tags, status, and priority. |
43,451–43,500 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.