Add MCP prompt template support#22
Merged
Merged
Conversation
Proxies prompt metadata from downstream MCP servers and exposes it to consuming LLMs via get_service_details (now returns tools + prompts together) and a new get_prompt tool for rendering prompt templates with arguments. Prompt data is cached with the same TTL as tools and invalidated on registry changes. Also feeds prompt metadata into the AI summary generator so summaries reflect a server's full capability set. Updated the summary system prompt to frame output for AI agent consumption rather than humans. Co-Authored-By: Claude Sonnet 4.6 (1M context) <noreply@anthropic.com>
Allows a consumer to immediately reload metadata from a downstream server after it has been updated, without waiting for the cache TTL. Co-Authored-By: Claude Sonnet 4.6 (1M context) <noreply@anthropic.com>
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
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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
get_service_detailsnow returns both tools and prompt templates in a single call — no extra round trip needed for consuming LLMs to see a server's full capability setget_prompttool renders a prompt template from a downstream server with optional argumentsTest plan
get_service_detailsreturns bothtoolsandpromptsarraysget_service_detailsstill succeeds and returns an emptypromptsarrayget_promptwith valid server/prompt name and arguments; verify rendered messages are returnedregenerate_summary(MCP tool and REST endpoint) also picks up prompt data🤖 Generated with Claude Code