Metadata-Version: 2.4
Name: mcp_codemode
Version: 0.0.4
Project-URL: Home, https://github.com/datalayer/mcp-codemode
Author-email: Datalayer <info@datalayer.io>
License: BSD 3-Clause License
        
        Copyright (c) 2025, Datalayer
        All rights reserved.
        
        Redistribution and use in source and binary forms, with or without
        modification, are permitted provided that the following conditions are met:
        
        1. Redistributions of source code must retain the above copyright notice, this
           list of conditions and the following disclaimer.
        
        2. Redistributions in binary form must reproduce the above copyright notice,
           this list of conditions and the following disclaimer in the documentation
           and/or other materials provided with the distribution.
        
        3. Neither the name of the copyright holder nor the names of its
           contributors may be used to endorse or promote products derived from
           this software without specific prior written permission.
        
        THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
        AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
        IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
        DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT HOLDER OR CONTRIBUTORS BE LIABLE
        FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
        DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR
        SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER
        CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY,
        OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
        OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
License-File: LICENSE
Keywords: AI,Jupyter,MCP,Model Context Protocol
Classifier: Intended Audience :: Developers
Classifier: Intended Audience :: System Administrators
Classifier: License :: OSI Approved :: BSD License
Classifier: Programming Language :: Python
Classifier: Programming Language :: Python :: 3
Requires-Python: >=3.10
Requires-Dist: agent-skills
Requires-Dist: code-sandboxes
Requires-Dist: httpx>=0.24
Requires-Dist: mcp[cli]>=1.0
Provides-Extra: lint
Requires-Dist: mdformat-gfm>=0.3.5; extra == 'lint'
Requires-Dist: mdformat>0.7; extra == 'lint'
Requires-Dist: ruff; extra == 'lint'
Provides-Extra: pydantic-ai
Requires-Dist: pydantic-ai-slim; extra == 'pydantic-ai'
Requires-Dist: pydantic-graph; extra == 'pydantic-ai'
Provides-Extra: test
Requires-Dist: ipykernel; extra == 'test'
Requires-Dist: jupyter-server<3,>=1.6; extra == 'test'
Requires-Dist: pytest-asyncio>=0.21; extra == 'test'
Requires-Dist: pytest>=7.0; extra == 'test'
Provides-Extra: typing
Requires-Dist: mypy>=0.990; extra == 'typing'
Description-Content-Type: text/markdown

<!--
  ~ Copyright (c) 2025-2026 Datalayer, Inc.
  ~
  ~ BSD 3-Clause License
-->

[![Datalayer](https://assets.datalayer.tech/datalayer-25.svg)](https://datalayer.io)

[![Become a Sponsor](https://img.shields.io/static/v1?label=Become%20a%20Sponsor&message=%E2%9D%A4&logo=GitHub&style=flat&color=1ABC9C)](https://github.com/sponsors/datalayer)

# 🔧 MCP Codemode

[![PyPI - Version](https://img.shields.io/pypi/v/mcp-codemode)](https://pypi.org/project/mcp-codemode)

**Code Mode for MCP Tools**: Programmatically call and compose MCP tools through code execution instead of individual LLM tool calls.

## Overview

MCP Codemode enables a "Code Mode" pattern where AI agents write Python code that orchestrates multiple MCP tool calls, rather than making individual tool calls through LLM inference. This approach is:

- **More efficient**: Reduce LLM calls for multi-step operations
- **More reliable**: Use try/except for robust error handling
- **More powerful**: Parallel execution with asyncio, loops, conditionals
- **More composable**: Save reusable patterns as skills

## Configuration highlights

- **Direct tool calls**: `allow_direct_tool_calls` (default: false). When false, `call_tool` is hidden and all execution flows through `execute_code`.
- **Tool listing filters**: `list_tool_names` accepts `server`, `keywords`, and `limit` for fast, filtered discovery.
- **Search rerank hook**: Provide an optional `tool_reranker` callable to reorder search results before they are returned (e.g., LLM-based rerankers). Falls back to registry order when not provided.
- **Execution language**: `execute_code` runs Python inside the configured sandbox; import bindings from `generated.servers.<server_name>`.
- **Safety cap**: `max_tool_calls` can limit the number of tool invocations per `execute_code` run.
- **Tool examples**: tool discovery and details include `output_schema` and `input_examples` to improve parameter accuracy.
- **Deferred tools**: tools may be marked `defer_loading` by servers. `list_tool_names` excludes them by default; `search_tools` includes them unless `include_deferred=false`.

## Installation

\`\`\`bash
pip install mcp-codemode
\`\`\`

## Quick Start

\`\`\`python
from mcp_codemode import ToolRegistry, CodeModeExecutor, MCPServerConfig

# Set up registry with MCP servers
registry = ToolRegistry()
registry.add_server(MCPServerConfig(
    name="filesystem",
    transport="stdio",
    command="npx",
    args=["-y", "@anthropic/mcp-server-filesystem", "/tmp"]
))
await registry.discover_all()

# Execute code that composes tools
async with CodeModeExecutor(registry) as executor:
    result = await executor.execute("""
        from generated.servers.filesystem import read_file, write_file
        
        # Read multiple files
        content1 = await read_file({"path": "/tmp/file1.txt"})
        content2 = await read_file({"path": "/tmp/file2.txt"})
        
        # Process and combine
        combined = content1 + "\\n---\\n" + content2
        
        # Write result
        await write_file({"path": "/tmp/combined.txt", "content": combined})
    """)
\`\`\`

## Features

### Progressive Tool Discovery

Use the Tool Search Tool to discover relevant tools without loading all definitions upfront:

\`\`\`python
# Search for tools matching a description (includes deferred tools)
result = await registry.search_tools("file operations", limit=10, include_deferred=True)

for tool in result.tools:
    print(f"{tool.name}: {tool.description}")

# Fast listing (deferred tools excluded by default)
names = registry.list_tool_names(limit=50)
\`\`\`

### Code-Based Tool Composition

Execute Python code in an isolated sandbox with auto-generated tool bindings:

\`\`\`python
async with CodeModeExecutor(registry) as executor:
    execution = await executor.execute("""
        import asyncio
        from generated.servers.filesystem import ls, read_file
        
        # List all files
        files = await ls({"path": "/data"})
        
        # Read all files in parallel
        contents = await asyncio.gather(*[
            read_file({"path": f}) for f in files
        ])
    """, timeout=30.0)

# Standard outputs are available on the execution object
print(execution.stdout)
print(execution.stderr)
print(execution.text)
\`\`\`

### Skills (Reusable Compositions)

Skills are Python files that compose tools into reusable operations. This allows agents to evolve their own toolbox by saving useful code patterns.

#### Creating Skills as Code Files

The primary pattern is skills as Python files in a `skills/` directory:

```python
# skills/batch_process.py
"""Process all files in a directory."""

async def batch_process(input_dir: str, output_dir: str) -> dict:
    """Process all files in a directory.
    
    Args:
        input_dir: Input directory path.
        output_dir: Output directory path.
    
    Returns:
        Processing statistics.
    """
    from generated.servers.filesystem import list_directory, read_file, write_file

## Examples

See the runnable examples in [examples/README.md](examples/README.md).

```bash
python examples/codemode_example.py
python examples/codemode_patterns_example.py
```
    
    entries = await list_directory({"path": input_dir})
    processed = 0
    
    for entry in entries.get("entries", []):
        content = await read_file({"path": f"{input_dir}/{entry}"})
        # Process content...
        await write_file({"path": f"{output_dir}/{entry}", "content": content.upper()})
        processed += 1
    
    return {"processed": processed}
```

#### Using Skills in Executed Code

Skills are imported and called like any Python module:

```python
# In executed code
from skills.batch_process import batch_process

result = await batch_process("/data/input", "/data/output")
print(f"Processed {result['processed']} files")
```

#### Composing Skills

Skills can import and use other skills:

```python
# skills/analyze_and_report.py
"""Analyze data and generate a report."""

async def analyze_and_report(data_dir: str) -> dict:
    from skills.batch_process import batch_process
    from skills.generate_report import generate_report
    
    # First process the files
    process_result = await batch_process(data_dir, f"{data_dir}/processed")
    
    # Then generate a report
    report = await generate_report(f"{data_dir}/processed")
    
    return {"processed": process_result["processed"], "report": report}
```

#### Managing Skills

```python
from mcp_codemode.skills import SkillDirectory, setup_skills_directory

# Initialize skills directory
skills = setup_skills_directory("./workspace/skills")

# List available skills
for skill in skills.list():
    print(f"{skill.name}: {skill.description}")

# Search for relevant skills
matches = skills.search("data processing")

# Create a new skill programmatically
skills.create(
    name="my_skill",
    code='async def my_skill(x: str) -> str: return x.upper()',
    description="Transform text to uppercase",
)
```

### MCP Server

Expose Code Mode capabilities as an MCP server:

\`\`\`python
from mcp_codemode import codemode_server, configure_server

configure_server()
codemode_server.run()
\`\`\`

Tools exposed:
- \`search_tools\` - Progressive tool discovery
- \`execute_code\` - Run code that composes tools
- \`call_tool\` - Direct tool invocation
- \`save_skill\` / \`run_skill\` - Skill management

## Key Concepts

### Tool Discovery

Instead of loading all tool definitions upfront (which can overwhelm context), use the Tool Search Tool pattern for progressive discovery based on the task at hand.

### Tool Composition

Compose tools through code instead of reading all data into LLM context. This is faster, more reliable (no text reproduction errors), and more efficient.

### Control Flow

Code allows models to implement complex control flow: loops, conditionals, waiting patterns, and parallel execution without burning through context with repeated tool calls.

### State Persistence

When running in a sandbox (like mcp-codemode), state can persist on disk. Skills themselves can be saved and composed into increasingly powerful tools.

## Architecture

\`\`\`
┌─────────────────────────────────────────────────────┐
│                   MCP Codemode                       │
├─────────────────────────────────────────────────────┤
│  ┌──────────────┐  ┌──────────────┐  ┌───────────┐ │
│  │ Tool Registry │  │ Code Executor│  │  Skills   │ │
│  │  - Discovery  │  │  - Sandbox   │  │ - Save    │ │
│  │  - Search     │  │  - Bindings  │  │ - Load    │ │
│  │  - Cache      │  │  - Execute   │  │ - Execute │ │
│  └──────────────┘  └──────────────┘  └───────────┘ │
├─────────────────────────────────────────────────────┤
│                    mcp-codemode                    │
│              (Isolated execution environment)        │
└─────────────────────────────────────────────────────┘
\`\`\`

## References

- [Introducing Code Mode](https://blog.cloudflare.com/introducing-code-mode) - Cloudflare
- [Code Execution with MCP](https://www.anthropic.com/engineering/code-execution-with-mcp) - Anthropic
- [Programmatic Tool Calling](https://platform.claude.com/docs/en/agents-and-tools/tool-use/programmatic-tool-calling) - Anthropic
- [Advanced Tool Use](https://www.anthropic.com/engineering/advanced-tool-use) - Anthropic
- [Programmatic MCP Prototype](https://github.com/domdomegg/programmatic-mcp-prototype)

## License

BSD 3-Clause License
