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 |
|---|---|
| csv-eda-mcp a-souhei/csv-analyst-mcp An HTTP MCP server for exploring CSV files that masks PII before any code execution, enabling safe data analysis with local or cloud LLMs. | |
| file-indexer-mcp a-souhei/file-indexer-mcp An HTTP MCP server that indexes large documents into exact-line-numbered sections, enabling AI models to locate, read, summarize, and edit parts of a document without ingesting the whole file. | |
| blender-lab-mcp-client a-to-pc/blender-lab-mcp-client MCP server for Blender that connects to the official Blender Lab add-on, exposing 27 tools for scene manipulation, object editing, materials, rendering, and Python execution through the add-on's actual wire protocol. | |
| osm-mcp a-tsitanov/osm_mcp Provides read-only query tools over OpenStreetMap data in PostGIS, enabling natural language queries for features, categories, and spatial analysis. | |
| InvoiceNinja MCP Server a-wiseguy/invoiceninja-mcp Enables read-only access to InvoiceNinja data, including invoices, expenses, clients, and tax reports, for AI assistants like Claude. | |
| MCP-CLIO a-yushko/clio-mcp Exposes Creatio CLI (CLIO) commands as tools for AI agents to manage Creatio environments. It enables users to perform environment health checks, restart web applications, and execute raw CLI commands through a stateless HTTP transport. | |
| OpenAPI Specification Docs MCP Server a-zara-n/openapi-spec-mcp-server Enables AI assistants to interact with OpenAPI documents for analysis, validation, and management through structured interfaces. | |
| azure-devops-cli-mcp a016098tony/azure-devops-cli-mcp A local MCP server that bridges Claude Desktop/Cowork to the Azure DevOps CLI, enabling full use of az devops, az repos, az boards, az pipelines, and az artifacts commands. | |
| Yahoo Finance MCP Server a05031113/yahoo-fianace-mcp Enables querying Yahoo Finance data including stock prices, historical data, financial statements, dividends, news, analyst recommendations, and company information through the yfinance library. | |
| JS Reverse MCP a0yark/js-reverse-pro-mcp A JavaScript reverse engineering MCP server that enables AI coding assistants to debug and analyze JavaScript code in web pages. | |
| mysql-readonly-mcp a1030307996-hash/mysql-mcp Read-only MySQL MCP server for safe schema inspection and SELECT-style queries. | |
| ssh-pro-mcp a1113622001/ssh-pro-mcp Enables AI agents to manage remote servers via SSH, including command execution, multi-host batch operations, SFTP file transfer, background job handling, DevOps diagnostics, port tunneling, and safety guardrails like high-risk command bloc | |
| kula MCP a12n4v/kula Enables AI agents to interact with a local-first git client that provides a knowledge graph of the repository, including graph analysis, issue and proposal management, and architectural review. | |
| beacon a1473838623/agent-beacon Provides real-time presence and collision avoidance for parallel AI coding agents, allowing them to report and query activities to avoid overlapping edits and destructive git operations. | |
| Memory MCP a157034816/memory-mcp A Rust-based MCP server that provides long-term memory capabilities for AI agents using keyword-based storage and retrieval. It supports isolated namespaces for different users or projects, allowing LLMs to remember and recall information a | |
| mcd-guard a1840436478/mcd-guard Human-in-the-loop guard proxy for the McDonald's China MCP server. Read-only tools pass through; write tools (orders, coupons, points) require local confirmation outside the AI's reach. Spending limits, read-only mode, tool blocklist, audit | |
| geo-mcp-servers a1964378/geo-mcp-servers Enables geospatial operations such as geocoding, routing, map visualization, satellite imagery, and weather data through a unified MCP interface, making Earth data accessible to non-programmers. | |
| YNAB MCP Server a1athrop/ynab-mcp Enables users to manage budgets, accounts, categories, and transactions on You Need A Budget (YNAB) through Claude. It supports both core daily budget management and extended operations like bulk transaction creation and historical trend an | |
| Sally MCP Server a1c-ai-agent/sally-mcp Enables MCP clients to interact with Sally AI assistant using x402 blockchain-based micropayments for secure, transparent transactions. | |
| Sally Skills a1c-ai-agent/sally-skills Plug Sally AI into your agent.
The clinical-grade health intelligence behind A1C Insights, Sally AI, now exposed as an MCP endpoint and REST API to your agent — 64+ biomarkers across Western clinical and TCM preventive frameworks. Authentic | |
| MyFitnessPal MCP a1dancole/myfitnesspal-mcp Enables Claude to access your MyFitnessPal diary—foods, portions, meal and daily nutrition totals, water, exercise, steps, and weight—through a custom connector on web, desktop, and mobile. | |
| Renpho Health MCP a1dancole/renpho-mcp Enables access to Renpho smart-scale body-composition data via the Renpho Health cloud API, providing metrics, trends, and diagnostics to Claude. | |
| kontra a1ex-bb/kontra Adds a challenger to your AI chat, enabling debate with multiple AI debaters to refine answers. | |
| APIUniCon MCP Connector a1exzabr/apiunicon This server enables AI assistants to interact with private services by turning API documentation into constrained, encrypted adapters. It guarantees data privacy by keeping keys local and requires user approval for any data modification. | |
| Swiss a1j9o94/swiss Swiss MCP is your AI-powered command center for orchestrating complex tasks with ease. Think of it as your personal AI assistant that can coordinate multiple AI tools to accomplish amazing things! | |
| Local Jina Reader MCP a1massist/jina-reader-mcp-local Enables agents to fetch web pages as Markdown from a self-hosted extraction service over stdio MCP, including single-page and bounded two-URL batch retrieval. It applies token limits, concurrency control, timeouts, optional API-key auth, an | |
| Redmine Analytics and Automation MCP Server a1official/mcp A comprehensive MCP server providing advanced Redmine project analytics, web automation via Playwright, and iTunes music integration. It enables detailed tracking of sprint metrics, bug counts, and team performance through a token-optimized | |
| userinyerface-mcp-server a1qa-education/userinyerface-mcp-server An MCP server that exposes test cases for the userinyerface.com capstone project, providing tools to list and retrieve test case details. | |
| figma-local-bridge a1tolia/figma-local-bridge Enables MCP clients to read and modify the currently open Figma design file through a paired local Figma plugin, supporting operations like creating nodes, editing properties, and exporting PNG/SVG. | |
| Hearsay a1vara5/hearsay Checks media-plan taste claims against Qloo audience data and returns a verdict per pick with the audience's real preferences. Also exposes what fans of one thing love in another category, so agents can validate picks before spending ad mon | |
| Codex-Control-MCP a2102502894-cyber/codex-control-mcp Enables local/remote execution infrastructure through the official Codex Runtime, providing shell, files, Git, sessions, browser, computer use, recoverable tasks, multi-host routing, dynamic MCP integration, and skill lifecycle management. | |
| MCP PostgreSQL Server a21071/mcp-postgres A Model Context Protocol server that enables performing PostgreSQL database operations (create, read, update, delete) on User and Post entities through MCP tools. | |
| What's for Dinner? MCP Server a2345sooted/whats-for-dinner Helps users decide what to eat by randomly selecting meals from a database of 100+ options or a custom list using an interactive spinning wheel widget. It supports cuisine filtering and provides an engaging visual interface to resolve mealt | |
| LocalPilot a252937166/localpilot Enables ordinary ChatGPT web Chat to work directly on a local machine over a private MCP tunnel — reading and editing project files, running shell commands and tests, loading local skills, manipulating images, and driving Chrome — without s | |
| Proofline MCP a252937166/proofline Enables AI agents to verify World Cup match evidence, check settlement readiness, purchase proof packets, and anchor results on Injective EVM testnet. | |
| MCP Trust Gateway a2a-settlement/mcp-trust-gateway Enables trust, reputation, and economic accountability for MCP by proxying between clients and servers, enriching every tool invocation with trust evaluation, KYA tiers, spending limits, and delegation chains. | |
| ClamAV MCP a2amarket/mcp-clamav A server that enables scanning files for viruses using the ClamAV engine, providing a simple integration with Cursor IDE via SSE connections. | |
| A2A MCP Server a2anet/a2a-mcp Enables Claude to connect and interact with A2A Protocol agents, allowing discovery of agent capabilities, sending messages to remote agents, managing multi-turn conversations, and viewing artifacts returned by agents. | |
| A2A MCP Server a2anet/a2amcp An MCP server that enables Claude to interact with A2A-compatible agents by providing tools to fetch agent cards, retrieve stored cards, and send messages to specific agents. | |
| moodle-mcp a2br/moodle-mcp Enables AI agents to access a student's EPFL Moodle data—deadlines, course files, assignments, forums, and grades—through read-only tools. | |
| things-mcp a2br/things-mcp Enables Claude to read and edit Things 3 to-dos by talking directly to Things Cloud, so it works with none of your devices switched on. It supports browsing Inbox, Today and other lists, searching, creating and updating to-dos, projects, he | |
| tfbash-mcp a2c-smcp/tfbash-mcp An MCP server providing stable, composable bash command execution and file operations for agents, with planned persistent PTY-based Shell tools for long-running and incremental commands. | |
| theseus-kit a2c-smcp/theseus-kit Open-source MCP server for inspecting, editing, templating, and publishing TFRobot configuration, with optional A2C-SMCP resources. | |
| CLIP STUDIO PAINT 5.1.2 Production MCP a2pha/clip-studio-paint-5.1.2-production-mcp Enables safety-gated, local MCP-driven automation of a validated Windows CLIP STUDIO PAINT 5.1.2 production environment, including screenshot inspection, UI input, shortcuts and Auto Actions, and constrained file import/export operations. | |
| netease-music-mcp a2tem1sia/netease-music-mcp Enables Claude to search NetEase Cloud Music and browse songs, albums, artists, playlists, lyrics, comments, and charts. After QR-code login it also exposes daily recommendations, liked songs, listening history, and playlist editing or song | |
| ai-act-mcp a2welt/ai-act-mcp Enables EU AI Act compliance assessment by classifying AI systems, listing obligations, computing deadlines, and scanning repos for required documentation, all running locally. | |
| verify402-mcp a32116150-ctrl/verify402 Enables AI agents to run a free fail-closed preflight gate on x402 payment challenges and transactions before signing, plus five USDC-paid on-chain truth checks covering arbitrage profitability, token safety, swap routing, quote validation, | |
| skillcheck a32fred/skillcheck Enables AI agents to validate HTTP(S) links referenced in Markdown files and directories through the Model Context Protocol, detecting broken links and returning structured JSON results. Supports configurable concurrency, timeouts, and igno | |
| MCP PDF Reader a3339530357/mcp_pdf_reader Intelligent PDF processing server that automatically detects PDF types (text or scanned), extracts text, performs OCR recognition in 10 languages, searches content with regex support, and retrieves metadata through the Model Context Protoco | |
| qenlo-memory a3ro-dev/qenlo-memory Provides a shared local memory MCP server so multiple coding agents can store, retrieve, and attribute memories across sessions. It enables agents to recall project knowledge and past fixes with provenance. |
22,501–22,550 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.