Categories › AI & Agents › Agent memory & context
Self-hosted AI workspace: semantic RAG document search, long-term memory, and AI chat via MCP.
Remote server: your requests and data go to web.synaplan.com. Claude Code: claude mcp add --transport http synaplan https://web.synaplan.com/mcp · Claude app: Settings → Connectors → Add custom connector.
The tools this server listed when we connected to it, in its own words.
synaplan_chat — Send a message through Synaplan's full AI pipeline — intent classification, web search, RAG over the user's documents, long-term memories, arag_search — Semantic search across the authenticated user's vectorized documents and knowledge base. Returns the most relevant text chunks with similarimemory_search — Search the authenticated user's stored long-term memories (preferences, facts, context) using semantic similarity.memory_add — Store a new long-term memory for the authenticated user — a durable fact or preference that Synaplan will recall in future conversations.file_ingest — Add a text document to the authenticated user's knowledge base. The content is chunked, embedded, and stored so it becomes retrievable via rrag_similar — Find document chunks similar to a given source message/document id (the `message_id` returned by rag_search).list_chats — List the authenticated user's conversations (most recently updated first).get_messages — Return the messages of one of the user's chats, in chronological order.list_prompts — List the user's available Synaplan task prompts (internal `tools:*` prompts excluded).list_assistants — List assistants the authenticated user may use from a connected app. Each row includes slug, name, description, version and origin.Not tested by KitScout yet. When our harness runs it, pros, cons and the tasks we tried appear here, with the date and evidence.