"Zoom" matching MCP servers:

Enables Claude chats to communicate across machines or sessions via shared encrypted rooms, with tools to create, join, send, read, wait, search, and delete room messages.

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.

Local-first knowledge graph MCP server — hybrid BM25 + vector + graph retrieval over your personal vault with provenance-grade extraction. 8 tools for Claude Desktop including search, archaeology, and graph write.

Exposes Iceberg-backed ontology objects, links, and actions as typed MCP tools for LLM agents, enabling governed data access and operations without raw SQL.

Enables every coding agent session, on every machine you use, to share one permanent word-for-word memory that is folded into a binary tree of one-line summaries, so a fresh session can read the whole history in a fixed-size view and zoom into any line down to the original message. Summaries are produced by your own agents through the server's compaction tools, with no model or API key required, and machines synchronize through a shared folder without any central owner.

Enables proof-carrying project execution through a read-only remote MCP endpoint and WebMCP tools for managing Project Passports, task graphs, evidence-backed provider comparisons, route approvals, artifacts, verification records, and checkpoints without executing external providers.

A git-native decision journal that uses a local LLM to infer and store the rationale behind code changes, providing MCP tools for AI coding tools to query commit history.

Enables Claude Desktop and compatible agents to search, read, add, update, and delete a locally stored, user-curated memory using hybrid retrieval with reranking and Qdrant. All processing runs locally without cloud services or API keys.