# Lc2mcp

> Convert LangChain tools to FastMCP tools

- **Type:** MCP server
- **Install:** `agentstack add mcp-xiaotonng-lc2mcp`
- **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior
- **Seller:** [xiaotonng](https://agentstack.voostack.com/s/xiaotonng)
- **Installs:** 0
- **Category:** [AI & ML](https://agentstack.voostack.com/c/ai-and-ml)
- **Latest version:** 0.1.0
- **License:** MIT
- **Upstream author:** [xiaotonng](https://github.com/xiaotonng)
- **Source:** https://github.com/xiaotonng/lc2mcp

## Install

```sh
agentstack add mcp-xiaotonng-lc2mcp
```

Requires the [AgentStack CLI](https://agentstack.voostack.com/docs/cli). Works with Claude Code, Cursor, and any MCP-compatible agent.

## About

# lc2mcp

[](https://pypi.org/project/lc2mcp/)
[](https://pypi.org/project/lc2mcp/)
[](https://opensource.org/licenses/MIT)

**Convert LangChain tools to FastMCP tools — in one line of code.**

> Stop rewriting your tools. Just adapt them.

`lc2mcp` is a lightweight adapter that converts existing **LangChain tools** into **FastMCP tools**, enabling you to quickly build MCP servers accessible to Claude, Cursor, and any MCP-compatible client.

---

## ✨ Features

| Feature | Description |
|---------|-------------|
| 🔄 **Instant Conversion** | One function call to convert any LangChain tool to FastMCP tool |
| 📦 **Ecosystem Access** | Unlock 1000+ LangChain community tools (Search, Wikipedia, SQL, APIs...) |
| 🎯 **Zero Boilerplate** | Automatic Pydantic → JSON Schema conversion |
| 🔐 **Context Injection** | Pass auth, user info, and request context to tools |
| 📊 **Progress & Logging** | Full support for MCP progress notifications and logging |
| 🏷️ **Namespace Support** | Prefix tool names and handle conflicts automatically |

---

## 🚀 Quick Start

### Installation

```bash
pip install lc2mcp
```

### 3 Lines to MCP

```python
from langchain_core.tools import tool
from fastmcp import FastMCP
from lc2mcp import register_tools

@tool
def get_weather(city: str) -> str:
    """Get current weather for a city."""
    return f"Sunny, 25°C in {city}"

mcp = FastMCP("weather-server")
register_tools(mcp, [get_weather])  # ← That's it!

if __name__ == "__main__":
    mcp.run()
```

Your tool is now available to Claude, Cursor, and any MCP client.

### Tool Parameter Descriptions

To include parameter descriptions in the MCP tool schema, you have two options:

**Option 1: Use `parse_docstring=True`** (Recommended for simplicity)

```python
@tool(parse_docstring=True)
def get_weather(city: str, unit: str = "celsius") -> str:
    """Get current weather for a city.

    Args:
        city: The name of the city to query
        unit: Temperature unit (celsius or fahrenheit)
    """
    return f"Sunny, 25°C in {city}"
```

**Option 2: Use `args_schema`** (Recommended for complex types)

```python
from pydantic import BaseModel, Field

class WeatherInput(BaseModel):
    city: str = Field(description="The name of the city to query")
    unit: str = Field(default="celsius", description="Temperature unit")

@tool(args_schema=WeatherInput)
def get_weather(city: str, unit: str = "celsius") -> str:
    """Get current weather for a city."""
    return f"Sunny, 25°C in {city}"
```

> **Note:** Without `parse_docstring=True` or `args_schema`, parameter descriptions from docstrings will not be extracted.

---

## 🔌 How It Works

```
┌─────────────────┐      ┌─────────────┐      ┌─────────────────┐
│  LangChain Tool │ ───▶ │   lc2mcp    │ ───▶ │  FastMCP Tool   │
│  (@tool, etc.)  │      │  (adapter)  │      │                 │
└─────────────────┘      └─────────────┘      └────────┬────────┘
                                                       │
                                                       ▼
                                              ┌─────────────────┐
                                              │  FastMCP Server │
                                              └────────┬────────┘
                                                       │
                                                       ▼
                                          ┌───────────────────────┐
                                          │      MCP Clients      │
                                          │ (Claude, Cursor, ...) │
                                          └───────────────────────┘
```

---

## 🔄 lc2mcp vs langchain-mcp-adapters

LangChain and MCP ecosystems can be connected in **both directions**:

| Direction | Tool | Description |
|-----------|------|-------------|
| **LangChain → MCP** | `lc2mcp` ✅ | Convert LangChain tools to MCP tools (this project) |
| **MCP → LangChain** | [`langchain-mcp-adapters`](https://github.com/langchain-ai/langchain-mcp-adapters) | Convert MCP tools to LangChain tools (official) |

**When to use `lc2mcp`:**
- You have existing LangChain tools and want to expose them via MCP
- You want to build an MCP server using LangChain's rich tool ecosystem
- You need to serve tools to Claude, Cursor, or other MCP clients

**When to use `langchain-mcp-adapters`:**
- You have MCP servers and want to use them in LangChain agents
- You want to call MCP tools from LangGraph workflows

**Using both together:**

```
┌─────────────────────────────────────────────────────────────────┐
│                        Your Application                         │
├─────────────────────────────────────────────────────────────────┤
│                                                                 │
│   LangChain Tools ──── lc2mcp ────▶ MCP Server ──▶ MCP Clients │
│         │                              │          (Claude, etc) │
│         │                              │                        │
│         ▼                              ▼                        │
│   LangChain Agent ◀── langchain-mcp-adapters ─── MCP Tools     │
│                                                                 │
└─────────────────────────────────────────────────────────────────┘
```

Both libraries are complementary and can be used together to build powerful AI applications that bridge the LangChain and MCP ecosystems.

---

## 📚 Examples

### Using Community Tools

Instantly expose DuckDuckGo search and Wikipedia to MCP clients:

```bash
pip install lc2mcp langchain-community duckduckgo-search wikipedia
```

```python
from fastmcp import FastMCP
from langchain_community.tools import DuckDuckGoSearchRun, WikipediaQueryRun
from langchain_community.utilities import WikipediaAPIWrapper
from lc2mcp import register_tools

mcp = FastMCP("knowledge-server")

register_tools(mcp, [
    DuckDuckGoSearchRun(),
    WikipediaQueryRun(api_wrapper=WikipediaAPIWrapper()),
])

if __name__ == "__main__":
    mcp.run()
```

### With Authentication Context

Inject user authentication and app context into your tools:

```python
from dataclasses import dataclass
from fastmcp import Context, FastMCP
from langchain_core.tools import tool
from langgraph.prebuilt import ToolRuntime
from lc2mcp import register_tools

@dataclass(frozen=True)
class UserContext:
    user_id: str
    tenant_id: str

@tool
def whoami(runtime: ToolRuntime[UserContext]) -> str:
    """Return the current user."""
    return f"Hello, user {runtime.context.user_id} from {runtime.context.tenant_id}"

def runtime_adapter(mcp_ctx: Context) -> ToolRuntime[UserContext]:
    return ToolRuntime(
        context=UserContext(
            user_id=mcp_ctx.get_state("user_id") or "anonymous",
            tenant_id=mcp_ctx.get_state("tenant_id") or "default",
        ),
        state={}, config={}, stream_writer=lambda x: None,
        tool_call_id=None, store=None,
    )

mcp = FastMCP("auth-server")
register_tools(mcp, [whoami], runtime_adapter=runtime_adapter)

if __name__ == "__main__":
    mcp.run()
```

### With Progress Reporting & Logging

Use MCP context for real-time progress updates and logging:

```python
from fastmcp import Context, FastMCP
from langchain_core.tools import tool
from lc2mcp import register_tools

@tool
async def process_data(data: str, mcp_ctx: Context) -> str:
    """Process data with progress reporting."""
    await mcp_ctx.info(f"Starting: {data}")
    await mcp_ctx.report_progress(0, 100, "Starting")
    
    # ... processing steps ...
    await mcp_ctx.report_progress(50, 100, "Processing")
    
    await mcp_ctx.info("Complete!")
    await mcp_ctx.report_progress(100, 100, "Done")
    return f"Processed: {data}"

mcp = FastMCP("processor")
register_tools(mcp, [process_data], inject_mcp_ctx=True)

if __name__ == "__main__":
    mcp.run()
```

### Namespace & Conflict Handling

Organize tools with prefixes and handle name collisions:

```python
from fastmcp import FastMCP
from lc2mcp import register_tools

mcp = FastMCP("multi-domain")

# Prefix all finance tools
register_tools(mcp, finance_tools, name_prefix="finance.")

# Auto-suffix on collision: tool → tool_2 → tool_3
register_tools(mcp, ops_tools, name_prefix="ops.", on_name_conflict="suffix")

if __name__ == "__main__":
    mcp.run()
```

---

## 📖 API Reference

### `register_tools()`

Convert and register LangChain tools as FastMCP tools on a server.

```python
register_tools(
    mcp: FastMCP,
    tools: list[BaseTool | Callable],
    *,
    name_prefix: str | None = None,           # e.g. "finance." → "finance.get_stock"
    on_name_conflict: str = "error",          # "error" | "overwrite" | "suffix"
    inject_mcp_ctx: bool = False,             # inject mcp_ctx: Context
    runtime_adapter: Callable | None = None,  # Context → ToolRuntime[...]
)
```

### `to_mcp_tool()`

Convert a single LangChain tool to FastMCP tool for manual registration.

```python
to_mcp_tool(
    tool: BaseTool | Callable,
    *,
    name: str | None = None,
    description: str | None = None,
    args_schema: Type[BaseModel] | None = None,
    inject_mcp_ctx: bool = False,
    runtime_adapter: Callable | None = None,
) -> Callable
```

---

## 🔧 Compatibility

| Component | Supported Versions |
|-----------|-------------------|
| Python | 3.10, 3.11, 3.12+ |
| LangChain | >= 1.0.0 |
| FastMCP | >= 2.0.0 |

### Tool Support

| Tool Type | Status |
|-----------|--------|
| `@tool` decorated functions | ✅ Full support |
| `@tool(parse_docstring=True)` | ✅ Full support (with parameter descriptions) |
| `@tool(args_schema=...)` | ✅ Full support (with parameter descriptions) |
| `StructuredTool` | ✅ Full support |
| `BaseTool` subclasses | ✅ Supported (requires `args_schema`) |

---

## 🤝 Contributing

Contributions are welcome! Please feel free to submit a Pull Request.

---

## 📄 License

MIT License - see [LICENSE](LICENSE) for details.

---

  Made with ❤️ for the LangChain and MCP communities

## Source & license

This open-source MCP server is cataloged on AgentStack and links to its original source — we do not rehost the code.

- **Author:** [xiaotonng](https://github.com/xiaotonng)
- **Source:** [xiaotonng/lc2mcp](https://github.com/xiaotonng/lc2mcp)
- **License:** MIT

Install and usage instructions live in the source repository linked above.

## Pricing

- **Free** — Free

## Security capabilities

Automated source analysis of v0.1.0 — what this tool can access:

- **Network access:** no
- **Filesystem access:** no
- **Shell / process execution:** no
- **Environment & secrets:** no
- **Dynamic code execution:** no

*"Yes" means the capability is present in the source — more access means more to trust, not that it is unsafe.*


## Versions

- **0.1.0** — security scan: passed — Imported from the upstream source.

## Links

- Listing page: https://agentstack.voostack.com/l/mcp-xiaotonng-lc2mcp
- Seller: https://agentstack.voostack.com/s/xiaotonng
- Browse the marketplace: https://agentstack.voostack.com/browse

---
Listed on AgentStack — the marketplace for AI agent skills and MCP servers. Every listing is security-reviewed. Creators keep 70%.