"Kingsoft Document Connector" matching MCP connectors:

A connector providing AI assistants searchable access to climate-aligned contract clauses, glossary terms, and practical guides from The Chancery Lane Project's curated knowledge graph.

Open scientific and engineering knowledge for AI agents: search, evidence, document publishing.

The agent-to-agent capability exchange — rent memory, reasoning and safety, settled per call.

A persistent intention layer for AI agents. Injects a soul document into model system prompts before each session. REST API + MCP server. Auth via X-API-Key header.

Durable, shareable and governed project memory with smart triage and explicit project composition.

Personal finance, bank account, and shared memory connector for Claude, ChatGPT, Gemini Spark & more

Read-only MCP connector serving the Run It on AI book; index and Implementation Blocks are free.

Private projects, preflight, decisions, and handoffs that keep work continuous across AI tools.

Private memory layer — one library your notes, docs, and chat history live in, that any AI tool (Claude, Cursor, ChatGPT) connects to over MCP instead of re-pasting context. Semantic search over your own documents with citations; every memory is a document you can read, edit, and delete. ~80% fewer context tokens than pasting your library. Connect via OAuth (sign in when prompted) — get started at

LLMtoMD is the memory layer for AI coding agents. It converts any document — PDF, DOCX, slides, spreadsheets, images, audio, even whole websites — into clean, structured Markdown, then exposes it over MCP so your agent can search your FRDs, specs, and API docs on demand instead of re-reading (or forgetting) them.

Personal wiki and memory layer for AI assistants. Persistent, structured memory across sessions.

Agentic search over your Dewey document collections from any MCP-compatible client.

Document hosting and encrypted agent memory with multi-tenant persistence.

Make your knowledge agent-ready. Connect docs from Confluence, Notion, GitHub, Dropbox, or Google Drive — any AI agent searches them via one MCP endpoint. 3 retrieval modes: vector search, broad search, and full document access. The agent decides how deep to dig.