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 |
|---|---|
| Bubble MCP Server d1dx/bubble-mcp Enables AI assistants to interact with Bubble.io applications through the Data API, supporting CRUD operations, schema discovery, and workflow execution. | |
| make-mcp d1dx/make-mcp This MCP server provides integration with Make.com (formerly Integromat) for workflow automation. It is now deprecated and replaced by Make's official cloud MCP. | |
| IAPI MCP Server d1dx2025/iapi_mcp_server Enables cryptocurrency investigation and analysis through the Chainalysis Investigations API. Provides access to 16 key endpoints for address clustering, transaction details, exposure analysis, and wallet observations across multiple blockc | |
| ai-visibility-mcp d1fpc3/ai-visibility-mcp Enables Claude to query ChatGPT, Claude, Perplexity and Gemini with customer questions and report whether a business is recommended, where it ranks, and which competitors are named instead. | |
| companion d1s3s/dsh-companion Enables persistent out-of-model memory plus screen, camera, browser, video, and messaging tools through MCP, with per-capability permissions, token cost tracking, and fail-closed approvals. Supports recalling preferences, viewing the screen | |
| TEUS MCP Proxy d1ys3nk0/teus-mcp-proxy Local stdio bridge that exchanges TEUS email and password for a short-lived JWT and forwards MCP JSON-RPC to TEUS over HTTPS, enabling interaction with TEUS MCP for users with ADMIN or ROOT authority. | |
| Moodle MCP Server d1zcipline/moodle-mcp Gives AI agents read-only access to a learning platform's courses, assignment details and deadlines, and downloadable course files through the official Web Services API. It automatically works around VPN/DPI network blocking and incomplete | |
| amazon-mcp d2d99/amazon-mcp Enables sellers to interact with Amazon Selling Partner API and Advertising API data—orders, inventory, pricing, ads, reports, and more—through MCP clients like Claude and Cursor. | |
| contact-verification-mcp d2emerge/contact-verification-mcp Enables agents to verify postal addresses, email addresses, and phone numbers against Melissa's Global Verification APIs before acting on the data, including batch verification and a per-session call budget to prevent runaway costs. | |
| move-api-mcp d33ptar00p/move-api-mcp Enables interaction with the Move AI UGC GraphQL API for markerless motion capture, allowing users to upload footage, create takes, run single- and multi-camera processing jobs, monitor progress, and download output files. | |
| proratia-mcp d3bn/proratia-mcp A generic MCP server that fetches OpenAPI/Swagger specs from any target API, with auto-discovery and Docker containerization. | |
| Yandex Lavka Uzbekistan MCP d3d0n/yandex-lavka-mcp Enables local MCP clients to search regional grocery products, authenticate with QR, inspect and modify a cart, preview checkout, and manage orders while requiring explicit confirmation for consequential writes. | |
| mcp-access-self-hosted d3hl/mcp-access-self-hosted An MCP server protected by Cloudflare Access as a self-hosted application, validating Access JWT and conditionally exposing tools based on user identity. | |
| remote-mcp-authless d3hl/remote-mcp-terraform-authless A remote MCP server deployed on Cloudflare Workers without authentication, enabling integration with AI Playground and Claude Desktop. | |
| Prover MCP d3lta02/prover-mcp Enables AI assistants to control Succinct Prover Network operations on Sepolia testnet, including running provers, calibrating hardware, staking tokens, and monitoring earnings through natural language commands. | |
| ojp-mcp d3orn/ojp-mcp Enables searching Swiss public transport locations, planning journeys, viewing departure boards, and retrieving trip details through the OJP 2.0 API using a personal token. | |
| chrome-hook MCP d3sh1n/chrome-hook-mcp Drives real Chromium browsers for multi-account testing and full network capture, with Cloudflare bypass via patched Playwright and real browser attach mode. | |
| saveon-mcp d3v0psdan/saveonfoods-mcp Enables Claude to search live grocery prices and stock, check weekly deals, price shopping lists, and plan meals from a selected Save-On-Foods location. | |
| SSH MCP Server d3v1an/ssh-mcp Enables remote server administration via SSH, supporting command execution, SFTP file transfers, and multi-profile management. It features security safeguards like destructive command detection and audit logging to ensure safe interaction w | |
| plum-virion d4-project/plum-virion Provides a read-only MCP interface to stored Plum-Island host observations over stdio, enabling IP inspection, structured and free-text search, tag and header discovery, and query help through the controller’s Discovery API. | |
| voxpipe d4n-sec/voxpipe Provides MCP tools to transcribe video/audio files into text, with silence-aware chunking, optional local backends, and progress notifications. | |
| exploitdb d4ngkh04w/exploitdb-mcp-server Enables searching Exploit-DB exploits and shellcodes by text and filters, retrieving metadata and source previews, and exact CVE search. | |
| NVD/NIST MCP server d4ngkh04w/nist-nvd-mcp-server Enables users to search and retrieve CVE records, CVE history, CPE Dictionary entries, and CPE match criteria through MCP tools, with local caching, pagination, and upstream rate-limit handling. | |
| weeek-mcp d4nilevi4/weeek-mcp Enables MCP clients to navigate and modify Weeek projects, boards, tasks, assignees, comments, tags, and time tracking through the Weeek API, with actions attributed to the API token owner. | |
| Bibliomantic MCP Server d4nshields/bibliomantic-mcp Enables casting I Ching hexagrams with the traditional three-coin method and retrieving James Legge's public-domain translation of judgments, images, and line texts, returning auditable cast records with changing and transformed hexagrams w | |
| Bibliomantic MCP Server d4nshields/bibliomantic-mcp-server Integrates I Ching divination with AI responses, allowing users to receive guidance through traditional Chinese philosophy using the bibliomantic approach described in Philip K. Dick's work. | |
| MCP Meetup-Claude Integration Server d4nshields/mcp-meetup A Model Communication Protocol server that connects Meetup.com's event discovery APIs with Anthropic's Claude LLM, enabling intelligent event discovery and natural language querying for Meetup events. | |
| WarungCyber MCP Server d4rks0ul555/warungcyber-mcp Connects MCP clients such as Claude Desktop, Cursor, and VS Code to 19 hosted AI models, providing tools for listing models, checking account balance, running chat completions, and generating client setup guides. | |
| sliverc2-mcp d4vydm/sliverc2_mcp MCP Server for Sliver C2 | |
| lightrag-mcp d8corp/lightrag-mcp Bridges AI assistants with LightRAG's knowledge graph capabilities, enabling document management and multi-mode queries through the Model Context Protocol. | |
| ChatGPT to Telegram MCP d8rt8v/chatgpt-to-telegram-mcp Publish reliable, duplicate-free Telegram posts from ChatGPT — manually or as part of a scheduled workflow. | |
| MCP FishAudio Server da-okazaki/mcp-fish-audio-server An MCP (Model Context Protocol) server that provides seamless integration between Fish Audio's Text-to-Speech API and LLMs like Claude, enabling natural language-driven speech synthesis. | |
| MCP Neo4j Server da-okazaki/mcp-neo4j-server This server enables interaction between Neo4j databases and Claude Desktop, allowing users to execute Cypher queries, create nodes, and establish relationships in the database. | |
| Spreadsheet MCP Server da-ponta/spreadsheet-mcp Enables AI assistants to read, write, and format Google Spreadsheets through the Model Context Protocol. It supports comprehensive operations including data retrieval, sheet creation, and cell formatting using natural language commands. | |
| trollspace-mcp da-troll/troll-mcp MCP server for the Trollspace API that exposes 47 type-safe tools for managing snippets, nuggets, todos, ideas, tools, repos, travel, subscriptions, and more. | |
| Canvas Student MCP Server da0806/canvas-student-mcp Enables AI assistants to interact with a student's Canvas LMS account, supporting course viewing, grade checks, assignment submissions, announcements, discussions, calendar events, inbox messages, and more via specialized tools. | |
| Elasticsearch MCP Server da1y/mcp-server-elasticsearch A Model Context Protocol server that enables LLMs to interact with Elasticsearch clusters, allowing them to manage indices and execute search queries using natural language. | |
| subagents da1z/subagents An MCP server that enables Cursor to delegate complex, multi-step tasks to specialized subagents, including general-purpose and explore agents, with automatic discovery of existing Claude subagents. | |
| Daily Briefing MCP Server da51d/daily-briefing Aggregates data from Google Calendar, TripIt, and Fireflies.ai to generate comprehensive daily briefings, schedule overviews, and action item lists. It enables users to manage their time by detecting meeting conflicts, identifying focus slo | |
| RepoDoctor MCP Server daamles/repodoctor Enables Claude to run read-only repository health checks for leaked secrets, code quality, and project structure. Exposes tools to scan repositories, retrieve Markdown or JSON reports, and filter findings by severity, rule, or path while co | |
| TrainingPeaks MCP Server daan12020/trainingpeaks-mcp Connects AI assistants to a TrainingPeaks account over the Model Context Protocol using cookie-based authentication that requires no API approval, letting users query and build structured workouts, schedule races and notes, manage equipment | |
| Yolfi MCP Server daan303/yolfi-agent Enables AI coding agents to add stablecoin checkout, payment links, payment status checks, webhook verification, and webhook-based access logic to applications. | |
| Financial Modeling Prep MCP Server daan550/financial-modeling-prep-mcp-server Enables AI assistants to query and analyze financial data through 250+ tools spanning stocks, ETFs, crypto, forex, commodities, economics, company fundamentals, SEC filings, and market news. It supports dynamic, static, or full toolset load | |
| EasyMCP daan7019/easy-mcp Enables developers to create Model Context Protocol servers in TypeScript with simple declarations for tools, prompts, resources, resource templates, and roots. | |
| Agent Harness Kit daan7093/agent-harness-kit Enables AI coding providers to run structured multi-agent development workflows, coordinating lead, explorer, consultant, builder, and reviewer roles through server-owned task claims, action logs, handoffs, and health-gated completion. Also | |
| Image Context Runtime daan7193/codex-image-context-runtime Enables Codex to run context-bounded image generation and inspection as durable local jobs, returning only bounded text handoffs, hashes, relative references, and Job IDs while keeping media bytes outside the task context. | |
| Frappe MCP daan7865/mcp Enables Frappe Framework apps to expose Python functions as MCP tools over a Streamable HTTP endpoint on WSGI-based servers, so LLM clients can call app logic through JSON-RPC. Tool schemas are inferred automatically from type annotations a | |
| Gitingest-MCP daan8429/gitingest-mcp Enables MCP clients such as Claude Desktop, Cline, and Cursor to quickly extract GitHub repository information, including summaries, directory structure, and file contents. | |
| swissdevjobs MCP Server daan94030/swissdevjobs-cli Enables AI agents and terminal users to search nine job boards across eight countries — including salary-transparent tech postings and Swiss and Singapore government portals — filtering by pay, remote work, tech stack and location, and to t | |
| Smart Coding MCP daanivanov/smart-coding-mcp Enables AI assistants to search a codebase by meaning using local AI embeddings, finding relevant code even when terminology differs from the query. Also provides package version lookup across 20+ registries, workspace switching, reindexing |
41,551–41,600 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.