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 |
|---|---|
| Glance deborahrodrigues57819/glance Gives Claude Code a real browser so it can navigate, click, type, screenshot, and visually inspect web pages directly from the terminal. It also enables multi-step test scenarios, assertions, session recording, and visual regression checks | |
| whoop-ai-mcp deborahsato161/whoop-mcp Enables read-only access to WHOOP recovery, sleep, HRV, strain and workout data through 16 tools, 4 resources and 5 prompt templates for Claude Desktop, Claude Code, Codex and GitHub Copilot. Lets users ask natural-language questions about | |
| mcp-server-atlassian-bitbucket deborahw097/mcp-server-atlassian-bitbucket Enables AI assistants to interact with Bitbucket Cloud workspaces, repositories, branches, commits, and pull requests through generic GET, POST, PUT, PATCH, DELETE, and clone tools, including reading PR diffs, adding comments, approving, me | |
| Email MCP Server debra5849/email-mcp Enables AI assistants to read, search, send, schedule, manage, and analyze mail across multiple IMAP/SMTP accounts, including drafts, provider-aware labels, real-time IDLE triage, verification-code capture, and calendar extraction. Runs ove | |
| pubmed-mcp-server debra8888/pubmed-mcp-server Enables searching PubMed and Europe PMC, fetching article metadata and full text through PMC, Europe PMC, or Unpaywall, and working with citations, related articles, MeSH terms, spelling corrections, and DOI/PMID/PMCID conversion. It runs o | |
| Niblet debra97/niblet-skill-mcp An MCP server that grounds coding-agent UI work in real product screens: it answers specific layout, state, or interaction questions with one to three real screen images, plus fonts, icons, and animated-icon materials with their recorded li | |
| SandBase CLI debraanastasiou40/cli Connects AI clients to over 2,000 models and APIs through the Model Context Protocol, enabling discovery, inspection, and execution of free data APIs and paid model calls via a local bridge with OAuth and rollback. | |
| MiniMax MCP JS debraanastasiou40/minimax-mcp-js Enables MCP-compatible clients to generate images and videos, synthesize speech, and clone or design voices through MiniMax APIs, with configurable local or URL resource handling. | |
| notebooklm-mcp debraf419/notebooklm-mcp Enables citation-backed Q&A over your own uploaded sources, on-demand generation of audio overviews, video, infographics, reports, presentations, data tables, quizzes and mind maps, plus quota-aware multi-account rotation with auto-reauth, | |
| Oh My Cassette debrah64/oh-my-cassette Enables users to turn raw video clips into finished, beat-synced montage cuts through natural-language chat, automating shot selection, music matching, subtitles, transitions, picture-in-picture, and rendering. Supports Claude Code, Codex, | |
| Instagram MCP Server debrakaraca/ig-mcp Enables AI applications to interact programmatically with Instagram Business accounts via the Graph API, covering profile and media retrieval, insights, publishing, and optional direct messaging. | |
| io.github.morluto/flameox debram03144/flameox Enables coding agents to coordinate local profilers, benchmark tools, trace processors, and direct targets, turning explicit artifacts or commands into bounded runtime evidence with provenance, coverage, and limitations. It exposes analysis | |
| WooCommerce MCP Server debraortiz9897/woocommerce-mcp-server Enables interaction with online store sites through the WordPress REST API, providing tools to manage products, orders, customers, shipping, taxes, coupons, reports, and store settings. Connects using consumer keys or WordPress credentials | |
| Vectorize MCP Server debras42745/vectorize-mcp-server Enables vector search over documents, extraction and chunking of files into Markdown, and private deep research through configured pipelines. | |
| freellmpool debratiwari790/freellmpool Exposes a pooled gateway of enabled free-tier and keyless LLM chat routes across many providers, letting MCP clients query, route, and fail over between cataloged chat models from a single OpenAI-compatible endpoint. | |
| Smart Coding MCP debraunal805/smart-coding-mcp Enables AI coding assistants to search codebases by meaning using local AI embeddings, and provides tools for package version lookup, reindexing, cache clearing, workspace switching, and status checks. | |
| MCP Weather Server debs-obrien/mcp-weather-server-demo Enables AI agents like GitHub Copilot to retrieve real-time weather data for any city using the Open-Meteo API, no API key required. | |
| tenten debuffjp/tenten Enables coding agents to create, edit, inspect, render, diff, preview, watch, and export indexed pixel-art sprites and animations as text grids through twelve MCP tools, including .tt and .aseprite import/export. | |
| Glance debugbase/glance An MCP server that gives Claude Code real browser control for web automation, testing, and screenshots. | |
| debugbase-mcp debugbase/mcp-server Enables AI agents to search and submit solutions, ask and answer questions, share findings, and vote on content via DebugBase's collective knowledge base. | |
| DebugBundle debugbundle/debugbundle DebugBundle helps AI agents investigate production incidents with deterministic debug bundles, reproductions, health checks, and diagnostics. It exposes incident inspection, bundle retrieval, and ops management tools over MCP. | |
| teaching-library debuger00/mcpdemo Provides a small educational library MCP server that demonstrates core Model Context Protocol concepts through book search, checkout, resource reading, prompts, and tool annotations, enabling developers to explore MCP mechanics interactivel | |
| Debugg AI MCP debugg-ai/debugg-ai-mcp Zero-Config, Fully AI-Managed End-to-End Testing for all code gen platforms. | |
| mcp-server-github debuggingmax/mcp-server-github A Model Context Protocol (MCP) server that enables AI assistants like Claude to interact with the GitHub API directly. | |
| @debuggingmax/mcp-server-notion debuggingmax/mcp-server-notion Comprehensive MCP server for the Notion API. Provides 22 tools for full CRUD operations on pages, databases, blocks, users, and comments. | |
| XcodeBazelMCP debugswift/xcodebazelmcp A comprehensive MCP server and CLI for Bazel-based Apple platform development, providing 112 tools across 19 workflow categories for building, testing, debugging, and managing iOS, macOS, tvOS, watchOS, visionOS, and Swift Package Manager p | |
| MCP Factory decagondev/mcp-factory An extensible Model Context Protocol server framework with a plugin architecture, enabling easy addition of API services like the bundled NASA APOD tools for astronomy content. | |
| mcp-server-usdd decentralized-usd/mcp-server-usdd Enables management of USDD protocol vaults, PSM swaps, savings, and token transfers across TRON, Ethereum, and BSC, plus protocol analytics and treasury insights. | |
| USDD Analytics MCP decentralized-usd/usdd-skills Provides 14 read-only tools to query USDD stablecoin protocol data across TRON, Ethereum, and BSC, enabling AI agents to fetch supply, APY, collateral, and vault configurations. | |
| Zcash MCP Server decentrathai/zcash-mcp-server Enables AI agents to send and receive private Zcash payments with shielded transactions, balance checks, and encrypted memos. | |
| Vault MCP Server deceptikon/vault-mcp-server Enables interaction with a file-based issue tracking and knowledge management system, allowing users to create, read, update, and move issues, as well as search and read notes within the UniHub Vault. | |
| connectsecure-mcp decian-inc/connectsecure-mcp Exposes every operation in the ConnectSecure OpenAPI specification as an MCP tool, enabling vulnerability management, assets, assessments, integrations, and reporting. | |
| curricula-mcp decian-inc/curricula-mcp Enables MCP clients to call all 44 Huntress Curricula public API operations as tools, with OAuth bearer authentication and support for production or sandbox environments. | |
| ghed-mcp decilion/ghed-mcp A Model Context Protocol (MCP) server that gives AI assistants like Claude direct access to the World Health Organization's Global Health Expenditure Database (GHED) — purpose-built for comparative health-financing research. | |
| gho-mcp decilion/gho-mcp A Model Context Protocol (MCP) server that gives AI assistants direct access to the World Health Organization's Global Health Observatory (GHO) for comparative health systems research. | |
| decisio-mcp-server decisio-app/decisio-mcp-server Enables AI assistants to perform structured decision-making using the Analytic Hierarchy Process (AHP), allowing users to define criteria, compare options pairwise, and calculate ranked results with consistency validation. | |
| decision-tune decision-tune/decision-tune Local 395M decision model as an MCP server: pick one option from a list or answer yes/no about text, or run a recipe over a CSV, XLSX or folder. Runs offline. Apache-2.0. | |
| IBM Decision Intelligence MCP Server decisionsdev/ibm-decision-intelligence-mcp-server Enables AI assistants to access and execute automated decision services from IBM Decision Intelligence or IBM Automation Decision Services. It exposes deployed decision operations as tools for platforms like Claude Desktop and IBM watsonx O | |
| IBM ODM Decision MCP Server decisionsdev/ibm-odm-decision-mcp-server Bridges IBM Operational Decision Manager with AI assistants, enabling decisions as tools for integration with platforms like Watson Orchestrate and Claude Desktop. | |
| Event Safety Check MCP Server deck6/event-safety-check-mcp Assesses event safety by providing prioritized actions, documentation needs, risk factors, and applicable regulations based on event conditions such as venue, crowd size, and setup. | |
| Learning Path Check MCP Server deck6/learning-path-check-mcp A server that enables checking and managing learning paths based on the 2022 Korean national curriculum, including child profile management, curriculum search, prerequisite tracing, and learning check creation with deterministic state asses | |
| AIShop4U decker757/buffetclearermcp Enables an AI agent to browse inventory and make purchases under strict human approval, with hard spending caps and auditable on-chain payment records. | |
| SilentFail decksaga/silentfail Diagnose MCP servers — health checks, tool testing, token cost audits, conflict detection, and security scanning with 50+ prompt injection patterns. Works as CLI or MCP server inside Claude Desktop. | |
| servicenow declade/servicenow-mcp-server MCP server that gives Claude Code tools to read, write, and configure a ServiceNow instance, enabling hands-off flow design and management via basic auth. | |
| five9-mcp declanboiston-cloud/babble-five9-mcp Enables MCP clients to manage and monitor a Five9 cloud contact center, including running campaigns, supervising agents, checking DNC lists, and building IVR call flows. | |
| inkscape declanbx/inkscape-live-mcp Lets an AI agent read and edit the Inkscape document you have open in your own window, with millimetre-exact positioning measured on live visual bounding boxes. A revision guard blocks stale edits and every change is verified as landed, all | |
| Computer Index declanfinerty/mcp-pc-index A personal file-indexing MCP server that provides semantic and keyword search over a file index, plus file content lookup and browsing. It enables agents to search and retrieve files from a user's home directory. | |
| Linux Video Editor MCP declanjeon/linux-video-editor-mcp Enables MCP-compatible agents to perform local FFmpeg-powered video editing on Linux, including probing media metadata, trimming and re-encoding clips, extracting audio to MP3, and burning SRT subtitles into MP4 files. All operations are co | |
| Homey MCP Server decline27/homey-mcp Enables AI agents to control Homey smart home devices, trigger flows, and query zones via the Homey API. | |
| React Tailwind Views MCP Server deco-cx/react-tailwind-views A full-stack template for building Model Context Protocol servers that expose tools and workflows to AI agents while also serving a web interface built with React and Tailwind CSS. |
43,251–43,300 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.