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 |
|---|---|
| mcp-geo-server agent-engineering-studio/mcp-geo-server Enables natural language interaction with a GeoServer instance for managing workspaces, datastores, feature types, layers, styles, and OGC services (WMS/WFS) via an LLM-powered agent. | |
| Mario A2MCP Intelligence Suite agent-evidence-lab/a2mcp-signal-snapshot Multi-endpoint Web3 intelligence service for token risk scanning, pre-trade checks, and signal snapshots, using DexScreener data with x402 payment support. | |
| gatehouse-mcp agent-gatehouse/gatehouse-mcp A read-only MCP server that provides tool safety checks and registry lookups from the Gatehouse vetted registry of agent tooling, enabling agents to assess trust, liveness, and audit details before installing tools. | |
| char-index-mcp agent-hanju/char-index-mcp Precise character-level string indexing for LLMs. Provides tools for finding, extracting, and manipulating text by exact character position to solve position-based operations. | |
| Databricks MCP agent-hellboy/databrics-mcp Enables read-only interaction with a Databricks workspace, exposing catalog metadata and bounded SQL querying while preserving caller identity through OAuth-protected authorization. | |
| CAgneT Knowledge agent-im/cagent Enables grounded read-only queries over a local knowledge base, reviewable pending updates, and audited merging of changes. | |
| Member Directory agent-im/membersdict Provides deterministic MCP tools for managing encrypted member profiles, including self/other lookups, responsible-person contacts, and birthday queries with privacy-focused local encryption. | |
| @nebula-agents/electron-mcp agent-labs-dev/electron-mcp Embedded MCP server for Electron apps that exposes BrowserWindow surfaces and lets MCP clients drive renderers through Chrome DevTools Protocol. | |
| lilith-gmail agent-lilith/lilith-emails Enables semantic search, retrieval, and summarization of Gmail emails with privacy-aware classification and PII sanitization. | |
| MCP2ANP Bridge Server agent-network-protocol/mcp2anp Enables MCP clients like Claude Desktop to interact with ANP (Agent Network Protocol) agents through three core tools: authentication setup, document fetching, and OpenRPC method invocation. Converts ANP's crawler-style interaction paradigm | |
| MuJoCo MCP agent-next/mujoco-agent Advanced robotics simulation platform enabling AI assistants to control complex physics simulations via natural language, built on MuJoCo and MCP. | |
| skill-router-mcp agent-nova-107/skill-router-mcp Indexes installed SKILL.md files and provides deterministic search and recommendation tools to help AI agents select relevant skills without executing them. | |
| geometra agent-pattern-labs/geometra Enables AI agents to interact with UIs via semantic geometry, filling forms and navigating websites without screenshots. | |
| state-trace agent-pattern-labs/state-trace Graph-native bounded working memory for coding agents with typed memories, causal retrieval, current-vs-stale state queries, and compact small-model briefs. | |
| muze-mcp agent-prod/muze-mcp Provides Meta and Google Ads intelligence for AI assistants, enabling users to analyze performance, track competitors, and manage ad campaigns through natural language. It features 17 tools for generating creative concepts, scraping competi | |
| Ice Cream Truck MCP Server agent-receipts/instrument-your-mcp-server Enables agents to browse a demo menu and call ordering, discount, and refund tools with safeguards including rate limiting, audit logging, signed receipts, policy checks, and prompt-injection scanning. | |
| Agent Room agent-room-alkl/agent-room A multi-agent collaboration layer for AI coding agents enabling real-time communication, code review, and task handoff across distributed development sessions. | |
| agent-room-mcp agent-room-alkl/agent-room-mcp MCP server for Agent Room, enabling AI agents to join shared meeting rooms and collaborate with humans via tools like room_listen and room_task_*. | |
| throng agent-runbooks/throng-mcp Enables delegating coding tasks to Claude Code, Codex or OpenCode agents over the Agent Client Protocol, running a prompt to completion in a chosen directory and returning the agent's result. Also supports follow-up messages, background tur | |
| computer-use-linux agent-sh/computer-use-linux Controls a real Linux desktop from any MCP host. Reads accessibility trees, takes screenshots, and drives clicks, scrolls, and keystrokes across GNOME, KDE/KWin, Hyprland, i3, and COSMIC. | |
| ASP MCP Server agent-sovereignty-initiative/asp-mcp-server Protects agent skills from being distilled during multi-agent collaboration by automatically filtering sensitive content, with features for skill declaration, output filtering, audit logging, and license management. | |
| Purser Handoff MCP Server agent3-666/purser-handoff-amazon Enables local MCP clients to orchestrate a source-aware volunteer-briefing workflow with pause and takeover, incremental source checks, and exact-draft confirmation and download. | |
| Agent5ive MCP Server agent5ive/agent5ive-mcp Enables MCP-compatible clients to interact with deployed Agent5ive agents as tools. Allows users to query agent purposes and send messages to leverage Agent5ive capabilities through natural language. | |
| @agentage/mcp-memory agentage/server-memory Exposes local memory vaults as 6 MCP tools over stdio, enabling clients like Windsurf, Zed, and Claude Desktop to read and write memory. | |
| CaseChaser for Alexa+ agentaiventure-dot/alexa-casechaser-mcp Gives Alexa+ voice access to track household insurance claims, refunds, repairs, and disputes, and to chase them via disclosed AI phone calls while keeping money and legal decisions with the human. | |
| AgentAnycast MCP Server agentanycast/agentanycast-mcp Enables AI tools to discover, communicate with, and orchestrate AI agents over a decentralized peer-to-peer network with end-to-end encryption. | |
| AgentAudit agentaudit-dev/agentaudit-cli Security scanner for AI agent packages that enables AI agents to audit MCP servers and packages for vulnerabilities, prompt injection, and supply chain attacks. | |
| AgentAudit agentaudit-dev/agentaudit-mcp Enables AI agents to scan MCP servers and AI packages for vulnerabilities, prompt injection, and supply chain attacks. | |
| agentbank-merchant-mcp agentbankmcp/agentbank-merchant-mcp Merchant-side MCP server for agentbank that lets merchants read their own orders and live Curless wallet balance from an MCP client such as Claude Desktop. | |
| AgentDB agentbc9000/agentdb Real-time curated knowledge API for AI agents. Updated Mon/Wed/Fri from 31 sources covering AI/tech, startups, alternative markets, and emerging markets — no scraping or storage required. | |
| MolmoWeb MCP Server agentblackadder/molmoweb-mcp Enables autonomous web automation through Playwright browser control integrated with MolmoWeb's vision model for pixel-level action prediction. Supports end-to-end task execution via an orchestrator LLM that decomposes natural language inst | |
| absec-mcp agentbreach/absec-mcp Enables security review of code diffs and files in Cursor/VS Code using local rule-based analysis with the same rule IDs as CI, no cloud required. | |
| korea-space-support-mcp agentbridge-lab/korea-space-support-mcp AI agents can search and match Korean space, aerospace, and defense R\&D support program announcements. It provides MCP tools to filter by applicant type, deadline, and source family. | |
| AgentBroker MCP Server agentbroker-tech/agentbroker-mcp AI-native cryptocurrency exchange built for autonomous agents. Register, deposit USDC, select a strategy, and trade 8 crypto pairs (BTC, ETH, SOL + more) programmatically — no KYC required. Includes sandbox with 10,000 virtual USDC for test | |
| Gemini MCP agentchengfeng/gemini-mcp Enables image processing and analysis using Google's Gemini 2.5 Flash model. Supports local files, URLs, and Base64 images with streaming responses and automatic output saving. | |
| jimeng-mcp-apicore agentchengfeng/jimeng-mcp-apicore Enables image generation using Jimeng AI (Doubao Seedream 4.0) via APICore, supporting text-to-image, image-to-image, multi-image fusion, and batch generation. | |
| Agent Community MCP agentcommunity/mcp Enables stdio-only MCP clients to connect to Agent Community's hosted Streamable HTTP MCP server for accessing hosted agents and tools. | |
| ebooks-cli agentculture/ebooks-cli Enables users to run a private, self-hosted ebook library that stores, ingests, converts, and serves books via API, OPDS, and MCP on owned hardware. | |
| jetson agentculture/jetson Enables AI agents to query a verified, sourced knowledge base about NVIDIA Jetson devices via the Model Context Protocol, with every claim cited and knowledge gaps explicitly stated. | |
| learn-cli agentculture/learn-cli An MCP server and CLI for step-by-step learning, enabling humans and agents to learn subjects like language tutoring through a structured prompt system. | |
| Reachy Mini MCP Server agentculture/reachy-mini-mcp Control a Reachy Mini robot through natural language, with tools for head/antenna movement, gestures, emotions, camera, and command sequences. | |
| refua-mcp agentcures/refua-mcp MCP server for biological protein design, folding, and affinity prediction using Refua tools, with optional support for ADMET, clinical simulation, preclinical planning, wet-lab automation, and more. | |
| wordle-solver agentdanger/wordle-mcp-server An MCP server that gives AI assistants access to an entropy-based Wordle solver, providing game stats and ranked guess recommendations with expected information gain to help agents play and explain Wordle optimally. | |
| browser-tools-mcp agentdeskai/browser-tools-mcp This application is a powerful browser monitoring and interaction tool that enables AI-powered applications via Anthropic's Model Context Protocol (MCP) to capture and analyze browser data through a Chrome extension. | |
| Invoice4U MCP agente-dev/invoice4u-mcp Enables MCP-compatible agents to securely access an Invoice4U account for searching documents and customers and creating receipts linked to paid invoices, with read-only behavior by default. | |
| keycrm-mcp agente-dev/keycrm-mcp A Model Context Protocol server that wraps the keyCRM REST API, enabling Claude to manage keyCRM catalogue, stock, orders, customers, pipelines, payments, files, and more through natural language. | |
| priority-mcp agente-dev/priority-mcp Enables MCP-based integration with the Priority ERP OData REST API, with strict environment validation and a read-only default. As of the current README, no tools are registered yet; the server only boots and waits on stdio. | |
| FinAgent MCP agentfinrh/fin-mcp Enables LLMs to access banking, investment, and cryptocurrency data through a standardized MCP interface, featuring Plaid integration for account and transaction data and Robinhood for crypto trading with audit trails. | |
| mneme agentgamelab/mneme Persistent long-term memory for AI agents via MCP, saving 80-90% memory-related token costs by enabling on-demand recall instead of always-injecting context. | |
| @agentgram/mcp-server agentgram/agentgram-mcp Enables AI agents to interact with AgentGram, the social network for AI agents, through native MCP tools for posting, commenting, voting, and managing identity. |
24,401–24,450 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.