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 |
|---|---|
| fast_mcp_template ayushneo/fast_mcp_template Enables MCP clients to call the app's REST endpoints as tools for listing, retrieving, and creating items, plus health checks, over Streamable HTTP. Destructive delete operations are excluded by default. | |
| Expense Tracker MCP Server ayushpaliwal1920/expensetracker_mcp_server It lets AI assistants create, retrieve, update, delete, search, and summarize expense records in a local SQLite database through natural-language requests. | |
| Expense Tracker MCP Server ayushpaliwal1920/expensetracker_remote_mcp_server Provides remote expense management and analysis with CRUD operations and summary reports. | |
| flatfind ayushrajsinghparihar/flatfind Enables agents to search Bangalore rental listings via NoBroker, inspect and analyze flat photos, check authentication status, and probe search parameters through MCP tools. | |
| Eval_MCP ayushsaha184/eval_mcp An MCP server for prompt and RAG evaluation workflows, enabling users to register, create API keys, and run evaluations via Claude Desktop, Cursor, or other MCP clients, with a hosted backend for heavy evaluation work. | |
| Claude FileMaker MCP Server ayushshah31/claude-filemaker-mcp An MCP server that connects Claude to FileMaker databases via the Data API, enabling natural language queries, record management, layout exploration, and script execution. | |
| codebase-rag-mcp ayushshanu/codebase-mcp-server An MCP server that transforms a local codebase into a queryable, citation-grounded knowledge base using hybrid FAISS and BM25 retrieval, with optional reranking and swappable LLM providers. | |
| OpsMCP ayushsharma109/opsmcp-ai-agent Enables natural-language interaction with company data stored in PostgreSQL, allowing users to query, create, update, and analyze users with secure permissions and audit logging. | |
| SEO AI Assistant ayushsinghvi92/app-seo-ai MCP server that enables AI assistants to perform SEO automation tasks including keyword research, SERP analysis, and competitor analysis through Google Ads API integration. | |
| mcp-tabular ayushsri/mcp-tabular Enables SQL querying over CSV and Excel files using DuckDB, providing tools to load files, inspect schemas, and run read-only queries via MCP. | |
| DokaAI MCP Service POC ayushsrivastava0609/dokaai-mcp-server-poc Unified MCP server providing business data APIs for Indian users, orders, and business metrics, deployable via Vercel. | |
| celo-chain-intel ayushsrivastava55/tickertape-celo-hack A paid MCP server providing AI agents with Celo chain intelligence tools (gas, token info, balances, transaction lookup, and x402 endpoint discovery) with payment via x402 on Celo. | |
| OnlineGDB MCP Server for C++ Code Execution ayushtiwari110/gdb-mcp-server Enables AI agents to execute C++ code, test solutions against multiple test cases, analyze performance, and generate test cases using OnlineGDB's online compiler. Perfect for solving competitive programming problems with iterative self-corr | |
| PRPilot ayushv7/prpilot This MCP server enables developers and AI clients to investigate public GitHub pull requests by gathering objective pull request metadata, categorized change maps, heuristic risk signals, real CI check evidence, and traced issue context. It | |
| neurochat ayushxrane/neurochat Enables natural language querying of brain volumes (NIfTI) with a fixed set of tools, returning visualizations and reproducible nilearn code. | |
| MCP Clusters API Server ayv8er/mcp-clusters-api-v1 A Model Context Protocol server implementation that provides endpoints for wallet-based authentication, cluster management, and name registration services. | |
| TTS MCP Server ayyandurai111/video-rander-mcp-server Text-to-speech MCP server using Microsoft Edge TTS, supporting multiple voices and async processing. | |
| MCP Calculator Server ayyappachinpandi/mcp-example-ayyappa A minimal Model Context Protocol server that provides basic arithmetic tools and a comprehensive meeting analysis prompt template for processing transcripts. It serves as a clean example for developers to learn how to build, test, and integ | |
| NutriVoice MCP Server ayyappanmj/nutrivoice-ai Enables users to log meals, retrieve daily nutrition summaries, receive nutrition recommendations, and resolve ambiguous food entries through standardized MCP tool calls. It supports voice-driven macro tracking and conversational disambigua | |
| Baserow MCP Server ayyazzafar/mcp-baserow MCP server enabling AI-powered Baserow database operations through natural language, with workspace, table, and row management. | |
| IslamicCorpusMCP ayzekhdawy/islamiccorpusmcp Enables querying the Quran, Tafsir (commentaries), and Hadith (sayings of Prophet Muhammad) from a relational MySQL database through natural language, using the Model Context Protocol for structured, anti-hallucination responses. | |
| PointHand ayzekhdawy/pointhand Enables AI agents to see and operate Windows applications through MCP, including windows, screenshots, mouse, keyboard, scrolling, UI Automation, clipboard, and freehand or geometric drawing. Supports supervised creative workflows with nati | |
| dhl-ops-tools az-cod/dhl_ops_mcp Enables agents and MCP clients to look up shipment tracking status, SAP order sync errors, ServiceNow incident tickets, and internal SOP runbooks through natural-language tool calls, with every execution written to a SQLite audit trail. | |
| excel-mcp az-coder-123/excel-mcp An MCP server for performing Excel file operations including read, write, and manipulation, with enterprise security features and VS Code integration. | |
| MongoDB MCP Server az-coder-123/mongodb-mcp A Model Context Protocol (MCP) server for MongoDB operations, enabling AI assistants to interact with MongoDB databases through a standardized interface. | |
| MySQL MCP Server az-coder-123/mysql-mcp A MySQL MCP server for secure database interaction, enabling schema inspection, query execution, and RBAC via AI coding assistants. | |
| PostgreSQL MCP Server az-coder-123/postgres-mcp Enables LLMs to interact deeply with PostgreSQL databases—query data, manage schema, analyze performance, and administer the database. | |
| SQL Server MCP az-coder-123/sql-server-mcp An MCP server that connects AI assistants to Microsoft SQL Server databases, enabling schema exploration and read-only queries safely. | |
| qwen3-asr az-innovation-labs/qwen3-asr-api-mcp Enables AI agents to transcribe local audio files or URLs into text with timestamps, chunking, and server status checks. | |
| my-local-mcp az-ka/my-local-mcp A local MCP server that turns AI clients into power users of local git repositories, enabling clone, browse, search, and inspect code without burning API tokens. | |
| cocos-mcp az198071123/cocos-mcp Lets AI assistants drive the Cocos Creator editor in-process: querying the live scene graph, reading and writing assets, starting builds, tailing logs, and capturing editor screenshots. | |
| Chrome DevTools MCP az9713/chrome-devtools-mcp Enables AI assistants to control and inspect a live Chrome browser for automated web debugging, performance analysis, and Lighthouse audits. It allows agents to capture screenshots, monitor network requests, and measure Core Web Vitals usin | |
| Hacker News MCP Server az9713/claude_skill_hn_mcp_server Enables AI assistants to access Hacker News content through 9 comprehensive tools for fetching stories, comments, user profiles, and job postings. Supports flexible output formats, pagination, and various story categories (top, new, best, A | |
| turbowebfetch aza-ali/turbowebfetch MCP server that lets Claude Code fetch web content using real Chrome browsers. Renders JavaScript-heavy pages, handles bot mitigation, and runs up to 14 parallel browsers locally with zero API keys. Makes outbound HTTP requests only to URLs | |
| Maya MCP azagoruyko/maya_mcp Enables inspection and editing of a running Autodesk Maya scene through tools for scene context, naming, hierarchy, connections, viewport capture, and native command execution. | |
| DevInsight MCP azalhoseinian/devinsight-mcp Enables Claude to inspect, analyze, and grade local Git repositories with tools for stats, TODO scanning, git history, large file detection, health scores, and tech stack fingerprinting. | |
| safe-db-mcp azam-ahmad-khan/safe-db-mcp Enables AI agents to run read-only SQL against SQLite or MySQL databases through MCP tools for listing tables, describing schemas, and querying data. Wraps every call in guardrails such as statement allow-listing, row caps, query timeouts, | |
| Task Tracker MCP Server azamafridi23/task-tracker-mcp Enables AI assistants to manage tasks with tools for adding, completing, and deleting tasks, and resources for viewing all or pending tasks. | |
| Agentic Ops Platform MCP Server azamali992/agentic-ops-platform Enables MCP clients like Claude Desktop to drive order, inventory, and billing operations through the same human-approval-gated tools and risk policy as the platform's LangChain agents. | |
| guardrail-mcp azambd/guardrail-mcp Enables AI coding agents to perform scoped, policy-enforced GitHub operations with allowlisted repositories and tools, protected branches, approval gates, dry runs, secret redaction, and a tamper-evident audit log. | |
| confluence-mcp-server azamlerc/confluence-mcp-server Fetches and parses confluence.org point pages, returning location data such as country, nearest place, and altitude. | |
| stickyrice-mcp azamuddin/stickyrice-mcp MCP server for Sticky Rice - interact with your notes from Claude. | |
| mcp-server-python azaok/mcp-server-python-mqyaam5x A minimal MCP server template for Python with Streamable HTTP transport, bearer token authentication, and a hello tool, designed for deployment on Render. | |
| gwb-mcp azarai-top/goworkbro-mcp Enables agents to read and write todos, habits, and countdowns on a paired phone over Bluetooth LE, and to query daily summaries, water intake, sleep records, and focus sessions. | |
| MCPX azazhang/mcpx Enables durable, crash-safe control of long-running AI-agent workflows with idempotent operations and scope-aware reconciliation over MCP filesystem and execution tools. | |
| MCP Advanced Reasoning Server azdeltaqq/mcp-reasoning-server A Model Context Protocol server that enhances Claude in Cursor AI with advanced reasoning capabilities including Monte Carlo Tree Search, Beam Search, R1 Transformer, and Hybrid Reasoning methods. | |
| booking-mcp azeem-subhani/booking-mcp Enables AI assistants to safely manage appointment bookings for appointment-based businesses over MCP, including searching availability, holding, confirming, rescheduling, and canceling bookings, and reading business policies. | |
| expense-tracker-mcp azeemwaqarrao/expense-tracker-mcp A personal expense tracker exposed over MCP, enabling users to log and query expenses in natural language sentences. It features category inference, recurring expenses, soft deletes, and SQLite storage with no external database. | |
| Splitwise MCP Server azeemwaqarrao/splitwise-mcp A server that wraps the Splitwise API so Claude can read and manage expenses, including listing, creating, updating, and deleting expenses with support for equal and custom splits. | |
| mcp-1c azeevan/mcp-1c Provides 1C configuration metadata, platform syntax, and query language reference for BSL coding agents. Resolves natural language terms to exact object names, returning structures, relationships, and version-aware method details. |
32,301–32,350 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.