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 |
|---|---|
| paid-mcp-gate danielhurnik/paid-mcp-gate Enables AI agents to search a proprietary knowledge base for free and buy access to documents or passages on demand, with automatic payment, licensing, and citation. | |
| FluentBoards MCP Server danieliser/fluent-boards-mcp-server Enables AI assistants to manage FluentBoards project management through WordPress REST API, supporting board operations, task management, comments, and labels with advanced safety controls and board focus mode. | |
| Israel Grocery MCP danieljl-altius/israelgrocerymcp Enables cross-store price comparison and recipe-driven cart automation for Israeli grocery stores Shufersal and Tiv Taam, with an extensible architecture for additional stores. | |
| Tiv Taam MCP Server danieljl-altius/tivtaammcp Enables shopping at Tiv Taam grocery store through Claude, including recipe parsing and cart population. | |
| clinical-evidence-mcp danielk-am/clinical-evidence-mcp Searches medical literature, clinical trials, drug labels, and adverse-event reports via official public APIs, returning structured records with source URLs and timestamps. | |
| @openbnb/mcp-server-airbnb danielk-am/mcp-server-airbnb Enables Airbnb searches with location, date, guest, price, and property type filters, and retrieval of detailed listing information such as amenities, house rules, and direct booking links. | |
| wireless-sgx danielk-am/wireless-sgx-explorer Enables MCP clients to explore a source-backed catalogue of Singapore hotspot venues through read-only tools for ranking nearby locations, searching venues and floor details, retrieving entries, and inspecting dataset provenance over stdio | |
| WordPress Block Catalog MCP danielk-am/wp-block-catalog-mcp A read-only MCP server that provides verified WordPress block definitions and markup across product environments, enabling search, comparison, generation, and validation of blocks. | |
| ReaMCP danielkinahan/reamcp An MCP server that enables users to control and edit REAPER projects through a Python-based interface and a Lua bridge. It supports managing tracks, controlling transport, manipulating MIDI and audio items, and adjusting FX parameters withi | |
| mcp-server-for-powershell danielklecha/mcp-server-for-powershell Unofficial Powershell MCP server | |
| Cookidoo MCP Server danielkliem/mcp-cookidoo Lets Claude read recipes from your Cookidoo account and create TM7-optimized custom recipes with guided-cooking annotations, quality scoring, and automatic rollback on upload failure. | |
| claude-tws-connect danielkristofik/mcp_claude_ibkr An MCP server that enables interaction with Interactive Brokers TWS/Gateway via natural language for portfolio management and market data retrieval. It provides tools for account summaries, historical data, and a secure two-step confirmatio | |
| io.github.morluto/flameox daniellaurent02/flameox Enables coding agents to coordinate profilers, benchmarks, trace processors, and direct local targets, turning explicit artifacts or commands into bounded runtime evidence with typed results, provenance, coverage, and optional durable prese | |
| FrameIO MCP Server danielldt/frameio-mcp MCP server for generating and validating FrameIO modules and plugins, with code generation, validation, examples, and step-by-step guidance. | |
| Ollama MCP Server daniellemorita48217/ollama-mcp Enables MCP-compatible clients to manage and run local or cloud LLMs, generate completions and embeddings, and perform web search/fetch through exposed tools. | |
| local-claude-chat-history-mcp daniellmorris/local-claude-chat-history-mcp Searches and browses local Claude Code and Cowork session histories stored on your machine, enabling questions about past work without uploading data. | |
| Fillout.io MCP Server danielma-tic/fillout-mcp-server Enables form management, response handling, and analytics through the Fillout.io API for enhanced form interactions and insights. | |
| garmin-athletics-mcp danielmcewan/garmin-athletics-mcp A private, read-only MCP server that gives local Codex and Claude Desktop sessions access to athletics and wellness data from a Garmin Forerunner 55. It runs locally over stdio, exposes read-only tools for daily health, recovery, performanc | |
| todo-txt-mcp danielmeint/todo-txt-mcp Connects AI assistants to todo.txt files, enabling task management through natural language while preserving plain text simplicity. | |
| Enhanced Fetch MCP danielmelody/enhanced-fetch-mcp Provides advanced web scraping with HTTP client, smart content extraction to Markdown, browser automation via Playwright, screenshot/PDF generation, and Docker sandbox execution environments. | |
| ABAP ADT API MCP Server danielmendoza79/mcp-abap-abap-adt-api-main Enables MCP clients to work with SAP systems through development-tool APIs for object search, source retrieval and editing, syntax checks, activation, transports, debugging, refactoring, Git operations, and analysis within a single SAP sess | |
| platform-eng-copilot danielmeppiel/agentic-platform-engineering Enables platform engineering workflows via GitHub Copilot, including creating repositories from templates and provisioning Azure deployment environments. | |
| Oracle DB Context MCP Server danielmeppiel/oracle-mcp-server Provides contextual database schema information for large Oracle databases, enabling AI assistants to understand and work with databases containing thousands of tables. | |
| Camoufox Browser MCP danielmiranda/camoufox-browser-mcp Provides stealthy browser automation capabilities using a custom Firefox build designed for anti-detection. It enables users to navigate pages, interact with elements, and manage persistent browser sessions through natural language. | |
| hecras-mcp danielmiranda2017-tech/hecras-mcp Enables Claude to drive HEC-RAS headless — inspecting projects, validating and executing 1D steady, 1D unsteady and 2D plans, and reading hydraulic results from HDF5 files. It also supports limited model modification, such as setting steady | |
| qgis-mcp danielmiranda2017-tech/qgis-mcp Enables Claude to work with QGIS 4.x headlessly by loading vector and raster layers, running Processing algorithms and field calculations, styling layers, and exporting maps or PDF layouts without opening QGIS Desktop. | |
| magnolia-docs-mcp danielnaranjo/magnolia-docs-mcp Enables AI assistants to search and retrieve information from the official Magnolia CMS documentation through a set of MCP tools. | |
| personal-agents-bridge danielnguyen/personal-agents-bridge Enables ChatGPT to drive sandboxed coding tasks via the Agents API, with independent review and exact-tree draft pull request publication for allowlisted repositories. | |
| Video MCP danielnguyenfinhub/video-mcp A local MCP server that gives Claude Desktop full video editing capabilities via FFmpeg, Whisper, and yt-dlp. | |
| uvxwebsearchmcp danielnmc/web_tools_mcp A zero-config web search and fetch MCP server for LLM agents, featuring multi-backend metasearch, persistent rolling cache, and structured error envelopes for retry-friendly interactions. | |
| Image Context Runtime danielolsson619/codex-image-context-runtime Enables Codex to run image generation and inspection as durable, resumable local jobs whose provider-returned media bytes stay behind the MCP boundary. Callers receive only bounded text handoffs, hashes, relative references, and Job IDs ins | |
| Teams MCP danielolsson619/teams-mcp Enables AI assistants to interact with Microsoft Teams and Microsoft Graph, covering chats and channel messaging, message search, user and team member lookups, and file upload or attachment downloads. Supports OAuth device-code authenticati | |
| Zotero MCP Server danielostrow/zotero-mcp-server Enables AI assistants to search, cite, and manage research references directly from a Zotero library. | |
| Finance MCP Server danielotony/finance-mcp-server Enables an LLM to inspect a relational database schema and answer financial questions by running validated, read-only SQL queries against a synthetic SQLite dataset. | |
| agent-intel-mcp danieloza/agent-intel-mcp An OpenAI-powered developer intelligence MCP server that scans GitHub repositories, extracts and clusters agent engineering patterns, analyzes local codebases, and proposes safe AGENTS.md improvements. | |
| FirstData MCP danielpanagiotou86205/firstdata Enables AI agents to turn natural-language data questions into authoritative primary-source recommendations with metadata, access URLs/API details, and step-by-step website navigation for retrieving original data. It helps integrate this so | |
| ClinicFlow AI danielpdev/clinicflow-ai Exposes availability and appointment-proposal tools over stdio so an MCP client can query open slots and suggest bookings, without being able to create them—actual booking requires human confirmation through the separate UI/API. Slot claims | |
| MCP Business Tools danielpdev/mcp-business-tools Exposes typed inventory reads and order preparation over MCP, with capability scopes enforced by the server process rather than tool arguments. Stock is committed only through a separate operator approval surface, keeping approval outside t | |
| JSONPlaceholder MCP Server danielpdev/mcp-jsonplaceholder Provides access to JSONPlaceholder's free fake REST API for testing and prototyping, enabling interaction with sample posts, users, comments, albums, photos, and todos through tools, resources, and prompts. | |
| editor-mcp danielpodrazka/editor-mcp A Python-based text editor server built with FastMCP that provides tools for file operations. This server enables reading, editing, and managing text files through a standardized API following a multi-step process. | |
| MCP_CAD danielproxd2/mcp_cad A SolidWorks-resident AI copilot for Mexican autoparts manufacturing PYMEs that enables Spanish-speaking junior CAD designers to interact with SolidWorks through chat for assembly mating, configurations, sketching, and other operations usin | |
| MCP_CAD danielproxd2/solidworks-mcp A local MCP server for controlled SOLIDWORKS automation, exposing typed operations for parts, assemblies, configurations, drawings, inspection, and verification. | |
| PokémonGPT MCP danielqingz/pokemongpt-mcp Enables AI assistants to search live Pokémon TCG card data and TCGplayer market prices, including Japanese cards and sealed products, through natural-language queries in multiple languages. | |
| NixOS MCP Server danielramosacosta/nixos-mcp Enables searching and retrieving NixOS configuration options using the official NixOS search API. It provides detailed metadata including option types, default values, and descriptions with full support for paginated results. | |
| xero-mcp-enhanced danielreddd/xero-mcp-enhanced An enhanced MCP server for Xero, enabling natural language interaction with your Xero organisation for accounting tasks like invoices, contacts, bank transactions, and payroll. | |
| repohunt danielrltan/repohunt Enables AI agents to discover GitHub repositories by expanding intents into multiple keyword queries, searching GitHub's live Search API, and returning deduplicated, ranked candidates with README excerpts and metadata. | |
| stratomcp danielrohregger/strato-mcp Enables users to search, read, organize, and draft email in Strato mailboxes from Claude, using a local full-text index and live IMAP search while keeping credentials in macOS Keychain and sending disabled by default. | |
| Agent Junction danielrosehill/agent-junction Enables Claude Code instances to communicate directly via an ephemeral, encrypted peer-to-peer message bus. Works on localhost or across your LAN. | |
| BTRFS Snapper MCP danielrosehill/btrfs-snapper-mcp Enables management of BTRFS snapshots via Snapper and monitoring of BTRFS filesystem health through the Model Context Protocol. | |
| donetick-mcp danielrosehill/donetick-mcp MCP server for Donetick chores management. Provides 27 tools to control Donetick instance via Claude or other MCP clients. |
42,001–42,050 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.