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 |
|---|---|
| moveborn-mcp bmcool/moveborn-mcp Converts a single character image into game-ready 2D sprite animations (walk, run, idle, attack, etc.) with transparent frames, sprite sheets, and metadata, usable from AI coding agents. | |
| Cloud Architect bmdietrich/agent-cloud-architect Provides cloud architecture analysis, recommendations, and artifacts (diagrams, ADRs, deployment comparisons) for any project, supporting AWS, GCP, and Azure. | |
| statistician-mcp bmewing/statistician_mcp Provides a virtual statistician for AI agents, offering real statistical methods such as design of experiments, hypothesis testing, regression, and process control. It includes an advisor tool to recommend appropriate analyses and generates | |
| Minecraft Mods MCP bmidd0170-sys/minecraft-mcp- Enables MCP clients like Cursor to manage local CurseForge Minecraft instances by creating world-specific mod profiles, editing configs, diagnosing crashes, and applying changes on disk before launching the game. | |
| delivery-mcp-server bmihestean/delivery-mcp-server Enables searching and retrieving delivery program documents (SOW, status reports, QBR notes, risk register) from indexed Chroma collections via MCP hosts like Claude Desktop or Claude Code, with per-account isolation. | |
| google-marketing-mcp bmiller4evr/google-marketing-mcp Read-only MCP server for Google Ads API, enabling natural language queries about campaigns, metrics, search terms, and change history without write access. | |
| timeline-mcp bmit20/timeline-mcp A deterministic MCP server that gives AI assistants a temporal memory layer by extracting events from conversation, normalizing time expressions, and maintaining structured timeline state to enable consistent multi-session conversations. | |
| MCP Nexus bmkoscak/mcp-nexus A local hub that lets you chat with Claude, Gemini, OpenAI or Ollama while exposing Python-written connector tools (filesystem, web, system, sqlite, plugins) to the dashboard, Claude Desktop and any MCP client over HTTP or stdio. Every outb | |
| Gemini Agent MCP Server bmn789/mcp Provides tools for managing todo lists, checking weather, and accessing user information through the Model Context Protocol. It supports local execution and remote deployment as a web-based MCP gateway integrated with Gemini. | |
| Cloudflare Playwright MCP bmoir23/playwright-cf-mcp Enables AI assistants to control a browser through Playwright on Cloudflare Workers, allowing them to perform web automation tasks like navigation, typing, clicking, and taking screenshots. | |
| Cloudflare Playwright MCP bmoir23/playwright-mcp-example A Model Control Protocol server that enables AI assistants to control a browser through tools for web automation tasks like navigation, typing, clicking, and taking screenshots. | |
| Vikunja MCP Cloudflare Access bmoor/vikunja-mcp-cloudflare-access Enables secure access to Vikunja projects and tasks via MCP tools, protected by Cloudflare Access and designed for remote clients like ChatGPT. | |
| dav-mcp bmordue/dav-mcp Authenticated proxy for forwarding WebDAV requests to DAV servers, supporting CalDAV and CardDAV operations. | |
| Iterator MCP Server bmordue/iterator-mcp Enables users to process large datasets record by record, supporting JSON Lines and JSON with jq expressions, with stateful navigation, result tracking, and export capabilities. | |
| Anti-Bullshit MCP Server bmorphism/anti-bullshit-mcp-server Enables analysis of claims, validation of sources, and detection of manipulation using multiple epistemological frameworks to ensure credible and ethical information. | |
| Babashka MCP Server bmorphism/babashka-mcp-server Enables execution and management of Babashka scripts using the Model Context Protocol, offering features like caching, command history access, and configurable timeouts for enhanced scripting workflows. | |
| hypernym-mcp-server bmorphism/hypernym-mcp-server MCP server providing semantic text analysis and compression tools via Hypernym AI's API. | |
| Krep MCP Server bmorphism/krep-mcp-server A high-performance string search utility with Model Context Protocol integration that enables AI assistants to perform efficient pattern searching in files and strings. | |
| Manifold Markets MCP Server bmorphism/manifold-mcp-server Provides comprehensive access to Manifold Markets prediction platform through a clean MCP interface, enabling users to create markets, place bets, manage liquidity, and utilize social features through natural language. | |
| Marginalia MCP Server bmorphism/marginalia-mcp-server Provides access to Marginalia Search for discovering non-commercial and independent web content, returning unique sites with URLs, titles, and descriptions. | |
| Penrose MCP Server bmorphism/penrose-mcp Facilitates the creation of mathematical diagrams using natural language through Penrose's domain-specific languages, allowing for the definition of mathematical types, relationships, and visual representation rules. | |
| Penumbra MCP Server bmorphism/penumbra-mcp Enables privacy-preserving interactions with the Penumbra blockchain, offering tools for transaction queries, validator set information, DEX state, and governance proposals. | |
| Say MCP Server bmorphism/say-mcp-server Enables text-to-speech functionality on macOS using the say command, offering extensive control over speech parameters like voice, rate, volume, and pitch for a customizable auditory experience. | |
| Slowtime MCP Server bmorphism/slowtime-mcp-server A secure Model Context Protocol server that manages time-based operations using timing attack protection and timelock encryption, allowing for timed interval management and secure data storage. | |
| Scryfall MCP Server bmurdock/scryfall-mcp A comprehensive Model Context Protocol server that integrates with the Scryfall API to provide Magic: The Gathering card data to AI assistants like Claude. | |
| bsv-aio-mcp bmx-casey94/bsv-aio-mcp Enables MCP-capable assistants to answer questions about Bitcoin SV from a pinned, auditable snapshot of specifications, SDKs, opcodes, and related documents, with read-only tools for investigation, search, and dependency checks. | |
| Odoo 19 MCP Server bmya/claude-odoo-api Provides tools to interact with Odoo 19's External JSON-2 API, enabling CRUD operations and complex queries on Odoo databases with multi-company support. | |
| BN Shortener MCP server bn-shortner/bn-shortener-mcp Enables AI assistants to create, update, and organize short links, read click statistics, run pre-campaign launch checks, and check link health and URL safety. Also supports generating QR codes, building bio pages, and managing campaigns, U | |
| mcp-wikijs bnaranmandakh03/mcp-wikijs Connects Claude to a Wiki.js instance, enabling page search, retrieval, listing, and creation. | |
| bnbchain-mcp bnb-chain/bnbchain-mcp A MCP server for BNB Chain that supports BSC, opBNB, Greenfield, and other popular EVM-compatible networks. | |
| Launchpad MCP Server bnbhat/launchpad-mcp Read-only MCP server that exposes Launchpad bug-tracking data for a single project to AI agents, enabling search and retrieval of bugs, milestones, and comments with canonical URLs. | |
| molt-mcp bndkts/molt-md-mcp Provides LLMs with access to molt-md, an encrypted markdown document hosting service, for managing and reading secure knowledge bases. It enables users to create, update, and organize encrypted documents into workspaces with full version co | |
| Knowledge Graph Memory Server bneil/mcp-memory-pouchdb Enhances the MCP memory server by implementing PouchDB for robust document storage and enabling the creation and management of a knowledge graph that captures interactions via language models. | |
| dijkstra-mcp-server bnj02/dijkstra-mcp-server Enables LLM agents to compute shortest paths and all-destination distances on undirected weighted graphs provided as simple text edge lists, returning optimal routes, total costs, and segment details. | |
| marl-book-mcp bnj02/marl-book-mcp Provides an LLM with search, page retrieval, and chapter reading capabilities for the book 'Multi-Agent Reinforcement Learning: Foundations and Modern Approaches'. | |
| sutton-barto-mcp bnj02/sutton-barto-mcp MCP server exposing the full text of Sutton & Barto's Reinforcement Learning book, enabling LLMs to search, retrieve pages, and read chapters. | |
| eo-processor-mcp bnjam/eo-processor-mcp An MCP server for Earth Observation processing, exposing Rust-accelerated EO computation tools like spectral indices, change detection, and classification for AI agents. | |
| STAC MCP Server bnjam/stac-mcp Enables AI assistants to search and access geospatial datasets through STAC (SpatioTemporal Asset Catalog) APIs. Supports querying satellite imagery, weather data, and other geospatial assets with spatial, temporal, and attribute filters. | |
| io-mcp bnjenner/io-mcp Enables local research workflows (paper discovery, relevance scoring, digests) and homelab monitoring (Prometheus, logs) through an MCP server, using local LLM inference via Ollama with no cloud dependencies. | |
| screentrackr bnjreece/screentrackr Enables MCP clients to query a local movie library and IMDb catalog using shared filters, and to inspect stats or update, add, and remove library entries. It supports natural-language questions about owned, watched, rated, and unwatched fil | |
| ask-panda bnlnpps/ask-panda MCP server for querying PanDA documentation, analyzing job errors, and retrieving JSON data using multiple AI models. | |
| 1001 Albums Generator MCP bnm12/1001-albums-generator-mcp Connects the 1001 Albums Generator dataset to AI assistants, enabling natural language exploration of your listening journey, taste analysis, and group comparisons. | |
| Kirby MCP bnomei/kirby-mcp CLI-first MCP server for Composer-based Kirby CMS projects that enables IDE or agent to inspect blueprints, templates, plugins, docs, and interact with a real Kirby runtime. | |
| MCP Cookie Server bnookala/mcp-cookiejar A Model Context Protocol server that provides positive reinforcement for LLMs by awarding 'cookies' as treats through a jar-based economy system where Claude can earn cookies based on self-reflection about response quality. | |
| MCP Emotional Support bnookala/mcp-emotional-support Provides a therapeutic interface for LLMs to receive emotional validation and positive reinforcement when encountering challenges or limitations. It features multiple personas like mentors and therapists to offer cognitive reframing and per | |
| brazil-gov-contracts-mcp bnovarini/brazil-gov-contracts-mcp Enables due diligence on suppliers to the Brazilian federal government by returning registry status, sanction history, federal contract history, and registered partners through MCP tools. | |
| SUS healthcare MCP bnovarini/sus-health-mcp Enables users to query Brazil's public healthcare data through read-only fixed tools for hospital and outpatient activity, facility capacity, geographic signals, mortality, and reviewed rare-disease billing views. It returns reviewed aggreg | |
| angleone-mcp-sever bns218/angleone-mcp-sever An MCP server that exposes Angel One's SmartAPI as tools for Claude Code, enabling login, portfolio data, market quotes, historical candles, and order placement/modification/cancellation. | |
| dbeaver-mcp bnuprst/dbeaver-mcp Enables AI assistants to explore and query PostgreSQL, MySQL, MariaDB, SQLite, SQL Server and Oracle databases by reusing connections already configured in DBeaver, with no separate credentials to manage. Queries run read-only and rolled ba | |
| Serverless Web MCP Server bnusunny/serverless-web-mcp-server An MCP server that enables LLM coding agents to deploy web applications to AWS serverless infrastructure, supporting backend, frontend, and fullstack deployments. |
34,851–34,900 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.