Merged
Conversation
This RFC proposes migrating MCP-Optimizer functionality from a standalone Python service to native vMCP tools, unifying the codebase and enabling full integration with ToolHive's authentication, authorization, and observability infrastructure. Add two new optimizer tools as vMCP-native MCP tools: - `optim.find_tool`: Semantic and keyword-based tool discovery using hybrid search (embeddings + BM25) - `optim.call_tool`: Dynamic tool invocation on any backend server These tools operate on vMCP's internal state and provide meta-capabilities over aggregated backend tools. - **Storage**: SQLite as the default embedding storage backend with a flexible interface for future providers - **Embeddings**: HuggingFace Text Embeddings Inference (TEI) as the initial embedding provider, with interface supporting future vLLM/OpenAI - **Authentication**: Full reuse of vMCP's two-boundary auth model with no modifications required - **Scope**: One-to-one relationship between optimizer and vMCP instance (no cross-vMCP search)
jerm-dro
approved these changes
Jan 13, 2026
JAORMX
reviewed
Jan 14, 2026
JAORMX
reviewed
Jan 14, 2026
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
5 participants
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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 RFC proposes migrating MCP-Optimizer functionality from a standalone Python service to native vMCP tools, unifying the codebase and enabling full integration with ToolHive's authentication, authorization, and observability infrastructure.
Add two new optimizer tools as vMCP-native MCP tools:
optim.find_tool: Semantic and keyword-based tool discovery using hybrid search (embeddings + BM25)optim.call_tool: Dynamic tool invocation on any backend serverThese tools operate on vMCP's internal state and provide meta-capabilities over aggregated backend tools.