Tachikoma Game Design MCP

Local and read-only MCP server for Claude to query a Chroma library on video game narrative and design. This repository contains only the public runtime; extraction, chunking, and embedding generation live in tachikoma-rag-infra.

Features

• Multilingual semantic search with BAAI/bge-m3.

• Results with book, page, text, and similarity.

• MCP transport via stdio, no open ports.

• Offline operation with a previously downloaded model.

• Read-only tools and protection against embedded instructions.

• Configurable index path, no infrastructure coupling.

Related MCP server: hw_rag_mcp

Contents

mcp_server.py                         Servidor MCP.
claude_desktop_config.example.json    Configuración de Claude Desktop.
requirements.txt                      Dependencias de ejecución.
pyrightconfig.json                    Configuración del análisis estático.
tests/test_mcp_server.py               Pruebas del runtime.

The PDFs, texts, chunks, embeddings, and Chroma databases are not part of this public repository.

Installation

py -3.12 -m venv .venv
.venv\Scripts\Activate.ps1
python -m pip install -r requirements.txt

Providing an index

Tachikoma needs a Chroma collection created with the same embedding model. You can generate it using the private repository tachikoma-rag-infra or receive it through an authorized channel.

Available variables:

The model must be downloaded to the local cache before starting the MCP. The server uses local_files_only=True and will not download files during a conversation.

The log is rotating, does not store query text, and records model load times, Chroma connection, embedding, vector search, and total execution time.

Configuring Claude Desktop

1. Copy the entry from claude_desktop_config.example.json inside mcpServers.

2. Replace the repository, Python, and Chroma paths.

3. Completely close Claude Desktop and reopen it.

On Windows, the configuration is usually located at:

%APPDATA%\Claude\claude_desktop_config.json

Tools

• search_narrative_library: semantic search with optional book filter.

• read_book_page: retrieves chunks of a page in order.

• list_library_books: lists the indexed books.

• library_status: checks model, collection, and chunk count.

Tests

python -m unittest discover -s tests -p "test_*.py"

Optional static analysis:

uv tool install basedpyright
basedpyright --pythonpath ".venv\Scripts\python.exe" -p pyrightconfig.json

Privacy

The index may contain fragments of documents. Do not publish Chroma or distribute indices created from copyrighted material without permission.