🧰 K3 MCP Toolbox
"Give your AI Agent the tools it actually needs." A production-ready Model Context Protocol (MCP) Server for Windows & Docker.
⚡ Quick Start (The "30-Second" Rule)
Installation
pip install -r requirements.txt
Run Server
# Exposes the server on stdio (works with Claude Desktop / Cursor)
python server.py
Configure (Claude Desktop / Cursor)
Add this to your claude_desktop_config.json:
{
"mcpServers": {
"k3-toolbox": {
"command": "python",
"args": ["/absolute/path/to/k3-mcp-toolbox/server.py"]
}
}
}
🛠️ The Tools
1. sequential_thinking (The Logic)
A "System 2" thinking module. Allows agents to break complex problems into dynamic steps, revise previous thoughts, and branch constraints.
- Based on Protocol 310.
2. mrl_search (The Brain)
Matryoshka Representation Learning (MRL) indexer.
- Zero-Setup: Uses local storage (no vector DB required).
- SOTA: Configured for
text-embedding-004(Gemini) by default. - Fast: Funnel search implementation (64-dim shortlist -> 768-dim rerank).
3. kill_zombies (The Ops)
Windows Only. Instantly terminates stuck Chrome/Chromedriver processes and releases file locks. Essential for Selenium/Playwright agents.
🤖 Agent Context (AI-Ready)
This repository includes a context.md file optimized for LLM consumption.
If you are using Cursor or Windsurf, simply @context.md to give your AI full understanding of this codebase.
🤝 Contributing
We follow the K3-9000 Growth Protocol.
- Hygiene: No
.envcommits. - Style: Type hints required.
- Tests: Must pass
test_mcp_health.py.
License: MIT
Metadata
Release files for iflow-mcp_fandry96-k3-mcp-toolbox 0.1.0
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | Actions |
|---|---|---|---|---|
| iflow_mcp_fandry96_k3_mcp_toolbox-0.1.0.tar.gz | 6.0 MB | Without provenance | Details for iflow_mcp_fandry96_k3_mcp_toolbox-0.1.0.tar.gz |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Actions Reset |
|---|---|---|---|---|
| iflow_mcp_fandry96_k3_mcp_toolbox-0.1.0-py3-none-any.whl | Python 3 | none | any | Details for iflow_mcp_fandry96_k3_mcp_toolbox-0.1.0-py3-none-any.whl |
Total release size: 12.1 MB
Release files / iflow_mcp_fandry96_k3_mcp_toolbox-0.1.0.tar.gz
| Download URL | iflow_mcp_fandry96_k3_mcp_toolbox-0.1.0.tar.gz |
|---|---|
| Size | 6.0 MB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
57075bd71b6c61882048f0d7606b18314f17a910e4c99fb7bf16aa4735dbe48f
|
|
BLAKE2b-256 checksum How to use checksums |
70663733eef09a742f9ca3ffa1743b4d65fc8ecc3ce7b8d3ff63784a9fadd2a8
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
uv/0.10.2 {"installer":{"name":"uv","version":"0.10.2","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":{"name":"Debian GNU/Linux","version":"13","id":"trixie","libc":null},"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":null}
|
Release files / iflow_mcp_fandry96_k3_mcp_toolbox-0.1.0-py3-none-any.whl
| Download URL | iflow_mcp_fandry96_k3_mcp_toolbox-0.1.0-py3-none-any.whl |
|---|---|
| Size | 6.0 MB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
5f46d2a129981b383f619125927c919b8480de9ac8610066e393111b41208b94
|
|
BLAKE2b-256 checksum How to use checksums |
d4b50c3f00507abdd443334d2eba59d09855eb1cc594ebaffbf717d9d625a209
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
uv/0.10.2 {"installer":{"name":"uv","version":"0.10.2","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":{"name":"Debian GNU/Linux","version":"13","id":"trixie","libc":null},"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":null}
|
Security for iflow-mcp_fandry96-k3-mcp-toolbox 0.1.0
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
No provenance found
None of the files in this release were uploaded with provenance metadata.
A note on package security
PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.
To learn more about protecting yourself from malicious actors, visit our package security documentation.