### Setup Development Environment

Source: https://github.com/bagowix/dishka-fastmcp/blob/main/CONTRIBUTING.md

Clone the repository, navigate to the directory, and use uv to sync dependencies and install git hooks.

```bash
git clone https://github.com/bagowix/dishka-fastmcp
cd dishka-fastmcp
uv sync            # creates the venv and installs dev dependencies
uv run prek install  # one-time: installs the git hooks
```

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

### Basic Dishka-FastMCP Setup and Tool Injection

Source: https://github.com/bagowix/dishka-fastmcp/blob/main/README.md

This snippet shows the fundamental setup for integrating Dishka with FastMCP. It defines a service (Catalog), a Dishka provider, creates a container, and initializes FastMCP with Dishka's lifespan management. A tool (`get_price`) is defined with dependency injection using `FromDishka`, demonstrating how services are automatically resolved per request.

```python
from dishka import Provider, Scope, make_async_container, provide
from fastmcp import FastMCP

from dishka_fastmcp import FromDishka, dishka_lifespan, inject, setup_dishka


class Catalog:
    _prices: dict[str, int] = {'book': 12, 'pen': 2}

    def price(self, item: str) -> int:
        return self._prices.get(item, 0)


class AppProvider(Provider):
    catalog = provide(Catalog, scope=Scope.REQUEST)


container = make_async_container(AppProvider())
mcp = FastMCP('shop', lifespan=dishka_lifespan(container))
setup_dishka(container, mcp)


@mcp.tool
@inject
async def get_price(item: str, catalog: FromDishka[Catalog]) -> int:
    return catalog.price(item)


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

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

### Install dishka-fastmcp

Source: https://github.com/bagowix/dishka-fastmcp/blob/main/README.md

Install the dishka-fastmcp package using uv or pip. Ensure you have the required versions of Python, dishka, and fastmcp.

```bash
uv add dishka-fastmcp        # or: pip install dishka-fastmcp
```

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

### Basic dishka-fastmcp Setup and Tool Usage

Source: https://github.com/bagowix/dishka-fastmcp/blob/main/docs/llms.txt

Demonstrates how to set up dishka with FastMCP and define an injected tool. Ensure `@inject` is placed below the FastMCP decorator and `setup_dishka` is called before server execution.

```python
from dishka import Provider, Scope, make_async_container, provide
from fastmcp import FastMCP

from dishka_fastmcp import FromDishka, dishka_lifespan, inject, setup_dishka


class Catalog:
    _prices = {'book': 12, 'pen': 2}

    def price(self, item: str) -> int:
        return self._prices.get(item, 0)


class AppProvider(Provider):
    catalog = provide(Catalog, scope=Scope.REQUEST)


container = make_async_container(AppProvider())
mcp = FastMCP('shop', lifespan=dishka_lifespan(container))
setup_dishka(container, mcp)


@mcp.tool
@inject
async def get_price(item: str, catalog: FromDishka[Catalog]) -> int:
    return catalog.price(item)  # client sees only `item` in the schema
```

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

### Setting up Dishka Container for Sync Tools

Source: https://github.com/bagowix/dishka-fastmcp/blob/main/README.md

Illustrates the setup of a sync Dishka container using `make_container` and `setup_dishka` for use with sync FastMCP tools. Ensures correct propagation of the request container into worker threads.

```python
from dishka import make_container

container = make_container(AppProvider())
setup_dishka(container, mcp)
```

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

### Setting up Async Dishka Container with FastMCPProvider

Source: https://github.com/bagowix/dishka-fastmcp/blob/main/README.md

Shows how to create an async Dishka container that includes `FastMCPProvider` to expose FastMCP objects like the request context to dependencies. Use `make_async_container` for async handlers.

```python
from fastmcp.server.context import Context

from dishka_fastmcp import FastMCPProvider

container = make_async_container(AppProvider(), FastMCPProvider())


@mcp.tool
@inject
async def notify(message: str, ctx: FromDishka[Context]) -> None:
    await ctx.info(message)
```

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

### Run Project Checks

Source: https://github.com/bagowix/dishka-fastmcp/blob/main/CONTRIBUTING.md

Execute formatting, linting, type checking, and tests locally using uv to ensure code quality and correctness.

```bash
uv run ruff format --check    # formatting
uv run ruff check             # linting
uv run mypy                   # type checking (strict)
uv run pyright                # type checking (strict, second checker)
uv run pytest --cov           # tests with coverage (threshold: 100%)
```

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

### Injecting Dependencies into FastMCP Prompts

Source: https://github.com/bagowix/dishka-fastmcp/blob/main/README.md

Shows how to use the `@inject` decorator with FastMCP prompts for dependency resolution. Requires `@mcp.prompt` decorator.

```python
@mcp.prompt
@inject
async def summarize(text: str, summarizer: FromDishka[Summarizer]) -> str:
    return await summarizer.run(text)
```

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

### Injecting Dependencies into FastMCP Sync Tools

Source: https://github.com/bagowix/dishka-fastmcp/blob/main/README.md

Demonstrates injecting dependencies into a synchronous FastMCP tool using the `@inject` decorator. The tool runs in a worker thread by default.

```python
@mcp.tool
@inject
def compute(x: int, service: FromDishka[Calculator]) -> int:
    return service.square(x)
```

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

### Injecting Dependencies into FastMCP Resources

Source: https://github.com/bagowix/dishka-fastmcp/blob/main/README.md

Demonstrates how to use the `@inject` decorator with FastMCP resources to resolve dependencies per operation. Requires `@mcp.resource` decorator.

```python
@mcp.resource('users://{user_id}')
@inject
async def user(user_id: str, repo: FromDishka[UserRepo]) -> dict:
    return await repo.get(user_id)
```

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

### Run a Single Test

Source: https://github.com/bagowix/dishka-fastmcp/blob/main/CONTRIBUTING.md

Execute a specific test case using uv and pytest to isolate and verify a particular functionality.

```bash
uv run pytest tests/test_tools.py::test_async_tool_injects_and_hides_deps_from_schema
```

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