mirror of
https://github.com/PrefectHQ/fastmcp.git
synced 2026-08-12 08:39:09 +02:00
7ccaa8ac6dCo-authored-by: marvin-context-protocol[bot] <225465937+marvin-context-protocol[bot]@users.noreply.github.com>
189 lines
8.9 KiB
Text
189 lines
8.9 KiB
Text
---
|
|
title: caching
|
|
sidebarTitle: caching
|
|
---
|
|
|
|
# `fastmcp.server.middleware.caching`
|
|
|
|
|
|
A middleware for response caching.
|
|
|
|
## Classes
|
|
|
|
### `CachableReadResourceContents` <sup><a href="https://github.com/jlowin/fastmcp/blob/main/src/fastmcp/server/middleware/caching.py#L38" target="_blank"><Icon icon="github" style="width: 14px; height: 14px;" /></a></sup>
|
|
|
|
|
|
A wrapper for ReadResourceContents that can be cached.
|
|
|
|
|
|
**Methods:**
|
|
|
|
#### `get_size` <sup><a href="https://github.com/jlowin/fastmcp/blob/main/src/fastmcp/server/middleware/caching.py#L44" target="_blank"><Icon icon="github" style="width: 14px; height: 14px;" /></a></sup>
|
|
|
|
```python
|
|
get_size(self) -> int
|
|
```
|
|
|
|
#### `get_sizes` <sup><a href="https://github.com/jlowin/fastmcp/blob/main/src/fastmcp/server/middleware/caching.py#L48" target="_blank"><Icon icon="github" style="width: 14px; height: 14px;" /></a></sup>
|
|
|
|
```python
|
|
get_sizes(cls, values: Sequence[Self]) -> int
|
|
```
|
|
|
|
#### `wrap` <sup><a href="https://github.com/jlowin/fastmcp/blob/main/src/fastmcp/server/middleware/caching.py#L52" target="_blank"><Icon icon="github" style="width: 14px; height: 14px;" /></a></sup>
|
|
|
|
```python
|
|
wrap(cls, values: Sequence[ReadResourceContents]) -> list[Self]
|
|
```
|
|
|
|
#### `unwrap` <sup><a href="https://github.com/jlowin/fastmcp/blob/main/src/fastmcp/server/middleware/caching.py#L56" target="_blank"><Icon icon="github" style="width: 14px; height: 14px;" /></a></sup>
|
|
|
|
```python
|
|
unwrap(cls, values: Sequence[Self]) -> list[ReadResourceContents]
|
|
```
|
|
|
|
### `CachableToolResult` <sup><a href="https://github.com/jlowin/fastmcp/blob/main/src/fastmcp/server/middleware/caching.py#L63" target="_blank"><Icon icon="github" style="width: 14px; height: 14px;" /></a></sup>
|
|
|
|
**Methods:**
|
|
|
|
#### `wrap` <sup><a href="https://github.com/jlowin/fastmcp/blob/main/src/fastmcp/server/middleware/caching.py#L69" target="_blank"><Icon icon="github" style="width: 14px; height: 14px;" /></a></sup>
|
|
|
|
```python
|
|
wrap(cls, value: ToolResult) -> Self
|
|
```
|
|
|
|
#### `unwrap` <sup><a href="https://github.com/jlowin/fastmcp/blob/main/src/fastmcp/server/middleware/caching.py#L76" target="_blank"><Icon icon="github" style="width: 14px; height: 14px;" /></a></sup>
|
|
|
|
```python
|
|
unwrap(self) -> ToolResult
|
|
```
|
|
|
|
### `SharedMethodSettings` <sup><a href="https://github.com/jlowin/fastmcp/blob/main/src/fastmcp/server/middleware/caching.py#L84" target="_blank"><Icon icon="github" style="width: 14px; height: 14px;" /></a></sup>
|
|
|
|
|
|
Shared config for a cache method.
|
|
|
|
|
|
### `ListToolsSettings` <sup><a href="https://github.com/jlowin/fastmcp/blob/main/src/fastmcp/server/middleware/caching.py#L91" target="_blank"><Icon icon="github" style="width: 14px; height: 14px;" /></a></sup>
|
|
|
|
|
|
Configuration options for Tool-related caching.
|
|
|
|
|
|
### `ListResourcesSettings` <sup><a href="https://github.com/jlowin/fastmcp/blob/main/src/fastmcp/server/middleware/caching.py#L95" target="_blank"><Icon icon="github" style="width: 14px; height: 14px;" /></a></sup>
|
|
|
|
|
|
Configuration options for Resource-related caching.
|
|
|
|
|
|
### `ListPromptsSettings` <sup><a href="https://github.com/jlowin/fastmcp/blob/main/src/fastmcp/server/middleware/caching.py#L99" target="_blank"><Icon icon="github" style="width: 14px; height: 14px;" /></a></sup>
|
|
|
|
|
|
Configuration options for Prompt-related caching.
|
|
|
|
|
|
### `CallToolSettings` <sup><a href="https://github.com/jlowin/fastmcp/blob/main/src/fastmcp/server/middleware/caching.py#L103" target="_blank"><Icon icon="github" style="width: 14px; height: 14px;" /></a></sup>
|
|
|
|
|
|
Configuration options for Tool-related caching.
|
|
|
|
|
|
### `ReadResourceSettings` <sup><a href="https://github.com/jlowin/fastmcp/blob/main/src/fastmcp/server/middleware/caching.py#L110" target="_blank"><Icon icon="github" style="width: 14px; height: 14px;" /></a></sup>
|
|
|
|
|
|
Configuration options for Resource-related caching.
|
|
|
|
|
|
### `GetPromptSettings` <sup><a href="https://github.com/jlowin/fastmcp/blob/main/src/fastmcp/server/middleware/caching.py#L114" target="_blank"><Icon icon="github" style="width: 14px; height: 14px;" /></a></sup>
|
|
|
|
|
|
Configuration options for Prompt-related caching.
|
|
|
|
|
|
### `ResponseCachingStatistics` <sup><a href="https://github.com/jlowin/fastmcp/blob/main/src/fastmcp/server/middleware/caching.py#L118" target="_blank"><Icon icon="github" style="width: 14px; height: 14px;" /></a></sup>
|
|
|
|
### `ResponseCachingMiddleware` <sup><a href="https://github.com/jlowin/fastmcp/blob/main/src/fastmcp/server/middleware/caching.py#L127" target="_blank"><Icon icon="github" style="width: 14px; height: 14px;" /></a></sup>
|
|
|
|
|
|
The response caching middleware offers a simple way to cache responses to mcp methods. The Middleware
|
|
supports cache invalidation via notifications from the server. The Middleware implements TTL-based caching
|
|
but cache implementations may offer additional features like LRU eviction, size limits, and more.
|
|
|
|
When items are retrieved from the cache they will no longer be the original objects, but rather no-op objects
|
|
this means that response caching may not be compatible with other middleware that expects original subclasses.
|
|
|
|
Notes:
|
|
- Caches `tools/call`, `resources/read`, `prompts/get`, `tools/list`, `resources/list`, and `prompts/list` requests.
|
|
- Cache keys are derived from method name and arguments.
|
|
|
|
|
|
**Methods:**
|
|
|
|
#### `on_list_tools` <sup><a href="https://github.com/jlowin/fastmcp/blob/main/src/fastmcp/server/middleware/caching.py#L233" target="_blank"><Icon icon="github" style="width: 14px; height: 14px;" /></a></sup>
|
|
|
|
```python
|
|
on_list_tools(self, context: MiddlewareContext[mcp.types.ListToolsRequest], call_next: CallNext[mcp.types.ListToolsRequest, Sequence[Tool]]) -> Sequence[Tool]
|
|
```
|
|
|
|
List tools from the cache, if caching is enabled, and the result is in the cache. Otherwise,
|
|
otherwise call the next middleware and store the result in the cache if caching is enabled.
|
|
|
|
|
|
#### `on_list_resources` <sup><a href="https://github.com/jlowin/fastmcp/blob/main/src/fastmcp/server/middleware/caching.py#L273" target="_blank"><Icon icon="github" style="width: 14px; height: 14px;" /></a></sup>
|
|
|
|
```python
|
|
on_list_resources(self, context: MiddlewareContext[mcp.types.ListResourcesRequest], call_next: CallNext[mcp.types.ListResourcesRequest, Sequence[Resource]]) -> Sequence[Resource]
|
|
```
|
|
|
|
List resources from the cache, if caching is enabled, and the result is in the cache. Otherwise,
|
|
otherwise call the next middleware and store the result in the cache if caching is enabled.
|
|
|
|
|
|
#### `on_list_prompts` <sup><a href="https://github.com/jlowin/fastmcp/blob/main/src/fastmcp/server/middleware/caching.py#L313" target="_blank"><Icon icon="github" style="width: 14px; height: 14px;" /></a></sup>
|
|
|
|
```python
|
|
on_list_prompts(self, context: MiddlewareContext[mcp.types.ListPromptsRequest], call_next: CallNext[mcp.types.ListPromptsRequest, Sequence[Prompt]]) -> Sequence[Prompt]
|
|
```
|
|
|
|
List prompts from the cache, if caching is enabled, and the result is in the cache. Otherwise,
|
|
otherwise call the next middleware and store the result in the cache if caching is enabled.
|
|
|
|
|
|
#### `on_call_tool` <sup><a href="https://github.com/jlowin/fastmcp/blob/main/src/fastmcp/server/middleware/caching.py#L351" target="_blank"><Icon icon="github" style="width: 14px; height: 14px;" /></a></sup>
|
|
|
|
```python
|
|
on_call_tool(self, context: MiddlewareContext[mcp.types.CallToolRequestParams], call_next: CallNext[mcp.types.CallToolRequestParams, ToolResult]) -> ToolResult
|
|
```
|
|
|
|
Call a tool from the cache, if caching is enabled, and the result is in the cache. Otherwise,
|
|
otherwise call the next middleware and store the result in the cache if caching is enabled.
|
|
|
|
|
|
#### `on_read_resource` <sup><a href="https://github.com/jlowin/fastmcp/blob/main/src/fastmcp/server/middleware/caching.py#L384" target="_blank"><Icon icon="github" style="width: 14px; height: 14px;" /></a></sup>
|
|
|
|
```python
|
|
on_read_resource(self, context: MiddlewareContext[mcp.types.ReadResourceRequestParams], call_next: CallNext[mcp.types.ReadResourceRequestParams, Sequence[ReadResourceContents]]) -> Sequence[ReadResourceContents]
|
|
```
|
|
|
|
Read a resource from the cache, if caching is enabled, and the result is in the cache. Otherwise,
|
|
otherwise call the next middleware and store the result in the cache if caching is enabled.
|
|
|
|
|
|
#### `on_get_prompt` <sup><a href="https://github.com/jlowin/fastmcp/blob/main/src/fastmcp/server/middleware/caching.py#L414" target="_blank"><Icon icon="github" style="width: 14px; height: 14px;" /></a></sup>
|
|
|
|
```python
|
|
on_get_prompt(self, context: MiddlewareContext[mcp.types.GetPromptRequestParams], call_next: CallNext[mcp.types.GetPromptRequestParams, mcp.types.GetPromptResult]) -> mcp.types.GetPromptResult
|
|
```
|
|
|
|
Get a prompt from the cache, if caching is enabled, and the result is in the cache. Otherwise,
|
|
otherwise call the next middleware and store the result in the cache if caching is enabled.
|
|
|
|
|
|
#### `statistics` <sup><a href="https://github.com/jlowin/fastmcp/blob/main/src/fastmcp/server/middleware/caching.py#L454" target="_blank"><Icon icon="github" style="width: 14px; height: 14px;" /></a></sup>
|
|
|
|
```python
|
|
statistics(self) -> ResponseCachingStatistics
|
|
```
|
|
|
|
Get the statistics for the cache.
|
|
|