### MCP-tools Build Data Structure

Source: https://github.com/xfey/mcp-zero/blob/master/README.md

This snippet details the directory structure for building the MCP-tools dataset, including scripts for extracting server summaries and running models.

```bash
MCP-tools/
├── build_data
│   ├── get_server_summary.py       # code to extract structural data for MCP server's ReadMe file
│   ├── run_vllm.sh                 # deploy the Qwen2.5-72B-Instruct model with VLLM
│   └── server_summary.prompt       # the prompt for extracting dataset
└── download_data.md
```

--------------------------------

### MCP-Zero Project Structure

Source: https://github.com/xfey/mcp-zero/blob/master/README.md

This snippet outlines the directory structure of the MCP-Zero project, detailing the purpose of key Python files and directories related to experiments, matching, prompting, and utilities.

```python
MCP-zero/
├── experiment_apibank.py       # experiments: APIBank
├── experiment_mcptools.py      # experiments: mcp_tools (needle test)
├── matcher.py                  # code for similarity matching
├── prompt_guide/               # prompts for our method
├── reformatter.py              # json formatter for tool description
├── sampler.py                  # sampler for selecting target tool
├── test_cases.jsonl            # testcase for the matcher
├── test_matcher.py             # unit test for the matcher
└── utils.py                    # utils: grid_search
```

--------------------------------

### MCP-Zero Citation

Source: https://github.com/xfey/mcp-zero/blob/master/README.md

BibTeX entry for the MCP-Zero paper, providing citation details for academic referencing.

```bibtex
@article{fei2025mcp,
  title={MCP-Zero: Active Tool Discovery for Autonomous LLM Agents},
  author={Fei, Xiang and Zheng, Xiawu and Feng, Hao},
  journal={arXiv preprint arXiv:2506.01056},
  year={2025}
}
```

--------------------------------

### MCP-tools Dataset Structure

Source: https://github.com/xfey/mcp-zero/blob/master/README.md

Defines the JSON structure for the MCP-tools dataset, which contains information about MCP servers and their associated tools, including descriptions and embeddings.

```json
{
  "server_name": string, // The name of the MCP server, extracted or inferred from the README
  "server_summary": string, // A summary of the server's purpose and capabilities, based on all relevant parts of the README.
  "server_description": string, // Description from metadata. 
  "description_embedding": float[3072], // The embedding of the server description from text-embedding-3-large
  "summary_embedding": float[3072], // The embedding of the server summary from text-embedding-3-large
  "tools": [
    {
      "name": string, // The function/tool name
      "description": string, // A concise description of what the tool does
      "description_embedding": float[3072], // The embedding of the tool description from text-embedding-3-large
      "parameter": {
        "param1": "(type) description1",
        "param2": "(Optional, type) description2"
      }
    }
  ]
}
```

=== COMPLETE CONTENT === This response contains all available snippets from this library. No additional content exists. Do not make further requests.