"Search for HITL (Human-in-the-Loop or other possible acronyms)" matching MCP servers:

Enables Codex and DeepSeek Harness to maintain a local, traceable record of current task intent, separating requirements, evidence, unknowns, and disagreements while preserving corrections without erasing history.

Provides hybrid search (BM25 + vector) and staleness reporting for local markdown notes, exposing search and indexing tools to AI assistants via MCP.

Persists Claude Code sessions to Notion as team memory, enabling queryable recall of decisions, work state, and project architecture.

Enables semantic search over markdown files to find related notes by meaning rather than keywords, and automatically detect duplicate content before creating new notes.

A live MCP server that connects AI assistants to a running Obsidian instance, enabling full app automation including reading notes, clicking UI elements, managing plugins, and executing JavaScript.

Enables local hybrid search over Obsidian and Markdown vaults via MCP, combining vector retrieval, full-text search, reranking, graph navigation, and safe CRUD while keeping data local.

Enables Claude to search and analyze Obsidian vault content using ripgrep with support for wiki links, backlinks, frontmatter properties, orphaned notes, and intelligent context detection showing which heading or property contains each match.

Enables local semantic and full-text search over Markdown notes through MCP, returning relevant passages ranked by meaning and exact terms without requiring a GPU or hosted APIs.

Self-hosted MCP server that provides embedding-powered semantic search with graph context over Obsidian vaults, supporting multiple vaults, local embeddings, and a web dashboard.

A zero-config personal knowledge management MCP server that enables Claude Desktop to automatically classify, search, and organize local Markdown notes using hybrid search and Graph RAG.

A robust MCP server that transforms OneNote notebooks into an AI-accessible knowledge base for Gemini Spark, enabling natural language queries to list, read, and search notes via Microsoft Graph API.

MCP server that indexes Obsidian notes and enables hybrid search (full-text, fuzzy, semantic) for AI assistants to find and read notes.

MCP server for Obsidian vaults, optimised for Cursor agents — safe note editing, lean tool surface, direct filesystem access.

Enables AI agents to search, create, and manage Notion pages and databases through the Model Context Protocol. It features file-based operations and response extraction to optimize token usage and context efficiency.

MCP server to interact with Obsidian via the Local REST API community plugin.

A TypeScript-based MCP server that enables AI assistants to create, search, list, and delete notes with tags. Serves as a starter template for building custom MCP servers with tools and resources.

Local-first MCP server that extracts structured knowledge from markdown notes into SQLite with full-text search, enabling AI coding tools to retrieve relevant context offline at zero cost.

Connects to Microsoft OneNote desktop via COM API, exposing 27 tools for hierarchy, page CRUD, search, rich content, export, health checks, and more. Enables natural-language control of OneNote without API keys or embedded AI providers.

Enables MCP clients to search and read recorded meeting data, including transcripts, notes, action items, and participants, from Walkie's local database.

Enables offline search of personal notes and FAQ collections through MCP tools.