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 |
|---|---|
| mcp-postgres divinedev111/mcp-postgres Enables AI agents to interact with PostgreSQL databases through schema intelligence, query execution, and DBA tooling including index analysis and health monitoring. Features configurable access levels and audit logging for secure database | |
| DivMagic MCP divmagiccom/mcp Enables copying any component from a live web page as clean, self-contained HTML or JSX with configurable styling, directly from an AI agent. | |
| Memory Store MCP Server divslingerx/mcp-server A lightweight, stateless MCP server utilizing Puppeteer for web searches, returning structured JSON results, easily integratable with other MCP-enabled systems. | |
| Convyy MCP divulture/convyy-mcp Enables AI agents to create and manage Convyy boards, including diagrams, kanban boards, journey maps, and more, through MCP tools like convyy_run_prompt. | |
| Divvi MCP Server divvi-xyz/divvi-mcp-server Enables AI assistants to automatically integrate Divvi referral tracking into JavaScript/TypeScript blockchain applications by guiding them through SDK installation, transaction modification, and implementation of referral submission follow | |
| coding-agent divya-shr/coding-agent Enables external AI clients to invoke an autonomous coding agent that plans, fixes, and self-corrects code in an isolated Docker sandbox via run_task and run_tests tools. | |
| mcp-learning-path-generator divya252007/mcp-learning-path-generator Generates personalized learning paths with day-by-day roadmaps, concepts, tasks, project ideas, and resource links based on topic, duration, and level. | |
| MCP-Studio divyag14/mcp-studio A collection of MCP servers that provide mathematical operations and weather information tools, enabling AI models to perform calculations and access weather data through a standardized interface. | |
| Spotify-Claude MCP Server divyamagg24/spotifymcp A tool that connects to the Spotify API and enables Claude to access artist information for enhanced music discovery through natural language queries. | |
| PayVoice Collections MCP Server divyan2211/mcp_server Exposes a save_collection tool to store collection data in Supabase, enabling payment commitment and callback tracking. | |
| SQL Insights MCP Server divyankmalik/sql-mcp-server Enables AI agents to query Postgres databases read-only over the Model Context Protocol through three narrow tools, validating every statement as a single SELECT with an enforced row limit before it reaches the database. Guards against dest | |
| powerbi-mcp-server divyansh-dev12/powerbi-mcp-server An MCP server that connects Claude and other MCP clients to Microsoft Power BI via its REST API using a Service Principal, enabling natural language queries to list workspaces, run DAX queries, refresh datasets, and explore reports. | |
| GitHub MCP Assistant divyanshagarwal7/github-mcp-server Enables Claude Desktop to analyze repositories, fetch and create issues, inspect pull request diffs, and comment on pull requests through the GitHub API using natural-language commands. | |
| Document Q&A MCP Server divyanshedunext/mcp-server Enables users to ingest PDF/DOCX/TXT/MD documents and ask natural language questions about them, using local embeddings and Groq-powered retrieval-augmented generation. | |
| GitHub MCP Server divyanshkushwaha/github-mcp-server-claude A modular command processor server that enables interaction with GitHub's REST API to fetch user details, repository information, and authenticated user data through natural language commands in Claude. | |
| GitPilot MCP divyanshu-hash/gitpilot-mcp An autonomous agent that automates GitHub contributions end-to-end, from issue analysis and code changes to pull requests, conflict resolution, and review updates. | |
| Antardrishti divyanshu-iitian/antardrishti Enables AI agents to locally analyze and reverse engineer binaries through a compact 12-tool MCP interface for triage, function discovery, disassembly/decompilation, cross-references, strings/imports, call graphs, memory reads, annotations, | |
| ContextFlux divyanshu-iitian/contextflux Task-adaptive repository context for coding agents, enabling budgeted evidence retrieval without API keys or network calls. | |
| VTOP Bhopal MCP divyarthjain/vtop-bhopal-mcp Enables AI assistants to log in to a student's VIT Bhopal academic portal and fetch attendance, marks, timetable, exam schedules, grades, calendar, and profile data. It also calculates bunk allowances, OD usage, and GPA/CGPA projections. | |
| ServiceNow MCP Server divyashah0510/mcp-server-servicenow A ServiceNow integration server for the Model Context Protocol that enables automated incident management, knowledge base article creation, and other ServiceNow operations through a standardized protocol. | |
| Vaani-Pay MCP Server divyaupadhyay56/vaani-pay Enables secure, bilingual AI assistants to query and manage payments, orders, refunds, transactions, wallets, fraud risk, and statistics with per-user data isolation enforced on every tool call. | |
| YouTube MCP Server divyav18/youtube-mcp Enables interaction with YouTube's Data API through MCP, providing tools for channel info, videos, playlists, captions, subscriptions, and more. | |
| MCP Analyzer Server divyesh-0x01/mcp-minimal Provides security analysis and malicious tool detection for MCP tools with context-aware detection, behavioral pattern analysis, and risk scoring. | |
| llm-prompt-optimizer divyesh-freelance/llm-prompt-optimizer A deterministic prompt optimization middleware for AI coding agents that preserves intent, compresses context, and detects drift, available as an MCP server with tools for optimize_prompt, classify_prompt, and more. | |
| Serpex MCP divyeshradadiya/serpex-mcp Enables multi-engine web search capabilities across Google, Bing, DuckDuckGo, Brave, Yahoo, and Yandex through the Serpex API. Features automatic engine routing, time filtering, and structured JSON results for reliable web search integratio | |
| Website-to-Agent MCP Bridge divyuuu/website-to-agent It enables AI agents to call a small set of reliable, permission-aware tools generated from an existing website through the Model Context Protocol, without rebuilding the site. | |
| India Stock MCP Server diwakarreddy11/india-stock-mcp Enables AI assistants to pull live NSE/BSE market data over Streamable HTTP, including stock quotes, OHLCV price history, technical indicators, fundamentals, multi-stock comparisons, and index overviews. It also reports whether the exchange | |
| ContextFlow MCP Server diwakarsrd/contextflow Enables MCP-compatible agents such as Claude and Cursor to retrieve permission-aware, structured context from local or hosted data stores. Exposes tools for semantic search, entity and relationship lookup, memory access, context pack compil | |
| Meridian-KG MCP Server diwakarsrd/meridian-kg Enables agentic retrieval over governed enterprise documents via a knowledge graph, with cross-silo orchestration, conflict detection, and audit trails. Exposes MCP tools like query_knowledge_graph, list_detected_conflicts, and get_audit_tr | |
| MCP Mermaid ER Server dixitayush/mcp-api Parses Mermaid ER diagrams to create PostgreSQL tables and automatically generates REST and GraphQL CRUD APIs. | |
| Siri Shortcuts MCP Server dixon405/mcp-server-siri-shortcuts Enables LLMs to list, open, and run shortcuts from the macOS Shortcuts app, including dynamically generated tools for every shortcut installed on the system. Shortcuts can be invoked by name or UUID with optional text or file input. | |
| Deep Code Reasoning MCP Server dixon77261/deep-code-reasoning-mcp Enables Claude Code to escalate complex code analysis tasks to Gemini for large-context reasoning, execution-flow tracing, cross-system impact analysis, performance bottleneck detection, and hypothesis testing, including AI-to-AI conversati | |
| ratduck-search-mcp dixonsolutions/ratduck-search-mcp An MCP server that gives an agent the open web: searches DuckDuckGo via its no-JavaScript front end, scrapes any URL, and filters/re-ranks results to deliver the top few instead of a wall of links. | |
| Cryptocurrency MCP Server diya28-mehra/crypto_mcp_server Python-based MCP server that provides real-time and historical cryptocurrency data from 100+ exchanges via CCXT, with tools for tickers, OHLCV, markets, and order books. | |
| contextpulse-mcp diya73/contextpulse-mcp Real-time context budget tracking for AI coding agents with token counting, loop detection, and alerts, backed by PostgreSQL. | |
| data-report-mcp diyaluo/data-report-mcp Turns a local CSV or XLSX table into a full analysis report — summary statistics, duplicate and missing-value diagnostics, top category frequencies, significant pairwise correlations, a Markdown insights writeup, and an Excel workbook with | |
| ai-travel-policy-assistant diyamohandas/ai-travel-policy-assistant Enables employee eligibility checks, trip validation, and reimbursement calculations for corporate travel policies. | |
| MCP Server with File Search Tool diyorap/mcp-server A Model Context Protocol server providing file search and question tools for AI models. Enables keyword search in files with line numbers and integration with external chat services. | |
| ChartNexus MCP Server diysimon/genui-for-echarts Provides a local stdio MCP interface for Apache ECharts infrastructure, enabling language models and agents to access chart-related tools and resources. | |
| c2b dizeldz20-ux/agent-shared-memory Enables Claude to recall context from a merged knowledge graph of your Obsidian vault and code projects, providing tools to search, find neighbors, and discover paths before editing files. Works offline by reading a local brain.json. | |
| Dizko Events MCP dizko-labs/dizko-mcp MCP server that provides live event search, explainable recommendations, night planning, and agentic ticket purchase with safety rails, using Dizko's event inventory. | |
| 0pi-mcp-server dizzydes/0pi-mcp-server Store and retrieve data objects for free. Temporary cloud storage for agents. Two hour expiry. Works with any format and flow.
Example use cases include:
* Manage large datasets across different sessions
* Generate shareable links for inte | |
| Landlord dizzymii/landlord An MCP server that orchestrates parallel Claude agent sessions by decomposing natural-language tasks into contract-bound tenants with structured outputs and validation, all running over stdio. | |
| dizzyvinci/apify-foundry Provides two MCP servers: Shopify Catalog Monitor for tracking product changes and US Building Permit Aggregator for construction permit data from 9 US cities. | |
| tuanjie-mcp dj-huang/tuanjie-mcp Enables AI tools to connect to and control Unity/Tuanjie editors via the Codely Bridge TCP server, supporting project management, scene manipulation, and console reading. | |
| GSI Vector Tile MCP App dj-oyu/elysiajs-gsi-gov Enables interactive GSI map viewing with layer switching, location search, and tile info retrieval within chat. | |
| esp32s3-hw-mcp dj-oyu/esp32s3-hw-mcp Enables agents to look up ESP32-S3 PIE instruction encodings, pipeline use/def stages, register and peripheral-address data, and to estimate instruction-sequence stalls, with every answer cited to a specific page of the official Espressif T | |
| mcpfold dj-pearson/mcpfold Local-first CLI + proxy that curates your MCP servers per client from one canonical config, cutting tool-schema tokens ~80% and resolving secret references instead of hardcoding keys. | |
| Supabase Coolify MCP Server dj-pearson/supabase-coolify-mcp-server Enables comprehensive management of self-hosted Supabase instances on Coolify, including database migrations, edge functions deployment, storage management, auth configuration, and full application lifecycle control through AI agents. | |
| Meta Ads MCP Server djackson1205/meta-mcp Enables connecting to the Meta Marketing API to manage ad accounts, campaigns, ad sets, creatives, audiences, reporting, and batch workflows through an MCP endpoint with Meta OAuth and app-issued JWT authentication. |
44,951–45,000 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.