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 |
|---|---|
| fastrack aabxtract/fastrack Enables plain-English workflow automation across connected tools like GitHub, Notion, Slack, and more, with self-healing execution, scheduling, and status reporting through MCP. | |
| Mathematica MCP Server aac6fef/mathematica_mcp Allows LLMs to execute Wolfram Language code in a secure, session-based environment by providing an interface to interact with a Wolfram Mathematica kernel. | |
| agent-chat-search aacero/agent-chat-search Enables agents to run cross-runtime, cross-machine BM25 full-text search over historical conversations from Hermes, Google Antigravity, OpenClaw, Codex, and Claude Code, and to retrieve any past session's full transcript by ID. Queries retu | |
| aacworkflow-mcp aachibilyaev/aacworkflow-mcp Enables Claude and Claude Code to manage AACWorkflow tasks, agents, projects, squads, autopilots, and analytics through natural language. | |
| MindBacklog aadarshb/mindbacklog-mcp Connect Claude directly to your MindBacklog workspace to read PRDs, user stories, and real-time customer signals. | |
| PostgreSQL MCP Server aadarshjain/postgres-mcp-server Enables exploration and querying of PostgreSQL databases through natural language. Supports listing tables, viewing schemas, executing SELECT queries, filtering records, and retrieving database statistics. | |
| Lead Details MCP aadarshlodhi/lead-details-mcp Manages leads and sends emails directly from Claude chat, with tools to add, search, filter, and update leads, plus email capabilities. | |
| Derive MCP Server aadarshvelu/derive-mcp Provides market data from Derive.xyz, allowing users to query currencies, instruments, tickers, and historical price information. This server enables access to real-time and historical financial data through the Derive public REST API with | |
| VSCode Language Server MCP Extension aaddrick/vscode-mcp-language-server Exposes VSCode's Language Server Protocol features through MCP, enabling AI assistants to perform language-aware operations like symbol navigation, reference tracking, safe renaming, type information retrieval, and hover documentation acros | |
| Restaurant MCP Server aadeshmahesh/restaurant-mcp-server MCP server exposing restaurant tools including search by cuisine, price, rating, and open status, restaurant details, user preferences stored in Neon Postgres, and RAG knowledge search covering 50 mock restaurants across Scottsdale and Phoe | |
| LangChain & LlamaIndex Coding Assistant aadhil96/mcp-coding-assistant Provides real-time retrieval of official documentation for LangChain, LlamaIndex, and OpenAI. It enables context-aware coding by fetching the latest API references and guides directly into Claude via the Model Context Protocol. | |
| mcp-market-server aadhitya369/mcp-market-server Enables agents to access live crypto market data and execute risk-controlled paper trades through standardized MCP tool calls. | |
| slcg aadhyathmik/slcg Provides a read-only PostgreSQL MCP server with schema introspection. Enforces least-privilege database roles to prevent any writes, even from malicious SQL. | |
| Canvas Connector aadi-ftc-12868/canvas-connector Enables AI assistants to navigate Canvas courses, read assignments, documents, feedback and grades, and prepare verified student actions through MCP, with local stdio and hosted OAuth options. | |
| MahoRAGa aadi775/mahoraga Persistent, graph-powered memory for AI agents that provides long-term semantic recall using a local Kuzu graph database. | |
| MCP Odoo Bridge Server aadilakbar/ad-mcp-bridge-server Enables AI assistants to interact with Odoo data using natural language to search, read, create, and update records. It acts as a secure bridge between MCP clients and Odoo instances version 17.0 through 19.0. | |
| marketifyall-mcp aadilhassan/marketifyall-mcp A thin bridge that connects any stdio-based MCP client to the MarketifyALL workspace, enabling content generation, search, and discovery through a hosted MCP server with graduated safety controls. | |
| groundline-mcp aadithyaale/groundline Enables AI agents to fact-check their own claims and answers, validate cited links, and gate code diffs for security and CVE issues by purchasing independent checks from Telegraph's ranked miners, returning verified/uncertain/contradicted v | |
| ucla-soc-mcp aaditsingh07/ucla-soc-mcp MCP server for querying the public UCLA Schedule of Classes. It provides tools to list terms, subject areas, search courses, and get detailed enrollment, waitlist, and section information. | |
| Tributary MCP Server aaditya-diwan/tributary Enables AI agents to share persistent, conflict-safe memory by providing tools to recall, learn, reinforce, and retire lessons, using CockroachDB for storage and AWS Bedrock for embeddings. | |
| chatgpt-kg aaditya-git/chatgpt-kg Builds a personal knowledge graph from selected ChatGPT conversations (stored in Neo4j) and exposes it to Claude Code as an on-demand MCP search tool. | |
| ToolPlan MCP aaditya0602/toolplan-mcp Turns raw project ideas into polished, cost-aware first prompts for AI coding agents by recommending high-leverage open-source tools and cost-saving techniques. | |
| TradeMCP aaditya2502/trade-mcp An MCP server that exposes trading analytics — technical indicators, portfolio state, risk metrics, and backtest results — as tools an LLM agent can call. | |
| worklog-mcp aadityakushwaha/worklog-mcp An MCP server that enables coding agents to log their work, decisions, test runs, PRs, and progress as structured events, either to a local JSONL file or an HTTP endpoint. | |
| MCP Azure DevOps Server aadityasinghal7/mcp A Model Context Protocol server that enables AI assistants to interact with Azure DevOps services, providing capabilities for work item management, project management, and team collaboration through natural language. | |
| CyberArk Privilege Cloud MCP Server aaearon/mcp-privilege-cloud Enables privileged access management for CyberArk Privilege Cloud through 53 tools for account management, safe management, platform management, and session monitoring. | |
| ClinicalTrials.gov MCP Server aafjes/mcp-clinicaltrials.gov Enables searching and retrieving information from the ClinicalTrials.gov database of over 400,000 clinical studies, including trial details, eligibility criteria, locations, and results across 220+ countries. | |
| Task Manager MCP Server aafsar/task-manager-mcp-server Enables AI assistants to manage tasks through a comprehensive interface with 8 tools for creating, updating, searching, and tracking tasks with priorities, categories, and due dates. Features persistent file-based storage, advanced filterin | |
| OpenFGA Modeling MCP Server aaguiarz/openfga-modeling-mcp A specialized MCP server that provides expert-level OpenFGA authorization modeling guidance, enabling users to create and manage authorization models for ReBAC systems directly from VS Code. | |
| agent-undo aah20/agent-undo Provides transactional rollback and compensating sagas for MCP tools, enabling atomic multi-step execution and automatic restoration of external systems to a clean state upon failure. | |
| ax-context-gateway aah20/ax-context-gateway Enables AI agents to securely retrieve pre-compiled bounded context and memory state over a zero-network Unix Domain Socket, ensuring tenant isolation and sub-millisecond rehydration in Kubernetes environments. | |
| canary-mcp aah20/canary-mcp Enables active deception for AI agents by injecting decoy honeypot tools that detect indirect prompt injection attempts, instantly terminate hostile sessions, and seal cryptographic incident evidence. | |
| Swarm-As-MCP aah20/swarm-as-mcp Enables dispatching entire autonomous multi-agent engineering swarms directly from IDEs like Cursor and Windsurf via a single MCP endpoint, with streaming progress updates and verified git diffs returned to the editor. | |
| swarm-context-mcp aah20/swarm-context-commander Provides two stdio tools for compiling bounded inline context and selecting runtime placement for agent tasks. | |
| agentguard-mcp aahilafraz123/agentguard-merchant Enables any MCP client to access PayPal's Agent Toolkit tools while policy-checking refund requests against PayPal records, merchant policy, customer history, and a risk classifier, then allowing, escalating for human review, or blocking th | |
| Google Calendar Gmail MCP aaka5204/google-calender-mcp An MCP server that enables AI assistants to interact with Google Calendar and Gmail, allowing users to manage events, send emails, and organize their inbox through natural language. | |
| MCP Server Demo - Learning Project aakankshagupta18/custom-mcp-server A comprehensive learning project demonstrating MCP server implementation with tools for calculator operations, file management, and system information retrieval, including Google ADK integration patterns and best practices. | |
| OpenLore aakarim/openlore A frontier knowledge base that’s minimal extensible and agent-native. Built to keep your team’s shared context current and inspectable. | |
| mcp-with-ssh aakarsh-sasi/memory-bank-mcp Memory bank with Server as SSH support for central knowledge base | |
| MCP Enterprise Gateway aakarsh1227/gateway-project-using-n8n A secure MCP proxy server with JWT authentication, SQL guardrails, rate limiting, and Kafka audit logging, enabling enterprise-grade access control for MCP clients like Cursor and Claude Desktop. | |
| BambooHR MCP aakarsh1t/bamboohr-mcp Enables AI assistants to interact with BambooHR for employee management, hiring, time-off, documents, and reporting, with read-only tools by default and optional write capabilities. | |
| Mailchimp MCP Server aakarsh1t/mailchimp_mcp- Provides read-only access to the Mailchimp Marketing API v3 via 18 tools covering 103 endpoints for audiences, members, campaigns, reports, automations, templates, landing pages, e-commerce, and account administration. | |
| Shopify Enterprise MCP Server aakarsh1t/shopifymcp Production-grade MCP server that exposes live Shopify Admin GraphQL data to Microsoft Copilot Studio agents, enabling real-time answers to business questions about inventory, orders, and products. | |
| Playwright Debug MCP Server aakarshitsharma06/playwright-debug-mcp Supercharges AI-assisted debugging of Playwright tests by parsing trace files to extract failures, action history, network logs, screenshots, and suggesting fixes. | |
| CareCircle aakarshitv/carecircle Enables Alexa+ users to log scheduled medication doses by voice and lets family caregivers check taken, missed, or upcoming doses with spoken daily summaries. | |
| AI Sticky Notes MCP Server aakash-agrahari/claude_connector_notes_mcp_server Enables AI assistants to manage local sticky notes, allowing users to add, read, retrieve the latest note, and generate AI summaries through natural language. | |
| perplexity-deep-mcp aakashanil67/perplexity-deep-mcp An MCP server that makes Perplexity's Sonar Deep Research usable from MCP clients that enforce a request timeout by using Perplexity's async API. | |
| Raksha aakashdeeeep/mcp A self-hosted MCP server that lets Alexa+ help care for an older family member — medicines, health readings, family messages, errands and scam calls — with every tool call screened by a deterministic safety gate and a Cedar policy. It appli | |
| mcp-playwright aakashh242/mcp-playwright 🚀 Active Fork of executeautomation/mcp-playwright
This repository is an actively maintained continuation of the original MCP Playwright server: >👉 https://github.com/executeautomation/mcp-playwright
A Model Context Protocol server that pro | |
| Gmail MCP Server aakashlokhande99/gmail_mcp_server Enables interaction with Gmail accounts via IMAP and SMTP, providing tools for searching emails, retrieving content, managing labels, and sending/forwarding emails through natural language. |
22,601–22,650 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.