"Less" matching MCP servers:

MCP Server for persistent code indexing. Gives AI assistants (Claude, Gemini, Copilot, Cursor) instant access to your codebase. 50x less context than grep.

Portable, auditable, local-first MCP memory for MCP-compatible AI agents and coding workflows. It keeps durable project memory outside the model runtime, compresses continuity into smaller working packs, and carries forward operational state so agents can resume with less repetition.

Enables MCP clients such as Claude Code, Codex, and Cursor to store, query, update, and share schema-less JSON records in a self-hosted Postgres-backed database across sessions.

Enables Claude Code to search and retrieve information from its past session transcripts, including tool calls, errors, and project-specific history, via an SQLite FTS5 full-text search index.

Inventory of your service accounts, kept current by your coding agents. Metadata only, no secrets.

Central MCP server for storing and querying lessons learned and project-specific implementation details, compatible with MCP-capable AI clients like Cursor, Claude Code, and Google Antigravity.

An MCP server that stores and searches lessons learned to prevent repeating mistakes, with full-text search and tag-based navigation.

Enables AI assistants to save, search, and manage bookmarks with semantic search, automatic metadata extraction, and optional LLM-powered enrichment, all running locally.

An MCP server that gives AI agents durable, temporal memory over local markdown vaults, with tools for searching, asserting facts, querying point-in-time state, and reinforcing useful knowledge.

A Model Context Protocol (MCP) server that provides persistent memory and context management for AI systems through a structured 5-phase optimization workflow.