* feat: add output_schema field to Tool struct
- Add optional output_schema field to Tool struct for defining tool
output structure
- Update Tool::new() to initialize output_schema as None
* feat: add structured_content field to CallToolResult
- Add optional structured_content field for JSON object results
- Make content field optional to support either structured or
unstructured results
- Add CallToolResult::structured() and structured_error() constructor
methods
* feat: implement validation for mutually exclusive content/structuredContent
- Add validate() method to ensure content and structured_content are
mutually exclusive
- Implement custom Deserialize to enforce validation during
deserialization
- Update documentation to clarify the mutual exclusivity requirement
* feat: add output_schema support to #[tool] macro
- Add output_schema field to ToolAttribute and ResolvedToolAttribute
structs
- Implement automatic output schema generation from return types
- Support explicit output_schema attribute for manual specification
- Generate schemas for Result<T, E> where T is not CallToolResult
- Update tool generation to include output_schema in Tool struct
* feat: implement IntoCallToolResult for structured content
- Add Structured<T> wrapper type for explicit structured content
- Implement IntoCallToolResult for Structured<T> with JSON serialization
- Add support for Result<Structured<T>, E> conversions
- Enable tools to return structured content through the trait system
* fix: update simple-chat-client example for optional content field
- Handle Option<Vec<Content>> in CallToolResult.content
- Add proper unwrapping for the optional content field
- Fix compilation error in chat.rs
* fix: update examples and tests for optional content field
- Add output_schema field to Tool initialization in sampling_stdio
example
- Update test_tool_macros tests to handle Option<Vec<Content>>
- Use as_ref() before calling first() on optional content field
* feat: implement basic schema validation in conversion logic
- Add validate_against_schema function for basic type validation
- Add note that full JSON Schema validation requires dedicated library
- Document that actual validation should happen in tool handler
* feat: add structured output support for tools
- Add output_schema field to Tool struct for defining output JSON schemas
- Add structured_content field to CallToolResult (mutually exclusive with content)
- Implement Structured<T> wrapper for type-safe structured outputs
- Update #[tool] macro to automatically generate output schemas from return types
- Add validation of structured outputs against their schemas
- Update all examples and tests for breaking change (CallToolResult.content now Option)
- Add comprehensive documentation and rustdoc
- Add structured_output example demonstrating the feature
BREAKING CHANGE: CallToolResult.content is now Option<Vec<Content>> instead of Vec<Content>
Closes#312
* fix: correct structured output doctest to use Parameters wrapper
The #[tool] macro requires Parameters<T> wrapper for tool inputs.
This fixes the pre-existing broken doctest in the structured output
documentation example.
* feat: replace Structured<T> with Json<T> for structured output
- Remove Structured<T> type definition and implementations
- Reuse existing Json<T> wrapper for structured content
- Update IntoCallToolResult implementations to use Json<T>
- Add JsonSchema implementation for Json<T> delegating to T
- Update all examples and tests to use Json<T> instead of Structured<T>
- Update documentation and exports
BREAKING CHANGE: Structured<T> has been replaced with Json<T>. Users must update their code to use Json<T> for structured tool outputs.
* feat: add output_schema() method to IntoCallToolResult trait
- Add output_schema() method with default None implementation
- Implement output_schema() for Json<T> to return cached schema
- Implement output_schema() for Result<Json<T>, E> delegating to Json<T>
- Enable trait-based schema generation for structured outputs
* feat: update macro to detect Json<T> wrapper for output schemas
- Add extract_json_inner_type() helper to detect Json<T> types
- Update schema generation to only occur for Json<T> wrapped types
- Remove generic Result<T, E> detection in favor of specific Json<T> detection
- Add comprehensive tests to verify schema generation behavior
* feat: add builder methods to Tool struct for setting schemas
- Add with_output_schema<T>() method to set output schema from type
- Add with_input_schema<T>() method to set input schema from type
- Both methods use cached_schema_for_type internally
- Add comprehensive tests for builder methods
* fix: address clippy warnings
- Add Default implementation for StructuredOutputServer
- Fix collapsible else-if in simple-chat-client
- No functional changes
* style: apply cargo fmt
Apply automatic formatting changes to:
- examples/simple-chat-client/src/chat.rs - fix line wrapping
- crates/rmcp-macros/src/tool.rs - format method chaining
- examples/servers/src/structured_output.rs - reorder imports and format function signatures
* chore: fix formatting
* chore: fix rustdoc redundant link warning
* refactor: validate_against_schema
* feat: enforce structured_content usage when output_schema is defined
This commit implements strict validation to ensure tools with output_schema
consistently use structured_content for both success and error responses.
Changes:
- Enhanced ToolRouter::call() validation to require structured_content when output_schema is present
- Added validation that tools with output_schema cannot use regular content field
- Added comprehensive tests covering the new strict validation behavior
- Created example demonstrating proper structured output usage
- Updated TODO.md to track validation improvements
This ensures consistent response format and better type safety for MCP clients.
* chore: remove TODO.md
* refactor: simplify output schema extraction logic in tool macro
- Extract complex nested logic into dedicated helper function
- Replace deeply nested if-else chains with functional approach
- Use early returns and ? operator for cleaner code flow
- Reduce 46 lines to 7 lines in main logic while improving readability
* chore: run cargo fmt
* fix: enforce structured_content usage when output_schema is defined
Structured content is returned as a JSON object in the structuredContent
field of a result.For backwards compatibility, a tool that returns
structured content SHOULD also return the serialized JSON in a
TextContent block.
https://modelcontextprotocol.io/specification/2025-06-18/server/tools#structured-content
Tools may also provide an output schema for validation of structured
results. If an output schema is provided:
- Servers MUST provide structured results that conform to this schema.
- Clients SHOULD validate structured results against this schema.
https://modelcontextprotocol.io/specification/2025-06-18/server/tools#output-schema
* chore: cargo fmt
The old form violates the spec, and all other `Option<bool>` fields also
behave this way. Concretely https://github.com/upstash/context7/ fails
without this change.
- Fix ResourceContents enum to properly serialize with camelCase field names
- Add comprehensive tests to verify JSON serialization compliance
- Ensure all resource-related structs use mimeType as per MCP spec
- Add tests for RawResource, ResourceContents, RawImageContent, RawAudioContent
- Add test for prompt message image content serialization
- Update message schema files to reflect mimeType changes
- Fix import ordering to match project formatting standards
This change ensures the Rust SDK is fully compliant with the MCP specification
which requires mimeType (camelCase) for all resource content types.
* refactor: refactor tool macros and router implementation
- Updated the `#[tool(tool_box)]` macro to `#[tool_router]` across various modules for consistency.
- Enhanced the `Calculator`, `Counter`, and `GenericService` structs to utilize `ToolRouter` for handling tool calls.
- Introduced `Parameters` struct for better parameter handling in tool functions.
- Added new methods for listing tools and calling tools in server handlers.
- Improved test cases to reflect changes in tool routing and parameter handling.
- Updated documentation and examples to align with the new router structure.
* fix: fix fmt and build error
* fix: fix test failure
* docs: documents for macros, fix ci
* fix: fix ci
* fix: fix wrongly replaced documents
* fix: remove useless file
* fix: change the parameter format for tool_router
* fix: update extract_doc_line to handle existing documentation and clean up unused code in server handler
* doc: update document for macro and examples
* doc: update readme and add contribute guide
* fix: fix type
* fix bug,
1 remove erroneous definitions_path setting,"#/components/schemas/" is used for openapi3
2 show meta_schema
* Update crates/rmcp/src/handler/server/tool.rs
Remove the commented-out settings.inline_subschemas line to avoid confusion and clean up dead code.
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
---------
Co-authored-by: wenhaozhao <wenhaozhao@sohu-inc.com>
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
* feat: allow failable service creation in streamable HTTP tower service
In our setup we need to lookup some info that may fail before we serve
the request.
* Fix examples build
* allow using a TokioCommandWrap for TokioChildProcess::new closes#243
TokioCommandWrap implements From<tokio::process::Command> so this is not a breaking change, but also downstream users have more control over flags such as KillOnDrop and CreationFlags
see https://docs.rs/process-wrap/latest/process_wrap/#killondrop-and-creationflags
- Introduced `is_standard_notification` function to check for standard MCP notifications.
- Added `try_parse_with_compatibility` function to handle parsing messages with compatibility for non-standard notifications.
- Updated the decoder implementation to utilize the new compatibility handling.
- Added unit tests for standard notification checks and compatibility function to ensure correct behavior.
* feat: provide more context information
1. provide context for notification
2. allow extract more info from tool call
3. inject http request part for streamable http server
* docs: add document for getting peer from context
* feat: better http server support
1. allow user get extensions in tool call.
2. allow user serve sse service without initialization.
* fix: fix document test
* feat(client): cleanup of zombie processes in child process client
Using process wrap library, Process Group for Unix and Job Object for Windows
* fix: install extra dep based on feature, update examples take owned command
Install process-wrap if transport-child-process feature is enabled. Update examples to take ownership
of the command instead of mutable reference
* fix: update other examples, comments and readme to take ownership of command
Updated more examples, comments and readme to take command instead of mutable ref.
Also small fix in cargo toml of example to use local path.
* refactor: add configure command ext
Added configure command ext to tokio process command so that
you can use .configure() to use inline commands for mcp stdio client.
Added warning if start kill process fails
* refactor: a transport trait and streamable http client
* test: test with js streamable http server
* refactor: separate sse stream connection
* fix(test): streamable http client test with js
* fix(test): wait longer time for js server startup
* feat(model): add json schema generation support for all model types
This commit adds JSON Schema support for all model types by implementing
`schemars::JsonSchema` trait. The feature is gated behind the new
`schemars` feature flag. This enables automatic schema generation for
API documentation and validation purposes. Added tests to verify schema
generation for client and server JSON-RPC messages.
* fix(model): add manual json schema implementation for `NumberOrString`
This commit adds a manual implementation of `JsonSchema` trait for the
`NumberOrString` enum to properly represent its union type nature in
JSON Schema. The schema now correctly specifies that the type can be
either a number or a string using the `oneOf` validation keyword.
* fix(model): skip extensions field in json schema generation
The `Extensions` type was incorrectly included in JSON schema
generation, which could lead to confusing API documentation. This commit
adds `#[schemars(skip)]` attribute to all `extensions` fields in request
and notification structs, and removes the manual `JsonSchema`
implementation for the `Extensions` type since it's an internal
implementation detail that shouldn't be exposed in the schema.
