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 |
|---|---|
| TruthLens MCP aniruddhaadak80/truthlens Enables agents to analyze YouTube channels for credibility, retrieve and update saved reports, and verify the auditable SHA-384 seal chain through a JSON-RPC 2.0 endpoint. | |
| upgrade-atelier aniruddhaadak80/upgrade-atelier Provides MCP tools to analyze npm packages with deterministic risk scoring, manage watch records, and verify SHA-384 audit seals. | |
| NPS MCP Server aniruddhashukla/nps-mcp Provides access to the National Park Service API, enabling natural language queries about parks, alerts, campgrounds, events, and more. | |
| Research World anirudh279/research-world Enables capturing web evidence, freezing content-addressed snapshots, and comparing research agents on the same sources with traceable access and quotations. | |
| GitHub Search MCP Server anirudhadasgupta/githubmcpserver Enables searching and exploring GitHub repositories with tools for cloning repos, searching code with regex, browsing directory structures, reading files, and extracting code outlines. | |
| Chronicle Beta anirudhb-6001/chronicle_beta A local-first personal RAG memory system that turns AI conversation history into a searchable, retrievable knowledge base via MCP, enabling LLMs to semantically search past conversations. | |
| cloud-engineer-mcp anirudhbiyani/cloud-engineer-mcp Fans out agent requests to AWS, Azure, and GCP MCP servers, using a local sentence transformer to surface only the 15 tools relevant to the current task, reducing context bloat. | |
| agent-vitals anirudhprashant/agent-vitals Local-first observability for AI agent stacks. Provides MCP tools for agents to check health, shadow configs, and burnout metrics proactively. | |
| YouTube MCP Server anirudhyadavms/youtube_mcp Enables YouTube content browsing, video searching, and metadata retrieval via the YouTube Data API v3. It also facilitates fetching video transcripts for summarization and analysis within MCP-compatible AI clients. | |
| Markdownify MCP Server anis-marrouchi/markdownify-mcp-http-server A Model Context Protocol server that converts diverse file types, including PDFs, images, audio, and Office documents, into Markdown format. It also transforms web content like YouTube transcripts and Bing search results into readable text | |
| palace-mcp anis-meliti/palace-mcp MCP server that exposes an Obsidian vault to AI assistants, enabling them to list, read, write, search, and delete notes via the Local REST API. | |
| YouTube MCP Server anisayari/mcp-youtube-server Provides YouTube video search, comment analysis, AI-powered text tools, and content generation via MCP protocol and REST API. | |
| Zerodha MCP Server anish5256/zerodha-mcp Enables natural language access to Zerodha trading accounts for retrieving portfolio holdings, positions, orders, funds, and real-time market prices. Supports secure authentication for Indian stock market trading operations via Claude, Curs | |
| ground-truth-mcp anish632/ground-truth-mcp Validate AI claims against live data: check endpoints, count competitors, and test hypotheses. Includes free and paid tools via x402. | |
| git-standup-mcp anisha-agarwal/git-standup-mcp Generates standup reports from git history by analyzing recent commits across configured repositories. Enables users to query their development activity, such as what they worked on yesterday or over multiple days, through natural language | |
| pr-roast-mcp anisha-agarwal/pr-roast-mcp Provides brutally honest, humorous code reviews for GitHub pull requests using Claude Haiku. Enables users to roast their PRs by fetching metadata and diffs via the GitHub CLI and returning severity-rated reviews with genuine compliments. | |
| ARIA anishachutha05/aria---mcp-research-server Autonomously researches any topic: searches web, scrapes sources, extracts insights, builds a knowledge graph, and synthesizes a structured research brief. | |
| Pokemon MCP Server anishadesai5/pokemon-mcp-server Enables users to fetch detailed Pokémon data, build tournament squads, and simulate battles using PokéAPI. It also integrates Wikipedia to provide fun comparisons between Pokémon and their real-world animal inspirations. | |
| Allowance anishalx/allowance Enables AI agents to make PayPal payments under plain-English spending rules, with deterministic checks and an AI auditor that can only tighten decisions, plus human approval for unusual purchases. | |
| grocy-mcp anishanilkumar/grocy-mcp MCP server for Grocy that enables AI assistants to read and manage pantry stock, product catalogs, and shopping lists, with safety checks against common errors. | |
| cargotrace-mcp anisharamanuj/cargotrace-mcp Enables AI assistants to track air waybills and ocean containers and compare freight quotes across carriers through typed, validated tools, with normalized milestone timelines, ETAs and check-digit validation. | |
| paddock anishde12020/paddock Enables AI agents to work in a persistent, isolated Linux workspace with file management, Bash execution, SSH/SFTP access, and durable storage while keeping workloads contained from the host and private networks. | |
| Personal Assistant Memory Server anisherdev/personal-assistant-wwllm Enables managing personal notes through natural language, with tools to save, search, list, update, and delete notes via a local LLM and persistent JSON storage. | |
| mail-mcp anishhs-gh/mail-mcp A self-hosted MCP server that gives AI agents full email superpowers. | |
| straitsX MCP Card Gateway anishnar/straitsx-mcp-demo Enables AI agents to pay with crypto (XSGD) via EIP-3009 and receive single-use virtual Visa cards from the StraitsX sandbox or production environment. | |
| WireMCP Secure anishphilip012git/wiremcp-secure Production-ready MCP server for real-time network traffic analysis and packet capture using Wireshark/tshark, with security hardening, threat intelligence integration, and comprehensive audit logging. | |
| Figma MCP Server anishtejwanigemi-max/mcp Enables interaction with Figma files through tools that list projects/files, fetch design data, and generate React+Vite frontend code directly from Figma frames. | |
| PenTest MCP anishxagrawal/pentest-mcp Enables AI agents to orchestrate 25+ security tools for penetration testing through natural language, automating scans, vulnerability detection, and report generation. | |
| SSE MCP Server with JWT Authentication anisirji/mcp-server-remote-setup-with-jwt-auth A Model Context Protocol server that exposes multiple AI tools over SSE transport with JWT-based secure authentication, allowing for dynamic tool registration and session management. | |
| claude-broker anisthesia/claude-broker-oss Lets fleets of long-lived Claude Code sessions coordinate over named channels backed by SQLite, exchanging schema-validated, role-scoped messages that survive restarts, gate actions behind human approval, and leave a queryable audit trail. | |
| E-commerce Local MCP Server anisurrahman06046/mcptestwithmodel Enables e-commerce shop owners to query their business data using natural language through local AI models. Provides secure, privacy-focused access to sales reports, inventory management, customer analytics, and order data without sending s | |
| MCP Database Server anit05/mcp This server provides database access capabilities to Claude, supporting SQLite, SQL Server, PostgreSQL, and MySQL databases. | |
| MCP01 Token Mismanagement anita-ani/mcp-security-lab A deliberately vulnerable MCP server demonstrating API key exposure through hardcoding, plaintext logging, and returning secrets to the model, part of the OWASP MCP Top 10 security lab. | |
| pob-mcp anitaguptaoffice/pob-mcp-suite MCP server for Path of Building that enables querying and managing PoB builds and trade data through the Lua bridge and official APIs. | |
| gmail-multi-mcp anitalklausen/gmail-multi-mcp Connects any number of Gmail accounts to Claude or another MCP client, enabling search, reading, sending, drafting, labeling, and trashing mail across one account or all of them at once. Runs entirely locally, so OAuth tokens never leave th | |
| Test Results MCP Server anittasusanthomas/test-results-mcp-server Enables an LLM assistant to analyze automated test results, search logs, group failures by cause, and draft Jira bugs with steps to reproduce, with dry-run Jira filing by default. | |
| FastMCP Demo Server anjalbhattarai79/mcpremoteserver-fastmcplibrary-withoutlangchhain A minimal demonstration MCP server built with FastMCP that exposes a simple greeting tool, showcasing basic server setup and remote deployment capabilities. | |
| Chronicle anjali-k27/chronicle_analyst_mcp Enables personal data analysis and insights using AI agents across Spotify, GitHub, finances, fitness, and journal entries. | |
| AI HR Leave Management MCP Server anjalimahapatra2004/mcp_tool Provides tools for managing human resources tasks such as applying for leave, checking leave balances, and viewing holiday schedules. It enables natural language interaction for employee information and leave history tracking via the Model | |
| Databricks MCP Server Template anjalipurewal03/anjali_mcp_server Enables users to host MCP prompts and tools on Databricks Apps so AI assistants like Claude can securely interact with Databricks workspace resources and APIs. | |
| Quorum anjanasuresh01/agentic-meeting-intelligence Quorum is an MCP server for querying meeting archives in natural language, returning answers with citations to speakers and timestamps or explicitly abstaining when evidence is insufficient. | |
| LinkedIn Job Scraper MCP Server anjani27/linkedin-job-scraper-mcp-server Enables AI assistants to search, filter, and extract job listings from LinkedIn using an automated headless browser with semantic AI filtering and deduplication. | |
| mcp_proxy anjani78/mcp_proxy Enables centralized routing, discovery, namespacing, and execution of tools from multiple remote MCP servers over HTTP/SSE, aggregating them behind a unified MCP gateway with dynamic server management. | |
| polymarket-us-mcp anjavera/polymarket-us-mcp Provides read-only access to Polymarket US public market data, including prices, order books, and spread/fee analytics, via MCP tools. | |
| jk-mcp anjingyeong/jk-mcp A local coding bridge that enables ChatGPT to read, edit, test, and manage Git operations on your local projects. | |
| mcp-android-emulator anjos2/mcp-android-emulator Enables AI assistants to interact with Android devices and emulators via ADB, providing tools for screenshots, UI inspection, touch and text input, app management, and device control. | |
| Expense Tracker MCP anjudevchaudhary0/expence-tracker-mcp Enables LLMs to record, list, update, and delete expenses and credits in a local SQLite database, with enforced categories and running balance summaries. | |
| GullakAI MCP Server anjulbhatia/gullak-mcp Enables personal finance management through conversational AI, including expense tracking, budget monitoring, financial news simplification, and purchasing power comparisons across South Asian cities. Designed for WhatsApp integration with | |
| HN Pulse ankamandy/hn-pulse Enables AI assistants to read and search Hacker News for top stories, comments, user profiles, and job listings using the Firebase and Algolia APIs. It facilitates natural language research into community discussions and technological trend | |
| ccfolia-mcp-workers anker12345/ccfolia-mcp-workers A Cloudflare Workers MCP server for the TRPG online session tool ccfolia, enabling character generation, NPC batch generation, session analysis, random events, and rule assistance. |
29,201–29,250 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.