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 |
|---|---|
| resolve402-mcp charleskremer-hub/resolve402-mcp French company data for AI agents: directors with probable business email, people search, counterparty checks (KYB) and hiring signals from official registries. Paid per call with x402 (USDC on Base or Solana), charged only when found. | |
| Klipper MCP Server charleslotto/klipper-mcp An MCP server that enables AI assistants to control and monitor Klipper 3D printers via the Moonraker API. It supports comprehensive printer management, including G-code execution, toolchanger operations, and real-time status monitoring. | |
| 2Bot charlesmichaelbaird/2bot-mcp Enables ChatGPT to execute Codex CLI prompts locally through a secure MCP tool, with support for both local stdio and remote HTTP modes. | |
| conformidade-pbtr-mcp charlesmmorais/conformidade-pbtr-mcp MCP server for automated compliance analysis of Basic Projects and Terms of Reference against SERPRO's checklist. Send a PDF and get a compliance index, prioritized findings, and reports in multiple formats. | |
| Coppermind charlesmmorais/coppermind Enables AI assistants to design PCBs in KiCAD through natural language, with transactional preview-verify-commit workflow, undo/redo, and an engineering knowledge base. | |
| TeleMCP charlesmmorais/telemcp Enables AI agents to search and act on Telegram conversations, groups, channels, files, and links, with semantic search, AI-powered knowledge extraction, human-in-the-loop approvals, and PostgreSQL/pgvector persistence. | |
| speak-to-me-mcp charlesmooredev/speak-to-me-mcp This MCP server enables Claude to speak summaries, announcements, and explanations aloud using text-to-speech — right from your terminal. | |
| GitHub MCP charlesnpx/github-mcp Enables self-hosted, read-only remote interaction with GitHub repositories, allowing listing repositories, searching code, and inspecting commits, pull requests, issues, and diffs via authenticated MCP clients. | |
| QuickBooks MCP Server charlespiccionebtp/local-mcp-server-for-quickbooks-sandbox This MCP server enables users to ask natural-language questions about their QuickBooks Online company and receive answers from its live data, with read-only access guaranteed by construction. It runs entirely locally, using tools for receiv | |
| phi-guard-mcp charlesree826/phi-guard-mcp MCP server and CLI for detecting, redacting, and auditing PHI in medical text before it reaches AI agents. | |
| project-manager charlesribeiro/day1-claude-code-mcp-lab Enables project task management through MCP tools to create, list, and update tasks, with SQLite persistence. | |
| memex charlesschaefer58482/memex An MCP server that gives AI coding agents persistent, cross-session memory by letting them save task insights as atomic markdown knowledge cards with bidirectional links and recall relevant cards before starting new work. Stores everything | |
| WhatsApp Channel charlessingh/whatsapp-claude-plugin Turns a Claude Code session into a two-way WhatsApp endpoint, letting users send and receive messages, media, and voice notes from chat while strangers are blocked by pairing codes and allowlists, and tool-permission prompts are approved or | |
| SerpApi MCP Server charlesstone424/serpapi-mcp Enables AI assistants to run real-time searches across Google, Bing, Yahoo, DuckDuckGo, YouTube, eBay and many other engines, returning structured JSON or token-efficient Markdown for organic results, news, images, shopping, weather, and st | |
| mymcpservercli charlesthebird/mymcpservercli A Model Context Protocol server framework featuring dynamic tool loading and automatic tool discovery from a dedicated directory. It leverages FastMCP to provide a robust environment for building, configuring, and testing individual Python- | |
| multiCAD-mcp charlesvargas54625/multicad-mcp Enables AI assistants to control supported CAD applications through natural-language instructions and unified MCP tools for drawing, layers, blocks, entities, files, and data export. | |
| aliasflare charleswei118/aliasflare Self-hosted email aliases on Cloudflare Workers (free tier). Agents can create/list/delete aliases, read recent messages and fetch verification codes. | |
| protoflow charlesye8848/protoflow Enables AI assistants to create interactive prototypes, annotate UI elements, generate PRDs, and track which annotations and documents need updating after changes. | |
| mcp-builder-mcp charley-forey-ai/mcp-builder-mcp Provides OpenAPI validation and analysis tools to assist developers in building Model Context Protocol servers. It generates developer context and specific agent prompts based on API specifications to streamline the creation of agentic work | |
| ProjectSight MCP Server charley-forey-ai/projectsight-mcp Provides access to the ProjectSight API for managing construction portfolios, projects, and records like ActionItems, RFIs, and Submittals. It features a modular architecture supporting CRUD operations, workflow state management, and OAuth2 | |
| mcp-server-demo charley-forey/mcp-builder-mcp Validates OpenAPI specs from files, inline content, or URLs, and generates prompts for agent developers based on the API analysis. | |
| MCP Mistral OCR charley-forey/mistral-ocr-mcp Provides OCR capabilities for images and PDFs using Mistral AI's OCR API, supporting both local files and URLs with output in markdown or JSON format. | |
| openapi-mcp-builder charley-forey/openapi-mcp Enables users to convert any OpenAPI or Swagger spec URL into a hosted MCP server on the Agentic Tools Platform, with tools for analyzing, trimming, and managing OpenAPI specifications. | |
| Salesforce Support MCP charley-forey/salesforce-support-mcp Provides an interactive support form that creates Salesforce Case records via the Salesforce REST API, supporting multiple authentication strategies. | |
| MCP Weather Server charley-forey/weather-mcp Provides hourly weather forecasts using the AccuWeather API, including current conditions and 12-hour forecast with precipitation details. | |
| web-search-mcp charley-forey/web-search-mcp Provides multi-provider web search capabilities with fallback chains, semantic reranking, and content extraction for grounded agent retrieval. | |
| ai-usage-metrics-mcp charlie-818/ai-history-mcp A MCP server for tracking AI usage metrics and structured logs across applications. Monitor model calls, analyze usage patterns, track costs, and debug AI interactions. | |
| gpt-game-arena charlie2233/turnplay-arena This MCP server enables playing chess, Quick Go (9x9), Go (13x13), and Real Go (19x19) against GPT, with a React widget UI, deterministic difficulty-aware move selection, and authoritative rules/session handling for both ChatGPT plugin and | |
| derive-options-mcp charlie85270/derive-options-mcp Enables users to describe a market view and get real option structures priced against live order books, sized to budget, with payoff diagrams and worst-case outcomes. | |
| mcp-SafeLink charliebot8888/safelink SafeLink lets AI agents hire other AI agents — and get hired — with cryptographic guarantees instead of trust. Every hire goes through a payment-locked escrow, a proof-of-work verification step, and a tiered risk approval gate before any fu | |
| edamcp charliecpeterson/edamcp An MCP server for Exploratory Data Analysis that automatically profiles datasets, detects quality issues, PII, bias, and leakage, and provides cleaning and export workflows. It helps data scientists quickly understand and prepare unknown da | |
| design-canvas-mcp charlieellington/design-canvas-mcp Enables AI agents to manage routes on the Design Canvas infinite canvas app, including adding, removing, listing routes, and capturing screenshots of the canvas. | |
| CloudWatch MCP Server charliefng/cloudwatch-mcp A simplified MCP server that provides a streamlined way to interact with AWS CloudWatch resources (log groups, log queries, and alarms) through the MCP protocol. | |
| Shipboard charliehorton/shipboard Enables AI coding agents to access and update a shared local database for tracking pull requests and work items across repositories. | |
| threejs-mcp charliekerfoot/threejs-mcp Enables AI assistants to generate and modify Three.js 3D scenes by providing a wide range of tools for scene setup, cameras, geometry, materials, lighting, controls, loaders, animation, interaction, helpers, post-processing, environment, UI | |
| Finey charliekmcmahon/finey Enables querying linked bank account balances and transactions through MCP tools, with manual sync and read-only access from any MCP client. | |
| academic-research-plugin charlielin-fan/academic-research-plugin A stdio MCP server for traceable scholarly retrieval and evidence-grounded literature review, with deterministic provider fusion, conservative ID canonicalization, and provenance-preserving citation traversal. | |
| tscircuit MCP Server charlielockyer-rice/tscircuit-mcp Provides Claude with access to the tscircuit electronics component registry, enabling search, browsing, and analysis of electronic components and circuit packages from the tscircuit ecosystem. | |
| Pretty Prompt MCP Server charliemday/pretty-mcp Exposes tools to list and save prompts from the Pretty Prompt library, enabling integration with AI editors like Cursor and Claude Desktop. | |
| Tableau MCP charliemhjeong/tableau-mcp Enables integration with Tableau to query data, explore workbook content, and retrieve visualization images through natural language. It provides developer primitives for building AI applications that interact seamlessly with Tableau server | |
| testing-mcp charlienearform/testing-mcp MCP server that enables AI agents to programmatically run tests, query results, and receive intelligent recommendations about test execution strategy. | |
| zhupi-mcp charliezong18/menxia-mcp Agent-side MCP server for the zhupi review loop, enabling AI agents to submit documents, read annotations, and reply via GitHub. | |
| SerpApi MCP Server charlottea043/serpapi-mcp Enables MCP clients to run searches across Google, Bing, Yahoo, DuckDuckGo, YouTube, eBay, and other engines, returning automatically detected and formatted JSON or Markdown results for answer boxes, organic results, news, images, shopping, | |
| Gitingest-MCP charlotteaksoy/gitingest-mcp Enables MCP clients to quickly extract GitHub repository summaries, project directory structures, and file contents. It supports clients such as Claude Desktop, Cline, and Cursor. | |
| mcp-shodan charlottec78065/mcp-shodan Enables AI agents to query the Shodan API and Shodan CVEDB for internet-connected device search, host reconnaissance (open ports, banners, TLS certificates, cloud provider), domain and DNS lookups, and vulnerability intelligence with CVSS, | |
| MCP-PostgreSQL-Ops charlottedejager60506/mcp-postgresql-ops Enables AI assistants to perform read-only PostgreSQL DBA work across versions 12–18, including performance analysis, slow query identification, bloat detection, lock and deadlock monitoring, autovacuum and schema inspection, and replicatio | |
| Luma MCP charlottei86007/luma-mcp Adds image understanding to AI coding assistants that lack native vision, letting them analyze screenshots of code, errors, UIs, and documents through a single image_understand tool. Supports multiple mainstream vision LLM providers, with a | |
| whoop-ai-mcp charlottekose/whoop-mcp Enables Claude, Codex, and GitHub Copilot to query WHOOP recovery, sleep, HRV, strain, and workouts through read-only tools, including daily summaries, personal baselines, trends, and HYROX/triathlon performance insights. | |
| threejs-devtools-mcp charlottelundberg/threejs-devtools-mcp Enables AI agents to inspect, live-preview, and debug Three.js and React Three Fiber scenes in a running browser, then convert the changes they keep into ready-to-paste code. Also supports website performance audits, video frame capture, an | |
| kali-mcps charlotteo2975/awsome_kali_mcpservers This MCP server enables security researchers and developers to run Kali Linux tools such as Nmap, nm, objdump, strings, and tshark through MCP clients for network scanning, binary analysis, string extraction, live packet capture, and isolat |
38,001–38,050 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.