{"$schema":"https://wellknown.network/schemas/agent-record-v1.json","schemaVersion":"1","id":"ag_9dc3n93dvkbs","handle":"iflow-mcp-fandry96-k3-mcp-toolbox","url":"https://wellknown.network/agents/iflow-mcp-fandry96-k3-mcp-toolbox","links":{"self":"https://wellknown.network/agents/iflow-mcp-fandry96-k3-mcp-toolbox/record.json","html":"https://wellknown.network/agents/iflow-mcp-fandry96-k3-mcp-toolbox","markdown":"https://wellknown.network/agents/iflow-mcp-fandry96-k3-mcp-toolbox/record.md","api":"https://wellknown.network/api/v1/agents/iflow-mcp-fandry96-k3-mcp-toolbox","status":"https://wellknown.network/api/v1/agents/iflow-mcp-fandry96-k3-mcp-toolbox/status","claim":"https://wellknown.network/agents/iflow-mcp-fandry96-k3-mcp-toolbox/claim","claimApi":"https://wellknown.network/api/v1/claims","claimDescriptor":"https://wellknown.network/agents/iflow-mcp-fandry96-k3-mcp-toolbox/claim.json","badge":"https://wellknown.network/agents/iflow-mcp-fandry96-k3-mcp-toolbox/badge.svg","openapi":"https://wellknown.network/openapi.json","history":"https://wellknown.network/api/v1/agents/iflow-mcp-fandry96-k3-mcp-toolbox/history","tools":"https://wellknown.network/api/v1/agents/iflow-mcp-fandry96-k3-mcp-toolbox/tools"},"ard":{"identifier":"urn:air::server:iflow-mcp-fandry96-k3-mcp-toolbox","type":"application/mcp-server-card+json"},"kind":"mcp_server","declared":{"name":"iflow-mcp_fandry96-k3-mcp-toolbox","summary":"K3 MCP Toolbox - Windows-native MCP Server implementation with cognitive protocols","description":"# 🧰 K3 MCP Toolbox\n\n> **\"Give your AI Agent the tools it actually needs.\"**\n> A production-ready Model Context Protocol (MCP) Server for Windows & Docker.\n\n[![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT)\n[![Python 3.10+](https://img.shields.io/badge/python-3.10+-blue.svg)](https://www.python.org/downloads/)\n[![MCP Ready](https://img.shields.io/badge/MCP-Ready-green.svg)](https://modelcontextprotocol.io)\n\n## ⚡ Quick Start (The \"30-Second\" Rule)\n\n**Installation**\n\n```bash\npip install -r requirements.txt\n```\n\n**Run Server**\n\n```bash\n# Exposes the server on stdio (works with Claude Desktop / Cursor)\npython server.py\n```\n\n**Configure (Claude Desktop / Cursor)**\nAdd this to your `claude_desktop_config.json`:\n\n```json\n{\n  \"mcpServers\": {\n    \"k3-toolbox\": {\n      \"command\": \"python\",\n      \"args\": [\"/absolute/path/to/k3-mcp-toolbox/server.py\"]\n    }\n  }\n}\n```\n\n---\n\n## 🛠️ The Tools\n\n### 1. `sequential_thinking` (The Logic)\n\nA \"System 2\" thinking module. Allows agents to break complex problems into dynamic steps, revise previous thoughts, and branch constraints.\n\n* *Based on Protocol 310.*\n\n### 2. `mrl_search` (The Brain)\n\n**Matryoshka Representation Learning (MRL)** indexer.\n\n* **Zero-Setup**: Uses local storage (no vector DB required).\n* **SOTA**: Configured for `text-embedding-004` (Gemini) by default.\n* **Fast**: Funnel search implementation (64-dim shortlist -> 768-dim rerank).\n\n### 3. `kill_zombies` (The Ops)\n\n*Windows Only.* Instantly terminates stuck Chrome/Chromedriver processes and releases file locks. Essential for Selenium/Playwright agents.\n\n---\n\n## 🤖 Agent Context (AI-Ready)\n\nThis repository includes a `context.md` file optimized for LLM consumption.\nIf you are using Cursor or Windsurf, simply `@context.md` to give your AI full understanding of this codebase.\n\n## 🤝 Contributing\n\nWe follow the **K3-9000 Growth Protocol**.\n\n* **Hygiene**: No `.env` commits.\n* **Style**: Type hints required.\n* **Test…","publisher":null,"homepage":"https://github.com/Fandry96/k3-mcp-toolbox-public","repository":"https://github.com/Fandry96/k3-mcp-toolbox-public","version":"0.1.0","license":null,"protocols":["mcp"],"tags":["mcp"],"pricing":null,"endpoints":[{"url":"pypi:iflow-mcp_fandry96-k3-mcp-toolbox","type":"package_pypi","auth":null,"probeable":false}],"skills":null,"tools":null,"extra":null,"attribution":{"kind":"pypi","name":"pypi","repoUrl":"pypi","summary":"pypi","version":"pypi","description":"pypi","homepageUrl":"pypi"}},"derived":{"capabilities":[{"slug":"infra.browser-automation","name":"Browser Automation","confidence":1,"provenance":"derived"}],"categories":["infra"],"language":"en"},"observed":{"status":"unknown","statusReason":"Distributed as a package to run locally; no network endpoint to check.","lastOkAt":null,"lastProbedAt":null,"statusComputedAt":null,"reliability30d":null,"latestObservations":[],"tools":null,"package":{"name":"iflow-mcp_fandry96-k3-mcp-toolbox","registry":"pypi","observedAt":"2026-11-09T08:24:43.594Z","publishedAt":"2026-02-26T14:47:10.506027Z","latestVersion":"0.1.0"},"toolSurface":null,"endpointFacts":[]},"verification":{"claimed":false,"claimedAt":null,"proofs":[]},"provenance":{"sources":[{"source":"pypi","key":"iflow-mcp_fandry96-k3-mcp-toolbox","url":"https://pypi.org/project/iflow-mcp_fandry96-k3-mcp-toolbox/","firstSeenAt":"2026-09-09T18:22:21.608Z","fetchedAt":"2026-11-09T08:23:18.119Z","normalizedAt":"2026-11-09T08:23:18.119Z"}]},"firstSeenAt":"2026-09-09T18:22:21.608Z","updatedAt":"2026-11-09T08:24:43.594Z"}