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 |
|---|---|
| Placed MCP Server exidian-tech/placed-mcp Provides access to 47 AI-powered career tools for resume building, job tracking, ATS optimization, and interview coaching. It enables users to manage their job search, research companies, and negotiate salaries directly through an MCP-compa | |
| mcp-db-server exigerdev/mcp-db-server Enables querying PostgreSQL and MySQL databases using natural language, with RESTful endpoints for listing tables, describing schemas, and executing read-only queries. | |
| meta-mcp exileum/meta-mcp Enables AI assistants to manage Instagram and Threads accounts — publish content, handle comments, view insights, search hashtags, and manage DMs through the Meta Graph API. | |
| ExisOne MCP Server exisllc/exisone-mcp Enables AI assistants to manage software licenses through natural language commands by connecting to the ExisOne licensing platform. | |
| @quikrun/mcp exit150/quikrun-mcp Enables AI agents to manage QuikRun snippets (list, read, create, edit, run, deploy, duplicate, delete) via the QuikRun API. | |
| CRM MCP Server exlumina/crm Exposes an authenticated Streamable HTTP endpoint that lets MCP clients search and read records, create and update people, companies and pipelines, manage boards and stages, append notes, set follow-ups, inspect history and export bounded p | |
| Jira MCP Server exmuzzy/exmuzzy-mcp A comprehensive Model Context Protocol server for Jira Cloud integration, offering tools for board, issue, user, project, and time tracking management with enhanced features like AI-powered workflows and rate limiting. | |
| relic exocriador/relic Enables AI models and products to access Telegram and YouTube conversations, messages, searches, and transcripts through MCP and REST APIs, governed by per-product scopes, usage accounting, and response budgets. | |
| OpenWA MCP Server exocubeyt/openwa-mcp Enables AI assistants to manage WhatsApp sessions, send multi-format messages, control group participants, and configure webhooks by wrapping the OpenWA REST API with 44 tools. | |
| MiniMax Unified MCP exomind-team/minimax-unified-mcp Unifies MiniMax's multimodal generation, web search, image understanding, audio, video, and music tools into a single MCP server for use with Claude and other clients. | |
| AdKit MCP Server exorust/adkit-mcp A lightweight semantic ad-matching engine for LLMs that serves relevant advertisements via MCP, allowing agents to request ads using natural-language context. | |
| Acme Enterprise Capability Hub exoticaitsolutions/mcp-server Enables AI assistants to invoke real-world enterprise business capabilities—such as customer management, device eligibility checks, and compliance runs—through MCP while hiding the underlying polyglot technology stack. | |
| WET - Web Extended Toolkit MCP Server expandingideas-ai/mcp-wet Web search, content extraction, and library docs for AI agents with 5-strategy scraping and runs without API keys. | |
| Mnemo MCP expandingideas-ai/mnemo-mcp Persistent AI memory server with hybrid search and embedded sync. Enables AI agents to store, retrieve, and manage information across sessions with temporal knowledge graph support. | |
| Home Assistant MCP Server expansing/mcp_server_ha AI sysadmin for Home Assistant that provides entity health analysis, automation diagnostics, dashboard analysis, configuration search, and system health scoring via the Model Context Protocol. | |
| Expanso Fleet expanso-io/expanso-chatgpt-plugin Enables ChatGPT users to view and inspect nodes, jobs, executions, recent errors, and bounded job logs in linked workspaces through read-only MCP tools, including sidebar views and mention-based queries. | |
| Convolut MCP Server expdal3/convolut-mcp Enables seamless integration with Convolut Context Bank for AI-powered context management, search, consolidation, and export operations. Provides 11 powerful tools for creating, managing, and analyzing contexts with semantic search and auto | |
| expedia-travel-recommendations-mcp expediagroup/expedia-travel-recommendations-mcp MCP server for Expedia travel recommendations. Enables LLMs to search hotels, flights, activities, and car rentals using natural language. | |
| Atlassian Goals MCP Server expel-io/atlassian-goals-mcp A Model Context Protocol (MCP) server for the Atlassian Goals API. Enables AI assistants like Claude to query, search, and update Atlassian Goals and Projects. | |
| night-shift experiai/night-shift Enables agents and people to commission an AI painter via MCP by submitting a description or photo, then check the commission's status and view recent paintings. | |
| docuprivado experimentosderodri/extension Enables Claude Desktop to redact and count personal data in PDFs and images, strip hidden metadata from photos, anonymize Word and text files, prepare watermarked ID copies, and compare contract versions using only user-approved local folde | |
| Conexa MCP expert-integrado/conexa-mcp MCP server that connects AI assistants to the Conexa business management system, enabling CRUD operations on sales, customers, plans, contracts, charges, and more via 83 tools. | |
| Image MCP expert-integrado/image-mcp Connects Claude Code to image generation models (OpenAI GPT Image 2, Google Nano Banana) for generating, editing, and converting images via natural language. | |
| Pipedrive MCP expertintegrado/pipedrive-mcp Enables natural language interaction with Pipedrive CRM via Claude Code, allowing users to manage deals, contacts, activities, and more through conversational commands. | |
| coldstar-signer-mcp expertvagabond/coldstar-agent-signer Enables AI agents to safely sign and send Solana transactions under a policy, with automatic signing for in-policy actions, air-gapped human approval for escalations, and rejection of disallowed transactions. | |
| fulfil-mcp expertvagabond/fulfil-mcp MCP server for Fulfil.io ERP with 29 tools for inventory, orders, shipments, customers, purchasing, returns, warehouse operations, and analytics. Integrates with Claude Desktop and other MCP clients via Fulfil.io REST API v2. | |
| jupiter-mcp expertvagabond/jupiter-mcp MCP server providing AI agents with native access to Jupiter's full DeFi stack on Solana. It offers 17 tools covering swaps, tokens, lending, limit orders, DCA, prediction markets, perpetuals, and portfolio management. | |
| livekit-ops-mcp expertvagabond/livekit-ops-mcp Enables AI agents to operate a LiveKit deployment, managing rooms, tokens, participants, data messages, egress/ingress, and hackathon workshops with one-call room setup, status, broadcast, and teardown tools. | |
| plaid-devx-mcp expertvagabond/plaid-devx-mcp Provides Plaid developers with sandbox integration tools for creating test items, reading financial data, simulating webhooks and login failures, plus docs-quality tools for API search and OpenAPI-vs-Postman-vs-docs drift checking. | |
| robinhood-chain-mcp expertvagabond/robinhood-chain-mcp Provides read-only access and unsigned transaction building for the Robinhood Chain Arbitrum Orbit L2, including NFT, ERC-20, stock tokens, oracles, and EIP-3009 tooling. | |
| sdp-mcp expertvagabond/sdp-mcp Provides 76 tools for enterprise Solana development, enabling stablecoin issuance, payments, trading, wallet management, and compliance screening via natural language. | |
| shopify-mcp expertvagabond/shopify-mcp MCP server for the Shopify Admin API, enabling 36 tools for managing products, orders, customers, inventory, fulfillments, collections, analytics, marketing, content, and webhooks. | |
| redmine-mcp expertzentrale/claude-redmine-mcp Enables Claude to read and, when explicitly enabled, update projects, issues, time entries, versions, wiki pages, and supported helpdesk, agile, CRM, and checklist data through the Redmine REST API. It runs read-only by default with separat | |
| MCP Llama Integration Server expesraza/mcp-llama-integration Implements the Model Context Protocol to retrieve context from a locally running Llama model, enabling AI applications to query and receive relevant information. | |
| reaper-mcp explod1983/reaper-mcp Enables AI-assisted VST plugin tuning by connecting Claude CLI to Reaper, allowing a loop of audio capture, spectrum analysis, and live plugin parameter adjustment. | |
| eip-mcp exploitintel/eip-mcp Gives AI assistants access to the Exploit Intelligence Platform for vulnerability and exploit intelligence. Supports searching CVEs, exploits, and generating pentest findings. | |
| hyperv-mcp exploo0osion/hyperv-mcp Enables controlled Hyper-V virtual machine operations over MCP, including status queries, checkpoints, in-guest command execution, and file transfers, without requiring guest networking or WinRM. | |
| Dealership AI MCP Server exploratory-projects/mcp-server MCP server that enables AI agents to instantly understand, generate pattern-aware code, search across repos, and validate changes in the Dealership AI codebase. | |
| Amazon Product Intelligence Agent explorellm32-usr/mcp-server-test This MCP server scrapes Amazon product details and reviews, manages a local JSON database, and visualizes intelligence data through a rich dashboard. | |
| Explorium AgentSource DXT Extension explorium-ai/agentsource-mcp-ext Enables access to live company and contact data from Explorium's AgentSource platform for business intelligence and enrichment within Claude Desktop. | |
| android-phone-mcp-server expoli/android-phone-mcp-server MCP server for controlling Android devices via semantic actions with verification, enabling any MCP client to interact with phones through natural language and structured tools. | |
| Stacks Clarity MCP Server exponentlabshq/stacks-clarity-mcp Enables comprehensive Stacks blockchain development with 30+ specialized tools for Clarity smart contracts, SIP compliance, security analysis, and performance optimization. Provides complete access to SIP standards, token development templa | |
| ats-fill-mcp expr2023/ats-fill-mcp Enables AI agents to automatically inspect and fill web application forms on job application sites through a logged-in Chrome, supporting text, select, radio, date, cascading dropdowns, and dynamic row operations. | |
| telegram-mcp expremiental/telegram-mcp Read-only MCP server for self-hosted Telegram access via Telethon. Enables reading messages, chats, and media but disallows any write operations. | |
| Store Sales Data MCP Server expresser-uxm/20260617-dx-dojo-mcp-server-sample Enables querying and managing daily store sales data stored in CSV files, including listing available dates, retrieving raw sales data, computing daily and per-item statistics, and saving new daily sales data. | |
| Charles MCP Server exqa/charles-mcp Enables AI agents to connect to Charles Proxy for live and historical traffic analysis, summary-first insights, request detail inspection, and data-driven mock creation via Map Local/Remote. | |
| perplexity-unofficial-mcp exqlnet/unofficial-perplexity-mcp Unofficial MCP server that wraps the Perplexity AI web API via browser cookies, enabling search, research, reasoning, and ask tools through STDIO. | |
| assay-mcp exquest/assay-mcp Enables paid queries to Assay's API as MCP tools, letting users check new Base liquidity pools and verify claims with multi-model consensus, paying per call in USDC from their own wallet under a daily limit. | |
| MCPO - MCP Pollinations Proxy exrienz/pollenai-mcp A Docker-containerized MCP proxy that provides AI image generation, text generation, vision analysis, and text-to-speech capabilities through REST endpoints using Pollinations AI services. Enables multimodal AI interactions including image | |
| Weather MCP exspiravit/weather-mcp Enables users to get real-time weather information for any city in the world. Provides current temperature and weather conditions through a simple city name query. |
49,151–49,200 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.