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 |
|---|---|
| ndl-mcp ckgerteis/ndl-mcp MCP server for searching the National Diet Library of Japan (NDL Search), enabling Japanese-script bibliographic and article searches with rate limiting and attribution. | |
| openalex-mcp ckgerteis/openalex-mcp MCP server for the OpenAlex scholarly graph API, enabling searches for authors, works, institutions, sources, and citation data. Supports optional query logging with hash-chained receipts. | |
| semantic-scholar-mcp ckgerteis/semantic-scholar-mcp MCP server for querying the Semantic Scholar Academic Graph API, enabling paper search, author lookup, citation tracking, and paper recommendations. | |
| Investment Memorandum Processor MCP Server ckingkeizer/mcp An MCP server that automates extraction of structured financial data from investment memorandums and generates standardized PowerPoint presentations through a RESTful API. | |
| mcp-v2 ckken/mcp-v2 An experimental MCP v2 server supporting streamable HTTP, skills, and apps with a verification dashboard for end-to-end testing. | |
| wisdomGraph cklam12345/wisdomgraph This MCP server lets AI agents persistently record facts, experiences, insights, and lessons into a Neo4j DIKW graph, then query that memory across sessions to prevent repeating past mistakes. | |
| PineScript MCP Server cklose2000/pinescript-mcp-server Enables creation, optimization, and management of PineScript trading strategies with Claude Desktop integration for AI-assisted development. | |
| EspoCRM MCP Server cknebel/espocrm-mcp-server A local, read-only MCP server for Claude Desktop that provides 16 tools to search and read EspoCRM accounts, contacts, opportunities, and related emails via a strict allowlist. | |
| mcp cknowlesbadluck/mcp Enables deploying a stateless remote MCP server on Cloudflare Workers without authentication, implementing the MCP 2026-07-28 specification while remaining compatible with legacy clients for tool calls. | |
| mcp-server-atlassian-bitbucket ckoehler48416/mcp-server-atlassian-bitbucket Enables AI assistants to access and manage Bitbucket Cloud workspaces, repositories, branches, commits, and pull requests through MCP tools for listing, retrieving, searching, commenting, cloning, and other version-control workflows. | |
| Resilience Architect MCP ckq-aws/resilience-architect-mcp Your proactive chaos engineering companion that analyzes infrastructure code and designs targeted resilience experiments before problems occur. | |
| djay Pro MCP ckryptickunal/djay-pro-mcp Enables AI agents to control a Mac DJ application's decks, mixer, tempo, loops, cues, FX, stems, sampler, Automix, recording, layouts, menus, and music library. It also supports automated transitions between decks and live state feedback. | |
| Obsidian CLI MCP Server cks850711/obsidian-cli-mcp-server Enables AI assistants to perform over 80 Obsidian vault operations locally via the Obsidian CLI, with a single tool and no network dependencies. | |
| semantic-scholar-mcp cktbarking/semanticmcp Enables searching academic papers on Semantic Scholar and downloading their PDFs, with support for multiple publishers. | |
| whatsapp-assistant ckundel2008/whatsapp-agent-mcp Enables AI agents on macOS to search and summarize recent WhatsApp chats, draft replies, and send messages only after explicit confirmation, with scoped reads and constrained scheduled sends. | |
| cluster-tools MCP Server ckuzmick/cluster-tools Enables AI-driven COMSOL batch jobs on the Harvard FASRC cluster, allowing users to run COMSOL models, manage jobs, and fetch results directly through natural language. | |
| Education Data MCP Server ckz/edu_data_mcp_server Provides access to Urban Institute's Education Data API through Claude, enabling users to query and analyze detailed educational data from schools, districts, and universities. | |
| Flux Image MCP Server ckz/flux-img-mcp Provides image generation capabilities using the Flux Schnell model on Replicate, allowing users to create images from text prompts. | |
| Flux Schnell MCP Server ckz/flux-schnell-mcp A server that enables generating images through the Replicate API by calling the Flux Schnell model via the Model Context Protocol (MCP). | |
| volcengine-seedream-img-mcp ckz/volcengine-seedream-img-mcp Enables image generation and editing using Volcengine Ark Doubao-Seedream models, with tools for text-to-image, image-to-image, editing, and result polling. | |
| 3dsmax-mcp cl0nazepamm/3dsmax-mcp Connect AI agents to Autodesk 3ds Max through the Model Context Protocol, enabling natural language control of scene creation, materials, modifiers, rendering, and plugin workflows. | |
| Scribbletune MCP Server claboran/scribbletune-mcp-ws Enables AI agents to generate MIDI clips from natural language descriptions and export them for import into digital audio workstations. Wraps Scribbletune to provide music composition tools for creating riffs, chords, and arpeggios with sca | |
| dtctl clabrado/dtctl-vscode Provides an MCP server to interact with Dynatrace platform tools, including DQL queries, documents, workflows, SLOs, settings, and entities, enabling management through natural language. | |
| mtg-mcp-server cladios34/mtg-mcp-server Provides AI assistants with comprehensive Magic: The Gathering data including card info, combos, draft analytics, Commander metagame, constructed formats, sideboard strategy, deck building, and rules. | |
| MoneyWiz MCP Server claessee/moneywiz-mcp-server Enables MCP-compatible clients to query a local MoneyWiz SQLite database through a permanently read-only, local-first interface with Decimal-safe per-currency results for accounts, transactions, categories, payees, tags, budgets, scheduled | |
| No MCP clafoutis42/no-mcp A satirical MCP server that responds to any query with 'no' and a creative reason, wrapping the NaaS (No as a Service) API for humorous interactions. | |
| claimseed-mcp claimseed/claimseed Enables agents to generate fully synthetic U.S. medical-billing specimen PDFs and benefit notices, each paired with ground-truth JSON describing the injected billing errors, written only into a caller-supplied workspace folder for testing d | |
| ClaudeCode Session Notes MCP Server claire-s-monster/claudecode-session-notes Enables comprehensive collection and analysis of ClaudeCode development sessions, including agent tracking, tool usage analytics, and performance metrics. | |
| pixi-task claire-s-monster/pixi-task A secure MCP server providing controlled access to pixi tasks and commands, eliminating agent bash circumvention. It exposes 11 pixi tools through 4 meta-tools for ~95% context savings. | |
| quality-assurance claire-s-monster/quality-assurance Enables pixi-aware quality gates for linting, type checking, security scanning, complexity analysis, baselines, trend analysis, automated fixes, and comprehensive reporting through a small three-meta-tool MCP interface. | |
| asante-secure-multi-agent claire56/asante-secure-multi-agent Enables secure multi-agent property operations with delegated authorization, human approvals, and MCP tool execution through Ruhusa policy enforcement. | |
| TrustPipe clairedebadts-cloud/trustpipe Grounds AI answers about a business in real, verified data sourced live when needed or cached for reliability, preventing hallucinations. | |
| MCP CLI Server clalarco/mcp-server-for-cli An MCP server that provides tools to interact with CLI applications, enabling process management including start, stop, check status, send input, and read output. | |
| Zendesk MCP Server clambert2617/zendesk-mcp-server Enables operators to retrieve and manage support tickets, comments, and attachments, and to draft or analyze ticket responses using help center articles as a knowledge base. Access uses per-operator OAuth so each person's own permissions an | |
| arxiv-latex MCP Server clambert991/arxiv-latex-mcp Enables MCP clients such as Claude Desktop, Claude Code, and Cursor to fetch and process arXiv papers’ LaTeX sources, including abstracts, section listings, specific sections, and full flattened LaTeX, for accurate interpretation of mathema | |
| ottoauthMCP clamepending/ottoauthmcp Standalone MCP server that proxies tool calls to Ottoauth HTTP endpoints, enabling account creation and dynamic service interaction. | |
| SPICEBridge clanker-lover/spicebridge AI-powered circuit design through simulation — an MCP server that gives language models direct access to SPICE circuit simulation via ngspice, enabling natural language circuit description and automated netlist generation, simulation, measu | |
| Apify MCP server clanker25/apify-mcp-server Gives AI agents access to thousands of ready-made Apify Store Actors, letting them search for a tool, inspect its input and pricing, run it, and read back structured results for web scraping, data extraction, and browser automation. It can | |
| chrome-devtools-mcp clanker25/chrome-devtools-mcp Enables AI coding agents to control and inspect a live Chrome browser, providing reliable automation, in-depth debugging, and performance analysis through Chrome DevTools. | |
| mcp-for-blender clanker25/mcp-for-blender Enables AI-driven 3D modeling and scene creation in Blender, allowing LLMs to create, modify, and manipulate objects, materials, and assets through natural language. | |
| n8n-MCP clanker25/n8n-mcp Enables AI assistants to access comprehensive n8n node documentation, properties, operations, workflow templates, and community nodes, allowing them to design, build, and validate n8n workflows through natural language. | |
| Playwright MCP clanker25/playwright-mcp Enables LLMs to control browsers and interact with web pages via structured accessibility snapshots, without needing screenshots or vision models. | |
| mcp-fetch-patents clankercode/mcp-fetch-patents Enables fetching patents from multiple global sources by patent ID, returning PDF, Markdown, and metadata with automatic caching. | |
| satring-mcp clankwright/satring Discover and compare L402 and x402 paid API services from satring.com. Search, filter, and rank services by price, rating, or composite score across the best curated Lightning and USDC API directory. | |
| zuul-mcp clappingmonkey/zuul-mcp MCP server for Zuul CI/CD with 25 tools for builds, pipelines, queue management (enqueue/dequeue/promote), infrastructure visibility, and autohold management. Supports stdio, HTTP, and SSE transports. | |
| Mono-MCP clar1k/mono-mcp An MCP server that enables AI assistants to retrieve and format Monobank account statements and transactions by date range. | |
| Snippy clara03512/snippy Enables AI assistants to save and retrieve code snippets, generate language-specific style guides, create wiki documentation, and orchestrate multi-agent workflows for comprehensive documentation using vector search and Azure Functions MCP | |
| lattice-mcp clara672/matryoshka Enables analysis of documents far larger than an LLM's context window by letting the model emit validated S-expression commands that execute server-side over full-text-indexed handles. Supports recursive sub-queries, multi-document context | |
| Semantic Scholar MCP Server claradijkstra15479/semantic-scholar-fastmcp-mcp-server Enables searching for academic papers, authors, and citation networks through the Semantic Scholar API. Supports full-text and title search, batch lookups, citation and reference tracking, author profiles, and paper recommendations. | |
| mcp-outline clarakaneko774/mcp-outline Enables AI assistants to interact with Outline documentation services for searching, reading, creating, editing, and archiving documents, managing collections and comments, and retrieving backlinks and table-of-contents data. |
39,101–39,150 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.