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 |
|---|---|
| Flower MCP damel91/flower-mcp Enables coding agents to manage a persistent software lifecycle across requirements, planning, implementation, verification, acceptance, and handover, with project state stored in a SQLite ledger. It supports investigating repositories, wri | |
| MCP Weather Server damerakd/mcp-weather-server Provides tools to retrieve current weather conditions and daily forecasts for cities worldwide using the Open-Meteo API. This Python-based server enables MCP-compatible clients to access real-time meteorological data through a standardized | |
| senior-projects-manager-mcp-server damesbahahamas/senior-projects-manager-mcp Enables MCP clients to send natural-language requests to deployed Zoho Zia agents, currently the Senior Projects Manager agent, which can read and write Zoho Projects, Mail, CRM, and WorkDrive data through its trigger API. | |
| Enterprise Code Search MCP Server damian-pramparo/semantic-context-mcp Enables semantic code search across local projects and Git repositories using AI embeddings with ChromaDB. Supports both OpenAI and local Ollama models for private, enterprise-ready code analysis and similar code discovery. | |
| No MCP server described damian0475/skills-integrate-mcp-with-copilot The README is a completion certificate for the GitHub Skills exercise and does not contain any description of an MCP server. | |
| CVE-Search MCP Server damian1751/cve-search_mcp Enables querying the CVE-Search API to browse vendors and their products, retrieve vulnerabilities per vendor/product, fetch details for a specific CVE ID, and list the most recently updated CVEs with CAPEC, CWE, and CPE expansions. Also ex | |
| slop-guard damian2651/slop-guard Enables agents to score prose from 0–100 for formulaic AI writing patterns using a purely rule-based linter, returning numeric scores, band labels, specific violations with context, and concrete advice. Also supports analyzing text files on | |
| S&P 500 MCP Server damianholland/sp500-mcp-server Enables querying S&P 500 company data from Supabase, including fundamentals, annual financial metrics, historical price data, news sentiment, officers, and SEC filings. It also ships embedded MCP App UI resources with elicitation and sampli | |
| date-today-mcp damianhunziker/date-today-mcp Provides the current date in multiple formats (e.g., European, ISO, US) via a simple MCP tool. | |
| MyMCP damiankaniewski/mymcp A local, no-code builder for MCP servers that lets you create AI tools by describing them in plain language, without writing code. Connect your tools to any MCP-compatible assistant like Claude, Cursor, or VS Code Copilot. | |
| Browser MCP Server damianlevy1987-prog/browser-mcp-server Provides AI clients with browser automation, anti-detection, phone-verification bypass, proxy rotation, account creation/tracking, and 47 MCP tools over HTTP/SSE. | |
| Joplin MCP Server damiannaik0594/joplin-mcp Enables AI assistants to search, create, update, organize, tag, import, and restore notes, notebooks, and tags through a standardized protocol, with optional permission controls and notebook access restrictions. | |
| opencode-mcp damiannaik0594/opencode-mcp Connects MCP clients such as Claude, Cursor, and VS Code to OpenCode's headless API, enabling users to ask questions, implement features, run and monitor background coding jobs, handle prompts and permissions, and review changes across proj | |
| vnsh damianparker612/vnsh Enables AI agents to create, read, update, and share encrypted, version-controlled workspaces through a single link, so multiple agents and people can collaborate on the same living document without clobbering each other. | |
| Ollama MCP Server damiansahu/ollama-mcp Enables MCP-compatible assistants to manage, run, and interact with local or cloud-hosted LLM models, including chat, text generation, embeddings, model operations, and optional web search/fetch. | |
| garmin-claude-mcp damien22110/garmin-claude-mcp Lets Claude read recent Garmin activities and wellness data (sleep, HRV, resting HR) and write, edit, or delete planned structured workouts on your intervals.icu calendar, which syncs them to Garmin Connect and your watch. | |
| Substack Draft MCP Server damienbenveniste/substack-mcp Private MCP server for validating, previewing, creating, and updating Substack newsletter drafts through an MCP-compatible client. | |
| ZX84 damieng-zx/zx84 An MCP server providing a ZX Spectrum emulator for AI testing, enabling loading and running of Spectrum software with debugging, display, and audio features. | |
| cairn mcp damiensmith1/cairn Exposes read-only tools over stdio that let an agent search the user's past Claude Code sessions by keyword and meaning, open exchanges with their neighbours, brief whole sessions, and trace everything touching a file, commit, PR or URL. Th | |
| GitHub MCP Server damijanc/github-mcp Enables interacting with GitHub repositories for pull requests, code, and reviews through natural language. | |
| pagespeed-insights-mcp damijanc/pagespeed-insights-mcp This MCP server integrates Google PageSpeed Insights to analyze website performance, accessibility, best practices, SEO, and PWA on mobile and desktop, returning detailed audits and optimization opportunities. | |
| Intercom MCP Server damilola-max/intercom-mcp-server An MCP server that exposes Intercom tools to Claude Desktop and sends a daily support report via email. | |
| MCP Cloud Infrastructure & Terraform Manager damilolaadegunwa/adk-mcp-cloud-infrastructure-manager Enables Terraform HCL plan generation, drift detection, and strict human confirmation approval barriers for cloud infrastructure management. | |
| adk-mcp-enterprise-erp-bridge damilolaadegunwa/adk-mcp-enterprise-erp-bridge Enables unified access to SAP S/4HANA material management and Salesforce CRM customer telemetry through Google ADK, with schema reflection for dynamic integration. | |
| adk-mcp-gitops-release-agent damilolaadegunwa/adk-mcp-gitops-release-agent Enables automated semantic release notes, PR tagging, and changelog verification by integrating GitHub, GitLab, and Jira MCP servers. | |
| MCP Sandboxed Python Data Analyst damilolaadegunwa/adk-mcp-sandboxed-data-analyst Enables secure execution of statistical Python code in isolated micro-VM sandboxes, generating charts and analytical summaries. | |
| MCP Google Workspace Server daminigit/mcp-server-for-pulse-detector Enables AI agents to create and send Gmail messages and append content to Google Docs through the MCP protocol. | |
| LinkedIn MCP Server damionrashford/linkedin-mcp Enables direct access to LinkedIn through natural conversation, allowing users to search for people, jobs, companies, and groups, as well as view profiles using their existing Chrome browser session. | |
| RivalSearchMCP damionrashford/rivalsearchmcp Enables comprehensive web research through multi-engine search, intelligent website crawling, content analysis, trends data exploration, and automated research workflows with anti-detection measures and rich snippet detection. | |
| shopify-changelog-mcp damionrashford/shopify-changelog-mcp Provides access to Shopify Developer and Platform changelogs via RSS feeds, enabling search, category filtering, and retrieval of recent updates. | |
| emulator-mcp damipineda/emulator-mcp Enables coding agents to open the same web page across persistent mobile, tablet, and desktop viewports, interact with it, capture screenshots, inspect the accessible DOM, and run responsive layout audits without losing state between calls. | |
| DevDb MCP Server damms005/devdb-vscode A zero-config VS Code database extension with affordances to aid development and debugging. | |
| CallMeter dammy/callmeter Near-term paid hop: JSON Schema draft/validate (transform.json_schema ≈ $0.02; unpaid tools/call → HTTP 402, x402 USDC on Base). Receipt→JSON (parse.receipt ≈ $0.10) remains demo/depth. Discover tools free via tools/list; pay per tools/call | |
| Azure DevOps MCP Server dammyboss/azuredevops-mcp-server An MCP server providing 69 tools for interacting with Azure DevOps, supporting both local deployment and remote Azure Functions deployment. | |
| web-search-mcp damnhotson-tech/google-search-mcp- MCP server that enables live web search via Gemini's built-in grounding, returning synthesized answers with source citations through a single web_search tool. | |
| Minecraft Ops MCP damocjwj/minecraft-ops-mcp An MCP server for managing and operating Minecraft servers through multiple backend protocols including MCSManager API, RCON, and MSMP. It provides tools for instance lifecycle management, file operations, console commands, player administr | |
| Leantime MCP Server damonhess/mcp-leantime Enables integration with Leantime project management software, allowing users to manage projects, tickets/tasks, time tracking, sprints, and goals through MCP-compatible tools and n8n workflows. | |
| OpenProject MCP Server damonhess/mcp-openproject Enables integration with OpenProject for project management tasks including work package operations, time tracking, comments, and accessing reference data like statuses, types, and users through n8n workflows. | |
| OSSInsight MCP Server damonxue/mcp-ossinsight Provides GitHub data analysis for repositories, developers, and organizations, enabling insights into open source ecosystems through API calls and natural language queries. | |
| daft-mcp damosullivan/daft-mcp MCP server that enables AI assistants to search Irish property listings on Daft.ie via the daftlistings library. | |
| Google Search Console MCP Server damupi/mcp-gsc-oauth This MCP server provides LLMs with programmatic access to Google Search Console data and functionality, including search analytics, sitemap management, site management, and URL inspection. | |
| jumia-vendor-center damurka/jumia-vendor-mcp Enables MCP clients to manage Jumia Vendor Center catalogs and orders through natural language, including product creation/updates, inventory sync, order fulfillment, shipping labels, and payout monitoring. | |
| Buffer MCP Server damusix/buffer-mcp MCP server for Buffer social media API, allowing management of posts, channels, organizations, and ideas through natural language. | |
| mcp-dev-tools dan-0526/mcp-dev-tools Aggregates GitHub, GitLab, and Figma development tools via MCP, enabling file access, code search, and design inspection. Also supports executing standalone tasks with Claude Code or Codex CLI. | |
| ragd-mcp dan-arnold/ragd-mcp Enables Claude Code to perform fuzzy and semantic codebase search via a query_codebase tool. | |
| Todoist MCP Server dan-bailey/todoist-mcp Enables AI assistants to interact with Todoist tasks and projects through natural language. Supports comprehensive task management including creating, updating, completing tasks, managing projects, and filtering by various criteria. | |
| mcp-ytTranscript dan-camargo/mcp-yt_transcript Simple MCP server that returns the transcription of a Youtube video using url and desired language. | |
| FedRAMP Rules MCP Server dan-fedramp/fedramp-rules-mcp Answers questions about the FedRAMP Consolidated Rules for 2026 using search and retrieval tools on the authoritative source text with citations. | |
| Confluence Downloader dan-rebura/confluence-downloader Downloads Confluence Cloud pages as Markdown with images, preserving folder hierarchy and providing YAML frontmatter. | |
| confluence-markdown dan-rebura/confluence-markdown MCP server for bidirectional Markdown-to-Confluence sync, enabling download and publish of Confluence pages as Markdown with images, frontmatter tracking, and dry-run safety. |
41,801–41,850 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.