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 |
|---|---|
| Jupiter Perps MCP Server diaorui/jupiter-perps-mcp Enables AI agents to trade leveraged perpetual futures on Solana's Jupiter Perpetuals while providing tools for market data and technical analysis. It supports portfolio management, fee estimation, and automated position execution for SOL, | |
| octatrack-kb diarized/octatrack-kb Serves a locally built knowledge base derived from your own copy of the Elektron Octatrack manual to AI clients over stdio. Exposes tools for semantic and full-text search, retrieving chunks and concepts, listing workflows and usage modes, | |
| kanpla-mcp diarmind/kanpla-mcp Unofficial read-only MCP server to log into Kanpla and read canteen menus using your account credentials. | |
| YouTube Data MCP Server diasm3/serpapi-youtube-mcp-server Enables extracting YouTube video transcripts, comments, and search results via MCP. Supports both Stdio and StreamableHTTP transports. | |
| AWS Athena MCP Server diasrafael/aws-athena-mcp A Model Context Protocol server that enables SQL queries and database exploration in AWS Athena through a standardized interface. | |
| Ninetn MCP Server diatonic-codes/ninetn-mcp-server Integrates with Ninetn, an AI-powered memo application, enabling AI-assisted memo creation, retrieval, search, and listing through natural language interactions. | |
| clearsigned-mcp diawest82/clearsigned-mcp Enables agents to verify claims against live web evidence with calibrated confidence, paying per call via x402 and receiving offline-verifiable signed receipts. | |
| ccg-mcp-tool diaz3618/ccg-mcp-tool This is a powerful Model Context Protocol (MCP) server that integrates multiple AI coding agents—Anthropic Claude Code, OpenAI Codex, and Google Gemini—directly into your workflow. It enables seamless cross-provider analysis, leveraging Gem | |
| memory-bank-mcp diaz3618/memory-bank-mcp An MCP server that gives AI assistants persistent memory across sessions. It stores project context, decisions, and progress in structured markdown files as well as a knowledge graph and sequential thinking for better memory storage. | |
| kali-mcps diaz5764/awsome_kali_mcpservers Enables security testing and reverse engineering through MCP by exposing Nmap, nm, objdump, strings, and tshark for network scanning, symbol/binary analysis, string extraction, and traffic capture/analysis, plus isolated Docker sandbox comm | |
| Korean DART MCP diaz6212/korean-dart-mcp Enables AI assistants to query Korean OpenDART electronic disclosure data — disclosures, financials, equity, and XBRL — through 15 consolidated tools, including insider-trading signals, accounting-risk scoring, Buffett-style quality checkli | |
| kali-mcps diaz673/awsome_kali_mcpservers Enables users to run Kali Linux security tools through MCP clients for network scanning, binary and symbol analysis, string extraction, live packet capture, traffic inspection, and sandboxed command execution in Docker containers. | |
| Korean DART MCP diaz7121/korean-dart-mcp Enables AI assistants to search and analyze OpenDART electronic disclosures, including filings, financial statements, XBRL, ownership, insider signals, accounting-risk scores, and Buffett-style quality checks. It also converts HWP/PDF attac | |
| WordPress Standalone MCP Server diazoxide/wp-standalone-mcp A Model Context Protocol server that automatically discovers WordPress REST API endpoints and creates individual tools for each endpoint, enabling natural language management of WordPress sites. | |
| Grey Panda dibakshya01/grey-panda Enables AI coding assistants to scan, review, and explain AI, agent, and MCP security issues, run AISVS verification, and access OWASP-anchored standards controls from the IDE via stdio. | |
| kiro-ibmi-mcp-bridge dibari62/kiro-ibmi-mcp-bridge Bridges AI with IBM i systems for source code management, SQL queries, and schema inspection via MCP. | |
| Windows Developer Agent MCP dibbed/computerpilot-mcp Enables a local Windows developer agent to perform atomic filesystem operations, validated AST-based code edits, PowerShell/CMD process execution, and durable SQLite-backed background jobs with system diagnostics. It can run either as a loo | |
| V.I.S.O.R. dibun75/visor Smart MCP server that reads your code, understands file connections, and provides precise context to AI coding assistants, reducing token usage and preventing errors from outdated or irrelevant files. | |
| Remote YouTube MCP Server dibyaranjan1/auth-mcp-remote A remote Model Context Protocol server that extracts YouTube video transcripts and provides content creation templates using OAuth 2.0 authentication. It enables secure interaction with YouTube content for AI clients like ChatGPT and Claude | |
| PresentFlow dibyendu-13/presentation-automation-mcp Enables Claude Desktop users to generate structured, editable PowerPoint decks from a natural-language brief and slide-count settings by triggering the n8n presentation pipeline. Returns the generated title, presentation ID, and a downloada | |
| AIOrc MCP Server dich01/aiorc Enables MCP-compatible LLM clients to execute server-verified agent workflows, with enforced transitions, invocation caps, and signed audit trails. | |
| obsidian-ts-mcp dickiedyce/obsidian-ts-mcp A Model Context Protocol server that wraps the official Obsidian CLI to allow AI agents to read, write, search, and manage notes within an Obsidian vault. It provides 16 specialized tools for comprehensive vault interaction, including note | |
| MCP Agent Mail dicklesworthstone/mcp_agent_mail A coordination layer for coding agents that provides memorable identities, inbox/outbox messaging, searchable message history, and file lease management to prevent conflicts. Uses Git for human-auditable artifacts and SQLite for fast querie | |
| LLM Gateway MCP Server dicklesworthstone/ultimate_mcp_server An MCP-native server that enables intelligent task delegation from advanced AI agents like Claude to more cost-effective LLMs, optimizing for cost while maintaining output quality. | |
| curl-curl-cool-mcp dicoy/curl-curl-cool-mcp An MCP server that gives Claude a full HTTP client — make requests, compare environments, infer TypeScript types from live responses, and work directly with your existing Postman collections and environments. | |
| mcp-devenv dicoy/iwomm-mcp An MCP server that gives your AI assistant full awareness of your local dev environment — running processes, Docker containers, git state, open ports, log files, and more. | |
| sqlens-mcp dicoy/sqlens-mcp Provides Claude with read-only access to local development databases (Postgres, MySQL, SQLite) to inspect schemas, run SELECT queries, and explain query plans without leaving the conversation. | |
| paper-fetch-mcp dictation354/paper-fetch-skill MCP server that turns DOI, URL, or paper titles into structured Markdown full-text with metadata and assets, enabling AI agents to read beyond abstracts. | |
| DIDA Hotel MCP dida-ai/dida-hotel-mcp-cn Enables AI agents to search, compare, and book hotels with real-time pricing and availability, supporting multiple location types, star ratings, and price filters. | |
| Dida Hotel MCP dida-ai/dida-hotel-mcp-global Enables AI agents to search and book hotels globally with real-time pricing and inventory from over 2 million properties. | |
| MCP Servers (OnePiece & Geolocalizar) didacusdev/mcp-servers A collection of two MCP servers that enable querying One Piece anime characters and geolocating public IP addresses. | |
| micro-app-mcp didengren/micro-app-mcp Provides semantic search and knowledge base management for the micro-app micro-frontend framework by ingesting its source code and documentation. | |
| mcp_qrant didierphmartin/mcp_qrant Provides a unified interface for storing and querying vector databases, currently supporting Qdrant with self-embedding and semantic search. | |
| OpenBB Widgets JSON MCP Server didierrlopes/openbb-widgets-json-mcp Exposes OpenBB widget specifications as structured tools, enabling developers and AI assistants to programmatically query widget types, parameters, and configuration examples for building OpenBB applications. | |
| stravamcp didikz/strava-mcp Enables a single Strava account to be accessed through the Model Context Protocol, exposing read-only athlete, activity, route, segment, stream, and gear data plus activity summaries and zones. | |
| keqing-kb didione110/kb MCP server for querying the Keqing customer service knowledge base, enabling AI agents to search structured knowledge entries and retrieve authoritative, citable answers. | |
| datadog didlawowo/mcp-collection provide access to monitor and cluster logs from datadog | |
| droit-territorial didou92i/juriste-territorial Enables legal analysis and decision preparation for French territorial authorities by providing 14 tools to search official legal sources, check citations, compare document versions, and control evidence for tracing proof. | |
| lmstudio-local didou92i/lmstudio-local-mcp Enables MCP clients to administer a local LM Studio instance: loading, estimating, downloading, configuring and unloading models, running chat and embedding inference, diagnosing the server, engines and hardware, and managing MCP connectors | |
| yt-dj-mcp didtjd59/yt-dj-mcp Syncs YouTube Music liked songs, analyzes them for DJ metadata like BPM and key, and enables creating playlists from previews. | |
| DataFrame Analyst MCP diederichsolis/dataframe-analyst-mcp Enables analysis of datasets from CSV/Excel files, Google Sheets, and Google Drive with comprehensive data profiling tools including schema inference, missing value reports, correlation analysis, and outlier detection. Supports exporting an | |
| nblm-mcp diego-dev-moros/nblm-mcp Enables AI agents to interact with Google NotebookLM, including listing and managing notebooks and sources, asking grounded questions with citations, and generating audio overviews, briefings, quizzes, and mind maps. | |
| paywings diego-maeda/paywings Enables AI agents to request policy-governed payments through MCP tools, with server-side enforcement of spending limits, merchant allow-lists, Pix BR Code validation, approval thresholds, and hash-chained audit logging in a sandbox. It let | |
| Memento diego-ninja/memento Persistent memory system for LLMs with lossless transcript management, enabling memory recall and full session history search across all conversations. | |
| georef-mcp diego-prieri/georef-mcp Enables AI agents to search and normalize Argentina’s official geographic data, including provinces, departments, municipalities, localities, street addresses, and reverse geocoding, through the public Georef API. | |
| Tickets MCP Server diego-prieri/mcp-server-template Enables agents to list, fetch, and create tickets through a ticket-tracking backend that can be swapped between an in-memory store and a REST API. Inputs are schema-validated, results include both text summaries and structured content, and | |
| caldav-mcp diego04919/caldav-mcp Enables AI assistants to connect to CalDAV servers and manage calendars, events, and tasks through tools for listing, creating, updating, completing, and deleting items. | |
| substack-mcp diegoa280/python-substack Enables MCP-compatible clients to author Markdown posts and safely create, inspect, export, update, schedule, publish, and delete drafts with explicit safeguards. | |
| YNAB MCP server diegoaad/ynab-mcp Enables read-only, on-demand inspection of accounts, category balances, transactions, and spending summaries for a single personal budget plan, with bounded date ranges and no persistence. | |
| Canvas LMS MCP diegoadborges/canvas-mcp Enables AI agents to access Canvas LMS academic data such as courses, assignments, grades, and events via MCP tools. |
44,501–44,550 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.