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 |
|---|---|
| Linear Kanban Server 0xikarus/linear-kanban-mcp Enables management of Linear kanban boards, projects, and issues directly through Claude via the Model Context Protocol. It includes an automatic task tracking hook that synchronizes Claude's real-time work progress directly to Linear board | |
| Intuition MCP Server 0xintuition/intuition-mcp-server An HTTP stream server for interacting with the Intuition knowledge graph, enabling users to query and manage data through tools like extracting triples, searching entities, retrieving account info, and exploring relationships. | |
| Gibraltar Prediction Markets MCP Server 0xjb-dev/gibraltar-prediction-markets-mcp Enables querying the Gibraltar Prediction Market Regulations 2026 in plain English via MCP clients, returning exact cited regulation text. | |
| CodeAnalysis MCP Server 0xjcf/mcp_codeanalysis A comprehensive Model Context Protocol server for advanced code analysis that provides tools for syntax analysis, dependency visualization, and AI-assisted development workflow support. | |
| omnifocus-mcp-bridge 0xjem/omnifocus-mcp-bridge An authenticated Streamable HTTP bridge that wraps the local OmniFocus MCP server, enabling remote MCP access with bearer token authentication and optional Tailscale Serve. | |
| screenwright 0xjesus/screenwright Enables users to create subtitled tutorial videos by scripting browser interactions with Playwright, outputting MP4 with burned-in captions and SRT file. | |
| Telegram MCP 0xjesus/telegram-mcp Connects a user's messaging account to an MCP assistant for conversation search, local transcription, attachment analysis, group monitoring controls, and durable scheduled messages. | |
| first-mcp-kit 0xjrp/first-mcp-kit A real, runnable MCP server exposing three read-only tools (inventory, pricing, hours) with a CLI agent that lets Claude discover and call them. | |
| mcp-starter-kit 0xjrp/mcp-starter-kit A starter kit for creating a read-only MCP server that lets AI assistants access business information, calculate prices, answer FAQs, and check availability. | |
| spreadsheet-qa-kit MCP server 0xjrp/spreadsheet-qa-kit Enables querying your spreadsheet using natural language questions; provides read-only tools for schema, sample data, and structured query execution with auditable computation traces. | |
| MegaMemory 0xk3vin/megamemory An MCP server that lets coding agents build and query a persistent knowledge graph of concepts, architecture, and decisions, enabling them to remember across sessions. | |
| vikunja-mcp 0xk3vin/vikunja-mcp Connect your AI assistant to Vikunja, the open-source task manager. This MCP server lets you manage projects, tasks, kanban boards, and more—just by asking. | |
| agent-bridge 0xkaz/agent-bridge A Kanban board enabling AI agents and humans to collaborate on tasks through MCP tools for project and task management. | |
| AgentClip MCP Server 0xkaz/agentclip Enables AI agents to store, search (keyword and semantic), retrieve, update, and delete personal browser clips from a Cloudflare-backed store, authenticated via per-user token. | |
| Redmine MCP Server 0xkillaflow/agama-redmine-mcp Enables AI agents to interact with Redmine through intent-shaped tools for issue tracking, time logging, project management, and more. | |
| Ethereum RPC MCP Server 0xkoda/eth-mcp Provides tools for AI assistants to interact with the Ethereum blockchain through standard JSON-RPC methods, enabling queries for account balances, gas prices, and smart contract code. | |
| WireMCP 0xkoda/wiremcp A Model Context Protocol server that provides LLMs with real-time network traffic analysis capabilities, enabling tasks like threat hunting, network diagnostics, and anomaly detection through Wireshark's tshark. | |
| freee-hr-mcp 0xkohe/freee-hr-mcp Enables managing freee HR operations like employee data, attendance, leave, and approvals through natural language in MCP-compatible clients such as Claude Desktop. | |
| MCP Argentina Datos 0xkoller/mcp-argentina-datos A Model Context Protocol server that provides tools to access information about Argentina through the Argentina Datos API, including holidays, presidential events, dollar exchange rates, and legislative data. | |
| rafter-mcp 0xksure/rafter-mcp Shared memory, skills and agents for your team — Claude, Cursor and other MCP clients start every session with how your firm actually works. Versioned artifacts with a wiki-link graph, remote Streamable HTTP with OAuth 2.1 sign-in. | |
| ssr-concept-mcp 0xksure/ssr-concept-mcp Concept-test your product with synthetic consumers, straight from Claude Code. It turns free-text reactions from roleplayed personas into purchase-intent reports using Semantic Similarity Rating. | |
| Brain Bridge 0xlicy/antigravity-brain-bridge Multi-conversation collaboration MCP server enabling cross-conversation memory, task delegation, and parallel workflow orchestration. | |
| OpenAPK 0xllvel/openapk Enables mobile application penetration testing with 83+ tools covering Frida instrumentation, APK analysis, decompilation, signing, emulator support, and system compatibility checks. | |
| medium-vault 0xmax-sec/medium-vault Enables offline archiving, deduplication, and quality-controlled indexing of Medium articles, exposing MCP tools for retrieving, managing, and exporting knowledge for AI agents and local pipelines. | |
| Hercules MCP 0xmihirk/hercules-mcp Enables AI agents to perform professional penetration testing through a containerized Kali Linux environment, exposing industry-standard offensive security tools as structured MCP tools. | |
| @cobbee-mcp/server 0xmonas/cobbee-mcp Enables AI agents to manage creator profiles, sell digital products, and make USDC payments on Base using the x402 payment protocol through the Cobbee platform. | |
| steno-personal 0xmythril/steno-personal Lets AI agents search and read your personal Telegram and WhatsApp conversations through a self-hosted, read-only MCP server backed by a single SQLite file. | |
| MCP DataBridge 0xnadr/mcp_databridge Enables AI agents to interact with the Titanic passenger database via MCP, providing tools for querying, analysis, and exploration. | |
| skill-lint 0xnagato/skill-lint Lint agent SKILL.md files and MCP tool schemas to catch issues like missing descriptions, similar skills, unconstrained parameters, and destructive tools without confirmation gates. | |
| Sentinel 0xnickdev/sentinel Enables AI agents to score Solana tokens, simulate and decode transactions, and apply owner-defined limits, allowlists and slippage rules before anything is signed, returning a clear allow, confirm, block or freeze verdict. Also supports on | |
| DG-MCP 0xnullai/dg-mcp Enables MCP clients to control DG-Lab Coyote 2.0/3.0 devices via Bluetooth, providing tools for device scanning, connection, strength adjustment, wave design, and emergency stop. | |
| mcp-omni-context 0xnurrabby/mcp-omni-context MCP server that gives AI chat real vision by reading images, files, logs, and zip archives via local OCR in any language, with privacy-first processing. | |
| omni-vision-pro 0xnurrabby/omni-vision-pro MCP server that analyzes images, reads code and ZIP archives, and provides text context for non-vision models. | |
| OKX-DEX-SDK MCP SSE Server 0xobedient/okx-mcp An SSE (Server-Sent Events) server that leverages OKX DEX SDK to support DEX trading operations on Solana blockchain and cross-chain bridge transactions. | |
| kindle-notes 0xpili/kindle-notes Enables AI assistants to search and read locally stored e-reader highlights, notes, bookmarks, and book lists from a synced database. Provides tools for full-text search, per-book notes, recent items, random highlights, and sync status. | |
| pi-browser-use 0xplayerone/pi-browser-use Enables the Pi coding agent to drive Chrome through DevTools, providing browser automation tools, persistent or isolated profiles, screenshots, page analysis, and bundled agent policies. | |
| luda 0xpolarzero/luda An MCP server that gives AI agents local Linux desktop control through tools for screenshots, accessibility, mouse, keyboard, and reliable text input. | |
| Zerodha Trading MCP 0xprajapati/zerodha-trade-mcp A Model Context Protocol server that enables AI models to interact with the Zerodha trading platform, allowing users to execute trades, view portfolio holdings, and manage positions through a standardized interface. | |
| NmapMCP 0xpratikpatil/nmapmcp Enables network scanning and reconnaissance tasks like port scanning, OS detection, DNS brute force, and more through MCP interfaces. | |
| cutroom 0xpratzyy/cutroom Enables AI agents to edit talking-head videos locally by transcribing footage, applying validated edit operations like cutting fillers and silences, adding zooms, captions, looks and branding, and checking results with rendered previews. Ag | |
| clawton-agentos 0xr-1/clawton-agentos Enables AI agents to enforce configurable spending policies before executing trades or x402 payments via Binance Agent OS, recording every policy decision onchain to an Ethereum Sepolia audit log. | |
| mcp-starter 0xrameshh/mcp-starter A production-grade MCP starter server in TypeScript with example tools, resources, and integration tests. It provides a clean, extensible foundation for building custom MCP servers. | |
| MCP RAG Server 0xrdan/mcp-rag-server Enables AI assistants to search and retrieve information from your knowledge base using RAG (Retrieval-Augmented Generation) with hybrid search, document indexing, and ChromaDB vector storage. | |
| parseltongue-capsules 0xreconlion/parseltongue-mcp Lets an agent manage local identities and public contact cards, and hide a message inside ordinary-looking cover text via concealment carriers, while inspecting and verifying sealed notes and encrypted capsules entirely on the user's own ma | |
| REI Crypto MCP Server 0xreisearch/crypto-mcp-beta FastMCP implementation providing API access to DefiLlama Pro, CoinGecko Pro, and Arkham Intelligence for crypto data retrieval without requiring users to manage individual API keys. | |
| Cognio 0xrelogic/cognio Persistent semantic memory server for AI assistants via MCP, enabling long-term context retention and semantic search across conversations. | |
| JLC EDA MCP Server 0xruth1ezz/jlc-eda-mcp Enables MCP clients to control JLCPCB EDA (嘉立创 EDA) for PCB and schematic design operations through a bridge and plugin architecture. | |
| MCP Server with Local LLM 0xsaju/mcp-server Integrates local language models (like Qwen3-8B) with MCP clients, providing tools for chat, code analysis, text generation, translation, and content summarization using your own hardware. | |
| 402 Coffee 0xsector/402coffee Non-custodial x402 tip jars for the agentic web, enabling USDC tips via a hosted MCP tool for agents. | |
| Pwno MCP 0xsensei/pwno-mcp Enables stateful binary analysis and pwn research through GDB/pwndbg debugging capabilities. Supports loading binaries, setting breakpoints, memory analysis, compilation with sanitizers, and process management for vulnerability research. |
21,601–21,650 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.