"FIRST" matching MCP servers:

Enables privacy-preserving document retrieval by exposing read-only search tools over MCP, allowing agents to query local vector and structured indexes without sending data to the cloud.

An evidence-first Model Context Protocol server for private business documents and structured datasets, preserving original files and source lineage.

Local-first MCP server for querying multi-repo engineering documentation artifacts from a SQLite corpus.

Local-first, single-file, knowledge-graph memory layer for AI agents.

Local-first, MCP-first cross-agent cognitive asset layer that enables agents to store, retrieve, govern, and migrate memory, roles, and verified skills as portable assets via MCP tools and SQLite.

Local-first Markdown vault retrieval for agents. Read-only MCP stdio server exposing search, get, status, and doctor over Obsidian-compatible Markdown with hybrid BM25/vector/wikilink/title retrieval and first-class CJK support.

ContextLattice is an HTTP-first, MCP-compatible memory/context/task orchestrator that persists writes and returns fused recall from specialized stores with local-first defaults. Primary URL: https://contextlattice.io/ Install: https://contextlattice.io/installation.html Troubleshooting: https://contextlattice.io/troubleshooting.html

Local-first memory for coding agents. Discovers the memory, instructions, and rules Claude Code, Codex, and Cursor already wrote on your machine, combines them into one canonical Markdown tree, and serves grounded, cited recall through tools like ask_memory and canonical_memory.

Lossless archive and search for AI agent sessions (Claude Code, Codex, opencode, pi and others), exposed to agents over MCP. Local-first, written in Rust.

Enables local-first, verbatim memory retrieval for AI agents, storing notes and text across sessions and retrieving original passages without generative rewriting.

Embedded memory and retrieval engine for AI agents, providing local-first memory with MCP support for multi-agent access control.

Cited Q&A and drift detection over your own markdown notes: answers cite exact passages, cited passages are hashed at citation time, and a scheduled verify flags when a source changed under a conclusion already drawn from it. Local-first, zero runtime dependencies (node:sqlite); tools: chamber_ask, chamber_verify, chamber_corpus.

Vulcanus turns a Git-versioned Markdown vault into structured project memory for coding agents. recall returns a project's capsule plus the read-next list, and warns when the capsule is older than the decisions beneath it. search ranks by layer, so the cheapest sufficient note surfaces first. Writes are scoped: update_capsule replaces one named section instead of rewriting the file, and `app

Embedded, local-first agent memory: facts extracted into a per-namespace SQLite file (vec0 + FTS5) with hybrid retrieval and point-in-time (time-travel) queries. ADD-only history over stdio — no server process, no cloud dependency.

Local-first context retrieval engine that serves precise documentation chunks to coding agents via MCP, ensuring high-confidence context for code generation.

A local MCP server that fetches official library documentation (llms.txt-first), caches it to disk, and serves relevant sections to coding agents offline with deterministic retrieval.

Enables local-first hybrid knowledge retrieval from authorized Markdown and plain-text files, combining full-text and vector search with reranking and traceable source references via a single search tool.

Local-first RAG MCP server that indexes local documents and provides hybrid search (semantic + keyword) with file ingestion, URL fetching, and a CLI, keeping data on-device.

A local-first personal RAG memory system that turns AI conversation history into a searchable, retrievable knowledge base via MCP, enabling LLMs to semantically search past conversations.

A local-first MCP server that exposes personal notes and files as unified semantic context for AI agents via vector search and file monitoring.