"Developing agents with expertise in the latest documentation" matching MCP servers:

Injects structured professional domain expertise into AI agents, providing access to decision frameworks, workflows, terminology, and regulatory context across 24 professional domains.

A template for building MCP servers that codify domain expertise into AI-accessible knowledge bases, deployable on Cloudflare Workers for AI assistants like Claude to query.

Enables AI harnesses to maintain a persistent memory layer backed by a local SQLite file, providing MCP tools to add, search, deprecate, and synchronize facts without deleting history.

Persistent memory and pattern learning for AI coding assistants via MCP.

Enables AI assistants to query and retrieve a structured professional profile, including expertise areas, CV, projects, active research, and target AI queries, through dedicated MCP tools and resources.

Evidence-governed coding agent memory and knowledge lifecycle MCP server for DeepSeek Harness (DSH), OpenAI Codex, and Google Antigravity. Provides local SQLite FTS5 + semantic hybrid retrieval, automatic session/compaction checkpointing, counter-example demotion, and a hard 1,200-char context budget guardrail with zero third-party Python dependencies.

A local markdown memory and cross-agent context engine for AI coding assistants. It provides an MCP server with tools to search, add, retrieve, and distill persistent memory across tools like Claude Code, Cursor, and Zed.

An MCP server that manages your conversation context automatically, pruning dead branches and keeping an audit trail of every cut.

Centrally manages Claude agent definitions, configurations, and custom commands across multiple devices using a SQLite database, eliminating file synchronization conflicts and enabling live updates across all connected Claude sessions.

Enables users to access, search, and get recommendations from AWS documentation through natural language queries. Supports both global AWS documentation and AWS China documentation with tools to fetch pages, search content, and discover related resources.

A Model Context Protocol implementation that enables AI assistants to interact with markdown documentation files, providing capabilities for document management, metadata handling, search, and documentation health analysis.

Enables agents to optimize context-window attention by reordering retrieved documents so critical evidence lands at prompt boundaries, mitigating lost-in-the-middle degradation. It combines BM25 lexical scoring, dense vector similarity, reciprocal rank fusion, knowledge-graph expansion, and recency-decay memory caching, exposed as a zero-dependency MCP stdio server.

Enables agents to run hybrid retrieval, reciprocal rank fusion, knowledge graph expansion, semantic caching, and context reordering so critical evidence is placed at prompt boundaries to reduce lost-in-the-middle degradation.

Enables AI agents to search and modify a personal knowledge base through OAuth-secured MCP tools, covering Obsidian vaults and Google Drive mirrors with semantic search, note read/write operations, audit logging, and eval-gated local classification.

An MCP server that enables Claude to interact with Google NotebookLM via browser automation, allowing management of notebooks, adding sources, and querying information.

Provides persistent identity and memory for AI agents across MCP-compatible harnesses, enabling agents to retain their name, values, and episodic memories between sessions regardless of the client or model.

Memory bank with Server as SSH support for central knowledge base

Enables chat with multiple LLM providers (OpenAI and Anthropic) while maintaining persistent conversation memory. Provides extensible tool framework for various operations including echo functionality and conversation storage/retrieval.

MCP server for alive-analysis. Query, search, and retrieve structured analysis history written with the ALIVE loop (Ask→Look→Investigate→Voice→Evolve), plus dashboard JSON export.

Enables agents to query across all their memory stores (brain, team, reading, code) in one call, returning a token-budgeted, ranked briefing with results interleaved from each source.