"pre-commit" matching MCP servers:

MCP server exposing memory search, index, and stats tools for agents, with honesty guards to prevent re-litigation of settled decisions.

An ultra-rational A2A protocol for zero-token edge pre-filtering and FEP-driven deadlock prevention. Uses Cloudflare Vectorize (384d cosine similarity) with a 24h deposit model, restricting bargaining to a 4-rally limit before forcing HTTP 402 dimension jumps.

Semantic memory for AI agents — local-first MCP server with hybrid search, knowledge graph, contradiction detection, and plan-then-commit consolidation.

RAGX MCP Server enables retrieval-augmented generation with document ingestion, hybrid search, and agentic answering using Claude, exposing tools for querying, searching, and managing documents.

An MCP server that enables AI assistants to directly interact with Elasticsearch for searching, aggregating, and retrieving documents from indices, supporting full-text search, semantic search, and various query modes.

Automatically discovers vector indexes in a Neo4j database and exposes each as a semantic search tool with metadata pre-filtering, enabling natural language queries with dynamic filter support.

Enables AI assistants to search and retrieve information from Teleport documentation using a vector database. It provides a tool for semantic vector search over pre-populated embeddings of Teleport pages and examples to assist with technical queries.

An enhanced memory repository MCP service that builds and queries temporally-aware knowledge graphs from user interactions and data. Features asynchronous parallel processing, task management, broader AI model compatibility, and a comprehensive visual management interface.

Enables stateless similarity search over pre-computed vector corpora using NMI and cosine fusion with entropy-calibrated weighting. Provides tools for ranking, scoring, outlier detection, and alpha calibration for AI agents.