fastmcp.server.middleware.caching

A middleware for response caching.

Classes

CachableResourceContent ^{<a href="https://github.com/PrefectHQ/fastmcp/blob/main/src/fastmcp/server/middleware/caching.py#L39" target="_blank"><Icon icon="github" style="width: 14px; height: 14px;" /></a>}

A wrapper for ResourceContent that can be cached.

CachableResourceResult ^{<a href="https://github.com/PrefectHQ/fastmcp/blob/main/src/fastmcp/server/middleware/caching.py#L47" target="_blank"><Icon icon="github" style="width: 14px; height: 14px;" /></a>}

A wrapper for ResourceResult that can be cached.

Methods:

get_size ^{<a href="https://github.com/PrefectHQ/fastmcp/blob/main/src/fastmcp/server/middleware/caching.py#L53" target="_blank"><Icon icon="github" style="width: 14px; height: 14px;" /></a>}

get_size(self) -> int

wrap ^{<a href="https://github.com/PrefectHQ/fastmcp/blob/main/src/fastmcp/server/middleware/caching.py#L57" target="_blank"><Icon icon="github" style="width: 14px; height: 14px;" /></a>}

wrap(cls, value: ResourceResult) -> Self

unwrap ^{<a href="https://github.com/PrefectHQ/fastmcp/blob/main/src/fastmcp/server/middleware/caching.py#L68" target="_blank"><Icon icon="github" style="width: 14px; height: 14px;" /></a>}

unwrap(self) -> ResourceResult

CachableToolResult ^{<a href="https://github.com/PrefectHQ/fastmcp/blob/main/src/fastmcp/server/middleware/caching.py#L80" target="_blank"><Icon icon="github" style="width: 14px; height: 14px;" /></a>}

Methods:

wrap ^{<a href="https://github.com/PrefectHQ/fastmcp/blob/main/src/fastmcp/server/middleware/caching.py#L86" target="_blank"><Icon icon="github" style="width: 14px; height: 14px;" /></a>}

wrap(cls, value: ToolResult) -> Self

unwrap ^{<a href="https://github.com/PrefectHQ/fastmcp/blob/main/src/fastmcp/server/middleware/caching.py#L93" target="_blank"><Icon icon="github" style="width: 14px; height: 14px;" /></a>}

unwrap(self) -> ToolResult

CachableMessage ^{<a href="https://github.com/PrefectHQ/fastmcp/blob/main/src/fastmcp/server/middleware/caching.py#L101" target="_blank"><Icon icon="github" style="width: 14px; height: 14px;" /></a>}

A wrapper for Message that can be cached.

CachablePromptResult ^{<a href="https://github.com/PrefectHQ/fastmcp/blob/main/src/fastmcp/server/middleware/caching.py#L113" target="_blank"><Icon icon="github" style="width: 14px; height: 14px;" /></a>}

A wrapper for PromptResult that can be cached.

Methods:

get_size ^{<a href="https://github.com/PrefectHQ/fastmcp/blob/main/src/fastmcp/server/middleware/caching.py#L120" target="_blank"><Icon icon="github" style="width: 14px; height: 14px;" /></a>}

get_size(self) -> int

wrap ^{<a href="https://github.com/PrefectHQ/fastmcp/blob/main/src/fastmcp/server/middleware/caching.py#L124" target="_blank"><Icon icon="github" style="width: 14px; height: 14px;" /></a>}

wrap(cls, value: PromptResult) -> Self

unwrap ^{<a href="https://github.com/PrefectHQ/fastmcp/blob/main/src/fastmcp/server/middleware/caching.py#L133" target="_blank"><Icon icon="github" style="width: 14px; height: 14px;" /></a>}

unwrap(self) -> PromptResult

SharedMethodSettings ^{<a href="https://github.com/PrefectHQ/fastmcp/blob/main/src/fastmcp/server/middleware/caching.py#L144" target="_blank"><Icon icon="github" style="width: 14px; height: 14px;" /></a>}

Shared config for a cache method.

ListToolsSettings ^{<a href="https://github.com/PrefectHQ/fastmcp/blob/main/src/fastmcp/server/middleware/caching.py#L151" target="_blank"><Icon icon="github" style="width: 14px; height: 14px;" /></a>}

Configuration options for Tool-related caching.

ListResourcesSettings ^{<a href="https://github.com/PrefectHQ/fastmcp/blob/main/src/fastmcp/server/middleware/caching.py#L155" target="_blank"><Icon icon="github" style="width: 14px; height: 14px;" /></a>}

Configuration options for Resource-related caching.

ListPromptsSettings ^{<a href="https://github.com/PrefectHQ/fastmcp/blob/main/src/fastmcp/server/middleware/caching.py#L159" target="_blank"><Icon icon="github" style="width: 14px; height: 14px;" /></a>}

Configuration options for Prompt-related caching.

CallToolSettings ^{<a href="https://github.com/PrefectHQ/fastmcp/blob/main/src/fastmcp/server/middleware/caching.py#L163" target="_blank"><Icon icon="github" style="width: 14px; height: 14px;" /></a>}

Configuration options for Tool-related caching.

ReadResourceSettings ^{<a href="https://github.com/PrefectHQ/fastmcp/blob/main/src/fastmcp/server/middleware/caching.py#L170" target="_blank"><Icon icon="github" style="width: 14px; height: 14px;" /></a>}

Configuration options for Resource-related caching.

GetPromptSettings ^{<a href="https://github.com/PrefectHQ/fastmcp/blob/main/src/fastmcp/server/middleware/caching.py#L174" target="_blank"><Icon icon="github" style="width: 14px; height: 14px;" /></a>}

Configuration options for Prompt-related caching.

ResponseCachingStatistics ^{<a href="https://github.com/PrefectHQ/fastmcp/blob/main/src/fastmcp/server/middleware/caching.py#L178" target="_blank"><Icon icon="github" style="width: 14px; height: 14px;" /></a>}

ResponseCachingMiddleware ^{<a href="https://github.com/PrefectHQ/fastmcp/blob/main/src/fastmcp/server/middleware/caching.py#L187" target="_blank"><Icon icon="github" style="width: 14px; height: 14px;" /></a>}

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 ^{<a href="https://github.com/PrefectHQ/fastmcp/blob/main/src/fastmcp/server/middleware/caching.py#L291" target="_blank"><Icon icon="github" style="width: 14px; height: 14px;" /></a>}

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 ^{<a href="https://github.com/PrefectHQ/fastmcp/blob/main/src/fastmcp/server/middleware/caching.py#L330" target="_blank"><Icon icon="github" style="width: 14px; height: 14px;" /></a>}

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 ^{<a href="https://github.com/PrefectHQ/fastmcp/blob/main/src/fastmcp/server/middleware/caching.py#L369" target="_blank"><Icon icon="github" style="width: 14px; height: 14px;" /></a>}

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 ^{<a href="https://github.com/PrefectHQ/fastmcp/blob/main/src/fastmcp/server/middleware/caching.py#L406" target="_blank"><Icon icon="github" style="width: 14px; height: 14px;" /></a>}

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 ^{<a href="https://github.com/PrefectHQ/fastmcp/blob/main/src/fastmcp/server/middleware/caching.py#L439" target="_blank"><Icon icon="github" style="width: 14px; height: 14px;" /></a>}

on_read_resource(self, context: MiddlewareContext[mcp.types.ReadResourceRequestParams], call_next: CallNext[mcp.types.ReadResourceRequestParams, ResourceResult]) -> ResourceResult

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 ^{<a href="https://github.com/PrefectHQ/fastmcp/blob/main/src/fastmcp/server/middleware/caching.py#L467" target="_blank"><Icon icon="github" style="width: 14px; height: 14px;" /></a>}

on_get_prompt(self, context: MiddlewareContext[mcp.types.GetPromptRequestParams], call_next: CallNext[mcp.types.GetPromptRequestParams, PromptResult]) -> PromptResult

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 ^{<a href="https://github.com/PrefectHQ/fastmcp/blob/main/src/fastmcp/server/middleware/caching.py#L506" target="_blank"><Icon icon="github" style="width: 14px; height: 14px;" /></a>}

statistics(self) -> ResponseCachingStatistics

Get the statistics for the cache.