feat(mcp): framework-native permission scoping with #[mcp(...)] + ToolPolicy + x-mcp OpenAPI#198
Merged
Merged
Conversation
…olPolicy + x-mcp extension - Add McpOperation struct in rustapi-openapi (serialized as x-mcp) - Support #[rustapi_rs::mcp(skip)], #[mcp(write, require="confirm")], #[mcp(readonly)] in macros - Add .mcp() to Route builder and Operation - ToolPolicy::ReadOnly as safe default (All for writes) - Method-based read/write classification - Permission + requiresConfirmation in tools/list response - Rich metadata from x-mcp OpenAPI extension - Updated discovery, e2e tests, docs, examples, cookbook Addresses agent blast radius. More examples in cookbook.
github-actions Bot
pushed a commit
that referenced
this pull request
Jun 19, 2026
…permission-scoping feat(mcp): framework-native permission scoping with #[mcp(...)] + ToolPolicy + x-mcp OpenAPI 6c98606
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
Implements proper framework-level permission scoping for MCP tools as requested in recent feedback.
Motivation
Auto-exposing every endpoint (including destructive ones) has real blast radius for AI agents. Permission scoping must be native to the framework, not bolted on later.
Changes
Testing
Feedback welcome on the API design (e.g. more granular Custom policy later).