feat: #2807 support callable approval policies for local MCP servers#2818
Merged
Conversation
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
This pull request adds first-class callable
require_approvalsupport for local MCP servers in the Python SDK. Local MCP integrations can now decide approval dynamically from(run_context, agent, tool)instead of being limited to static"always"/"never"policies, per-tool maps, or grouped tool-name lists.The implementation extends the public MCP typing surface, preserves existing static approval behavior, and keeps the legacy fail-closed fallback for older
MCPUtil.to_function_tool(...)call sites that do not provide an agent. It also exports the new callable type fromagents.mcp, adds bridge-level and end-to-end tests for synchronous and asynchronous policies, and updates the MCP documentation with a concrete runtime-state example.One behavior detail worth calling out is that callable approval policies are evaluated again when a paused run resumes after approval. That behavior already matches the runtime bridge and is now covered by tests and an explicit runtime probe.
Resolves #2807