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 |
|---|---|
| codebase-rag ahmadsurti/codebaserag-lancedb-treesitter-mcp-based-symbol-aware-codebase-retrieval-system Enables AI coding agents to navigate and understand entire codebases through symbol-aware semantic retrieval and relational call graph traversal, supporting structural impact analysis and code modification workflows over MCP. | |
| bluesky-mcp ahmadtariq1337/bluesky-mcp MCP server for managing a Bluesky account, enabling posting, replying, liking, reposting, following, searching, and reading timelines/notifications via natural language. | |
| devto-mcp ahmadtariq1337/devto-mcp Enables managing a Dev.to account from Claude or any MCP client, including browsing articles, creating/editing posts, and reading comments. Uses the official Forem API with a personal API key. | |
| minecraft-mcp-server ahmadtariq1337/minecraft-mcp-server Enables AI agents to control a Minecraft bot inside a Java Edition world via MCP, providing tools for movement, building, mining, combat, farming, trading, inventory, and world perception. | |
| streamlabs-mcp ahmadtariq1337/streamlabs-mcp MCP server that gives AI assistants direct control over Streamlabs Desktop, enabling scene switching, source/audio management, and streaming/recording controls through natural language. | |
| Composio MCP Bridge ahmadthetech/composio-mcp-bridge A remote MCP server that proxies tool calls to the caller's own Composio account, using their own API key for each request to access services like Gmail, Slack, and Google Sheets. | |
| WordPress MCP Server ahmadthetech/wp-mcp Enables AI agents to manage WordPress sites through the WordPress REST API, supporting content, media, users, settings, and Elementor management with safety policies for production use. | |
| emailsRboring ahmadzafar-code/emailsrboring A safe, redacting MCP server for Apple Mail on macOS that enables an LLM to read, search, triage, draft, and confirm sending email while stripping secrets and blocking dangerous actions. | |
| gitrama-mcp ahmaxdev/gitrama-mcp AI-powered Git workflow intelligence — 10 tools for commit messages, branch naming, PR descriptions, changelogs, and stream-based context management. Works with Cursor, Claude Desktop, Windsurf, VS Code, and all MCP clients. | |
| StatePulse API ahmed-achtatar/statepulse-api 55+ pay-per-call tools for AI agents over MCP: live telemetry, blockchain/on-chain checks, environmental, transit, finance, and network utilities. No API key or signup — agents pay per request with x402 USDC micropayments (Base and Solana). | |
| Google Calendar MCP Server ahmed-ag/mcp-test Enables natural language queries to Google Calendar API for checking appointments, availability, and events. Supports flexible time ranges, timezone handling, and both service account and OAuth authentication methods. | |
| Bob Demo MCP Server ahmed-chaudhry-ibm/bob-demo-mcp-server A comprehensive MCP server that demonstrates Bob's capabilities through 9 specialized tools for file operations, code analysis, and git operations. | |
| Gravitas-Core-MCP ahmed-coding/gravitas-core Production-grade, autonomous Model Context Protocol (MCP) server that elevates AI models from stateless code generators into persistent, self-verifying software engineers. | |
| data-analyst ahmed-deebb/agentic-data-analyst Enables MCP clients to ask bilingual data questions, inspect database tables and schemas, and execute validated read-only SQL through exposed tools. | |
| Ripple ahmed-haggag-2016/ripple-alexa-mcp Enables users to simulate everyday disruptions, compare deadline-safe recovery options against budget and service availability, and approve and verify each proposed recovery action through MCP tools. | |
| local-network-mcp ahmed-hashim-pro/local-network-mcp MCP server enabling local network interaction, shell command execution, system resource monitoring, and SSH-based remote device management. | |
| MCP Task ahmed-mansy-mansico/mcp_llm_server_for_erpnext Enables LLMs to interact with any ERPNext instance through comprehensive CRUD operations, advanced permissions, and a web chat interface. | |
| MCP Policy Gateway ahmed0qaid/mcp-policy-gateway Enables AI agents and MCP clients to safely access upstream MCP servers through centralized policy enforcement, including allow/deny/approval decisions, schema pinning, circuit breakers, and audit logging. | |
| SentinelForge ahmed35636/sentinel-forge A read-only MCP telemetry server that lets an agent investigate Windows hosts by pulling process lineage, network connections, behavior-specific detections, and local threat-intelligence matches from exported Sysmon snapshots. Queries are b | |
| Watershed MCP Server ahmeda-afk/watershed-mcp-server Enables querying live USGS stream gauge data by river name or location, retrieving current water-quality readings (temperature, pH, dissolved oxygen, turbidity), and ranking locations by EPA Clean Water Act compliance scores and grades. Sup | |
| mcp-comms ahmeda14960/mcp-comms Enables multiple AI agents to communicate and coordinate via a shared SQLite-backed message log, supporting directed messages, broadcasts, and session discovery. | |
| safe-sql-mcp ahmedabdirahman1-max/safe-sql-mcp Enables read-only SQL database access for AI assistants, allowing schema exploration and safe query execution without risk of data modification. | |
| Linux MCP Server ahmedadan/unix-mcp-server A read-only MCP server for Linux and macOS system administration, diagnostics, and troubleshooting, supporting remote SSH execution and multi-host management. | |
| Math MCP ahmedahmedeg/math-mcp A comprehensive math utility server implementing the Model Context Protocol (MCP) for reverse engineering and general-purpose arithmetic, bitwise, conversion, and encoding tasks via streamable HTTP. | |
| mcp-server-base ahmedalbanna/mcp-server-base Provides a production-ready Model Context Protocol server with dual STDIO and Streamable HTTP transports, enabling file operations, memory, database queries, RAG, web search, GitHub integration, background tasks, and prompt-based workflows. | |
| Vibedit ahmedaldakheel/vibedit Enables Claude and other MCP clients to write, validate, preview, inspect, and render plain-English motion-graphics scripts into finished video files locally. | |
| Duffel MCP Server ahmedaliqadir/duffel-mcp Enables AI assistants to search live travel inventory for flights, stays, and car hire through typed tools, with place resolution and price details while deliberately exposing no booking or payment surface. | |
| Orbixio Studio ahmedaliqadir/orbixio-studio MCP server for generating and managing YouTube video scripts with human-in-the-loop approval. | |
| GitHub MCP Connector ahmedaltu/github-mcp-connector Enables browsing GitHub profile, repositories, issues, and pull requests directly in Claude conversation through OAuth authentication. | |
| memory-mcp-server ahmedaltu/memory-mcp-server Bridges Claude Code and Claude.ai by exposing project memory files over MCP for shared context across both interfaces. | |
| bytebase-mcp ahmedbally/bytebase-mcp Enables SQL querying, schema browsing, query history, and human-approved change-plan workflows against Bytebase via the Connect-RPC API, secured with OAuth 2.1 PKCE and multi-process-safe token rotation. | |
| clockwork-mcp-remote ahmedbally/clockwork-mcp Enables debugging any Laravel application remotely via the Clockwork HTTP API, from any MCP client, with tools for query analysis, slow query detection, N+1 detection, exception inspection, and full request profiling. | |
| GitLab MCP Server ahmedbhl/mcp-server-gitlab HTTP-based MCP server for GitLab API, enabling project management, issue tracking, merge requests, and file operations through natural language. | |
| upnote-mcp ahmedco88/upnote-mcp Enables Claude to read and create UpNote notes locally, using a WAL-correct SQLite snapshot for reading and the upnote:// URL scheme for writing, with no account, cloud, or API key required. | |
| ColabAI MCP Server ahmedcoolprojects/colab-ai-mcp Enables AI agents and LLM tools to verify academic citations against real literature, detect hallucinated references, retrieve authoritative metadata and DOIs, generate BibTeX/APA/IEEE citations, and search over 200M+ scientific publication | |
| LinkedIn MCP Server ahmedekramalsada/linkedin-mcp Enables AI agents to interact with LinkedIn for posting, commenting, liking, and managing connections via OAuth2 authentication. | |
| Gameball MCP Server ahmedelmonady/gbx-mcp-beta Unified MCP server for Gameball's documentation and API integration, enabling documentation search, code generation, and API operations for customers, transactions, orders, coupons, and more. | |
| Universal Spec Architect ahmedelpannann/bob-a-thon-submission Enforces a rigorous spec-driven engineering workflow for AI coding assistants, requiring requirements, design, and task planning before any code is written. | |
| opendss-mcp-server ahmedelshazly27/opendss-mcp-server Connects Claude AI with EPRI's OpenDSS power system simulator, enabling conversational power system analysis for distribution planning. | |
| OpenDSS MCP Server ahmedelshazly27/opendss-mcp-server1 Enables conversational power system analysis by connecting Claude AI with EPRI's OpenDSS simulator. Allows distribution planning engineers to perform sophisticated electrical grid studies through natural language instead of complex scriptin | |
| Azan-MCP ahmedeltaher/azan-mcp Azan-MCP is an open-source Model Context Protocol (MCP) server that brings a comprehensive suite of Islamic utilities directly into AI assistants such as Claude Desktop. | |
| alibi ahmedezz26/alibi Enables diagnosing long AI-agent traces by identifying the most likely root-cause steps, so users can quickly find where an agent run went wrong. | |
| ApprovalLens ahmedhsn710/approvallens-release Hosts an advisory review layer that compares proposed agent tool calls and explanations against developer-owned policy and available evidence before a human decision, returning grounded approval recommendations over MCP. | |
| reconcilex ahmedkhalid0/reconcilex Enables AI IDEs to perform financial reconciliation through five native tools for matching invoices, detecting bundled payments, and handling bank fee variances. | |
| white-box-synthesis ahmedkishki/mcp-white-box-synthesis Enables verification that a synthesized passage preserves the human-ness of source passages by checking exact copies, logged deletions/reorderings, and flagged unverified transformations. | |
| memory-ultra-rag-mcp ahmedkishki/memory-ultra-rag-mcp-server Serves UltraRAG memory to agents over stdio MCP, providing project-local and per-user global memory. It lets agents read and append standing memory and daily dialogue rounds in UltraRAG's format, with an optional browser view. | |
| io.github.D4Vinci/Scrapling ahmedlala502/scrapling-tool Enables web scraping through Scrapling's adaptive parsers, fetchers that bypass anti-bot systems, and scalable spider framework, allowing users to fetch pages, extract structured data, and run concurrent crawls with proxy rotation. | |
| AutoCAD MCP Server ahmedmuji/autocad_mcp Enables Claude Web to control a local AutoCAD instance via MCP, exposing 149 tools for CAD operations with dual COM/ezdxf backend support. | |
| PostgreSQL MCP Server ahmedmustahid/postgres-mcp-server A Model Context Protocol server providing dual transport (HTTP and Stdio) access to PostgreSQL databases, allowing AI assistants to query databases and fetch schema information through natural language. | |
| elastic_mcp ahmednaguib/elastic_mcp Enables MCP-compatible AI clients to search and retrieve Elasticsearch application logs through a provided search tool. |
24,751–24,800 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.