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 |
|---|---|
| set-and-signal aranlucas/set-and-signal Enables MCP clients to connect to a privacy-first, self-hostable workout planning and training log, allowing coaching agents to preview and apply program changes while accessing training data through OAuth-protected endpoints. | |
| Shipshape MCP aranlucas/shipshape-mcp Enables maintainers to prioritize maintenance across GitHub repositories by converting repository, branch, CI, security, and release signals into deterministic, evidence-backed scores and ranked actions. | |
| ClickHouse MCP Agent arannomante/clickhousemcp Enables querying ClickHouse databases using natural language with AI models, supporting multiple providers and access restrictions via per-call allow-lists. | |
| yamory MCP Server aranseshita/yamory-mcp-server Enables AI agents to query yamory vulnerability management for vulnerability detection, risk assessment, and remediation guidance. | |
| storybook-mcp aransword/storybook-mcp Enables AI agents to read and analyze local Storybook component specifications, including component listings, props, and source code examples. | |
| FHIR MCP Server aranyajenkins7342/fhir-mcp-server Enables LLM-based agents and MCP-compatible clients to query and manipulate clinical data on a FHIR-compliant backend using natural-language prompts, with full CRUD operations, document ingestion, semantic search, and LOINC terminology supp | |
| Kingdee MCP Server aranyajimenez/kingdeemcp Enables Claude, Cursor, and other AI assistants to query and operate Kingdee Cloud Star ERP in natural language through MCP tools. It supports purchasing, sales, inventory, finance, production, costs, assets, auditing, workflow, and metadat | |
| Vectorize MCP Server aranyakowalczyk/vectorize-mcp-server Enables vector search and document retrieval, text extraction and chunking of files into Markdown, and private deep research through an integrated pipeline service. | |
| loci-mcp aranyamurphy/loci Enables AI hosts and agents to search, ask, and retrieve cited sections from a locally indexed collection of notes, documents, PDFs, web pages, org files, and chat logs using hybrid vector and BM25 retrieval. | |
| Glance aranyascott/glance An MCP server that gives Claude Code a real browser, letting it navigate, click, type, capture screenshots, and run assertions to visually test web applications from the terminal. | |
| Hegelion aranyasoderberg/hegelion Enables LLMs to reason dialectically by running separate thesis, antithesis, and synthesis calls, and to build verified code through a player-coach loop where an independent verifier checks each requirement rather than trusting the implemen | |
| jevmem aranyat25/jevmem Persists decisions, rules, bugs, to-dos and dead ends from AI coding chats as lines in a repo's JEVMEM.md file, then brings the relevant ones back in later sessions. Also checks commands and file edits against the saved rules before they ru | |
| multiCAD-mcp aranyateixeira/multicad-mcp Enables users to control supported CAD applications through AI assistants using the Model Context Protocol, supporting drawing, layers, entities, blocks, files, exports, and natural-language automation. | |
| Android Source Explorer MCP Server aranyaz3902/android-source-explorer-mcp Enables AI tools to query precise AOSP and AndroidX source code on demand, including class and method lookups, hierarchy inspection, source searches, and optional cross-file navigation via LSP. | |
| Juror Cloud MCP arao32/juror Enables MCP clients to inspect workspace-scoped code review findings and hosted runs, then prepare and, after explicit confirmation, start or rerun existing hosted reviews. It provides concise review summaries without exposing raw diffs, fu | |
| Arara MCP ararahq/mcp Turns Claude Code, Claude Desktop, Cursor, Windsurf or ChatGPT into a WhatsApp operator that knows your customers, your templates, your wallet, and your funnel. | |
| lakehouse arash-yazdani/lakehouse-to-agent Enables Claude to list Iceberg tables and run read-only DuckDB SQL queries, including time travel by snapshot, with per-caller token authentication and audit logging. | |
| learners-mcp arashbehmand/learners-mcp Turns any source material into a guided learning experience with learning maps, notes, four-phase study loop, spaced repetition flashcards, and grounded Q\&A. | |
| searxng-jev-mcp arashbehmand/searxng-jev-mcp Gives coding agents a single search tool backed by a self-hosted SearXNG instance, parsing and scrubbing queries, merging duplicates, and ranking results with BM25F plus optional decision-model reranking. Returns compact, token-efficient re | |
| zotero-mcp arashgmn/zotero-mcp MCP server for interacting with a Zotero library via the local API. Enables searching, retrieving, creating, updating, and deleting Zotero items, managing collections and tags, and generating citations. | |
| MCP Zero Shot Agentic Forecaster arashnicoomanesh/zero-shot-demand-forecasting Enables zero-shot demand forecasting for supply-chain decisions, returning mean predictions, quantile bands, and confidence scores via a strictly-typed MCP tool. | |
| VerifierMCP arashomranpour/verifier_mcp Enables LLMs and agents to check their own work by calling tools instead of trusting assertions, covering symbolic math identities, sandboxed Python execution, JSON-Schema validation, dimensional analysis, and regex testing. Runs over stdio | |
| ucp-mcp-server aratan/ucp-mcp-server Let AI assistants shop. An MCP server that gives Claude, Cursor, and any MCP-compatible AI the ability to interact with UCP-enabled merchants. | |
| Kanban MCP Plugin aratasia/mcp A Kanban board MCP server and Claude Code plugin that allows AI agent teams to create, track, and manage tasks through a structured workflow. It features a web UI for real-time status monitoring and enables users to review, approve, or reje | |
| mcp-editor arathald/mcp-editor A TypeScript MCP server port of Anthropic's filesystem editing tools, allowing file manipulation via client-approved operations without automated writes to prevent system harm. | |
| Snippy araujo933/snippy Enables AI assistants like GitHub Copilot to save and retrieve code snippets with semantic vector search, and to launch multi-agent workflows that generate language-specific style guides and comprehensive wiki documentation. It exposes thes | |
| hwc-calculator araujoviana/autocalc Enables AI agents to query Huawei Cloud catalog and list prices, build quotes, and generate share links on the Huawei Cloud pricing calculator. | |
| Spenzo arav-arun/spenzo Omni-chain financial MCP server that tracks expenses, manages Web3 portfolios, simulates DEX swaps, and generates payment links via natural language in WhatsApp and Claude Desktop. | |
| Mycena aravdharnikota/mycena-mcp An MCP server that gives AI agents a shared, living memory by distilling solved tasks into reusable, verifiable skills, enabling collective intelligence and reducing redundant inference. | |
| VoiceOS Instagram Integration aravdharnikota/voiceos-instagram-integration Enables voice-controlled Instagram account management from the Mac notch, including reading insights, comments, DMs, and publishing photos or carousels via natural language, with scheduled publishing and secure photo handling. | |
| Personal MCP Hub aravind-mj/mcp_repo Enables publishing and managing authenticated HTML artifacts and creating credential-free questionnaires with signed public answer links through a unified MCP service. | |
| TheMCP-server aravind-tronix/themcp-server Enables interaction with SQLite databases, filesystem, AWS IAM, and Gmail through a master MCP server with a Streamlit UI optimized for Claude. | |
| MCP Gatekeeper aravindargutus/mcp-gatekeeper Enables users to validate MCP servers, skills, extensions, and packages for schema, security, functional, and semantic quality directly from their MCP client. | |
| inkscape_mcp aravindev/inkscape_mcp MCP server that lets AI agents drive Inkscape — interactively alongside the GUI or headlessly from the CLI | |
| Azure DevOps MCP Server aravindflash/az_devops_mcp Enables AI assistants to manage work items, repos, pull requests, pipelines, boards, wikis, and test plans through Model Context Protocol tools, resources, and prompts, supporting PAT, OAuth, Managed Identity, and Service Principal authenti | |
| dbt-investigator aravindhraja123/data-quality-agent Enables AI clients to automatically investigate dbt test failures, trace root cause through BigQuery lineage, and generate plain-English incident reports. | |
| sql-review-agent aravindhraja123/sql-review-agent Enables reviewing BigQuery SQL queries for performance issues, cost estimation, and suggested rewrites via an MCP interface. | |
| My Calculator MCP Server aravindr-k/my-calc Enables basic calculator operations such as add, subtract, multiply, and divide through an MCP interface. | |
| Amazon Price Tracker MCP aravindtri/amazon-price-tracker-mcp MCP server for tracking Amazon product prices via camelcamelcamel.com, using headless Chromium to bypass Cloudflare protection. | |
| mcp-york-county-assessor aravindtri/mcp-york-county-assessor Enables AI agents to query York County, SC property tax assessor records including owner names, property addresses, vehicle registrations, assessed values, and tax payment information. | |
| MySQL MCP Server araxiaonline/mysql-mcp A lightweight server for executing SQL queries and inspecting schemas across multiple MySQL database connections. It provides tools for managing persistent connection configurations and exploring database structures through natural language | |
| aero-vote-radar araxis33/aero-vote-radar An MCP server + CLI that reads live on-chain data from Aerodrome Finance (Base) to rank pools by veAERO vote efficiency, and recommends a vote allocation that accounts for self-dilution. | |
| MySQL MCP Server araxyai/mysql-mcp-server__9860d521cce2 Enables AI applications to securely interact with MySQL databases by listing tables, reading table contents, executing SQL queries, inspecting schemas, sampling data, and optionally using SSH tunnels. | |
| MySQL MCP Server araxyai/mysql-mcp-server__addc965daab9 Enables AI applications and clients to securely explore MySQL databases by listing tables, reading table contents, executing SQL queries, retrieving schema metadata, and sampling table data through a controlled Model Context Protocol interf | |
| kali-mcps aray84844/awsome_kali_mcpservers Enables users to run Kali-based security tools for network scanning, binary and symbol analysis, string extraction, and live or captured traffic analysis through an MCP client. It also supports isolated Docker sandbox command execution with | |
| Storyblok MCP Server arb-ec/mcp-storyblok-server Enables comprehensive management of Storyblok CMS through natural language interactions. Supports story creation and publishing, asset management, component schema updates, release workflows, and content discovery across all major Storyblok | |
| USPTO Patent MCP Server arbajian/odp-patent-mcp Enables access to USPTO patent data through multiple APIs including patent search, prosecution history, PTAB proceedings, and patent litigation. Provides 52 tools across six data sources. | |
| RAG MCP Server arbaz-builds/rag-mcp-server Exposes a Retrieval-Augmented Generation pipeline as MCP tools, allowing users to index documents and query them through any MCP-compatible client like Claude or IDEs. | |
| Australian Business Verification MCP arbazex/australian-business-verification-mcp An MCP server that provides tools to look up and verify Australian businesses using the Australian Business Register API, enabling AI agents to retrieve business details via ABN, ACN, or name search. | |
| pptx-mcp-server arbazpathan91/pptx-mcp-server A Model Context Protocol (MCP) server that lets any AI model create standardised, high-quality PowerPoint presentations via a clean JSON API. |
30,101–30,150 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.