{"id":583551,"recorded_at":"2026-10-28T00:01:12.545637Z","observed_at":"2026-10-28T00:01:12.545498Z","subject_kind":"endpoint","subject":"6b00068e-f1cb-411b-84e0-6f57b07ac553","kind":"mcp.tools","method":"probe.mcp/1","body":{"count":10,"tools":[{"description":"Add a text document to the authenticated user's knowledge base. The content is chunked, embedded, and stored so it becomes retrievable via rag_search.","inputSchema":{"additionalProperties":false,"properties":{"content":{"description":"The text content to ingest. It is chunked, embedded, and made retrievable via rag_search.","type":"string"},"group_key":{"description":"Optional group key to scope the document. Pass the same value to rag_search to retrieve only this group; omit it to search the whole corpus.","type":["string","null"]},"name":{"description":"A human-readable name/title for the document.","type":"string"}},"required":["name","content"],"type":"object"},"name":"file_ingest"},{"description":"Return the messages of one of the user's chats, in chronological order.","inputSchema":{"additionalProperties":false,"properties":{"chat_id":{"description":"The id of the chat (from list_chats) to read messages from.","type":"integer"},"limit":{"default":50,"description":"Maximum number of (most recent) messages to return (1-100).","maximum":100,"minimum":1,"type":"integer"}},"required":["chat_id"],"type":"object"},"name":"get_messages"},{"description":"List assistants the authenticated user may use from a connected app. Each row includes slug, name, description, version and origin.","inputSchema":{"additionalProperties":false,"properties":{},"type":"object"},"name":"list_assistants"},{"description":"List the authenticated user's conversations (most recently updated first).","inputSchema":{"additionalProperties":false,"properties":{"limit":{"default":50,"description":"Maximum number of chats to return (1-200).","maximum":200,"minimum":1,"type":"integer"}},"type":"object"},"name":"list_chats"},{"description":"List the user's available Synaplan task prompts (internal `tools:*` prompts excluded).","inputSchema":{"additionalProperties":false,"properties":{},"type":"object"},"name":"list_prompts"},{"description":"Store a new long-term memory for the authenticated user — a durable fact or preference that Synaplan will recall in future conversations.","inputSchema":{"additionalProperties":false,"properties":{"category":{"description":"Category for the memory, e.g. preferences, work, personal, health.","type":"string"},"key":{"description":"Short identifier for the memory (min 3 characters), e.g. tech_stack.","minLength":3,"type":"string"},"value":{"description":"The fact or preference to remember.","minLength":1,"type":"string"}},"required":["category","key","value"],"type":"object"},"name":"memory_add"},{"description":"Search the authenticated user's stored long-term memories (preferences, facts, context) using semantic similarity.","inputSchema":{"additionalProperties":false,"properties":{"category":{"description":"Optional category filter (e.g. preferences, work, personal).","type":["string","null"]},"limit":{"default":5,"description":"Maximum number of memories to return (1-50).","maximum":50,"minimum":1,"type":"integer"},"query":{"description":"Natural-language query describing the memory to look up.","type":"string"}},"required":["query"],"type":"object"},"name":"memory_search"},{"description":"Semantic search across the authenticated user's vectorized documents and knowledge base. Returns the most relevant text chunks with similarity scores.","inputSchema":{"additionalProperties":false,"properties":{"group_key":{"description":"Optional document group key to scope the search to a single document/collection.","type":["string","null"]},"limit":{"default":10,"description":"Maximum number of chunks to return (1-50).","maximum":50,"minimum":1,"type":"integer"},"min_score":{"default":0.3,"description":"Minimum similarity score (0-1) a chunk must reach to be returned.","maximum":1,"minimum":0,"type":"number"},"query":{"description":"Natural-language search query.","type":"string"}},"required":["query"],"type":"object"},"name":"rag_search"},{"description":"Find document chunks similar to a given source message/document id (the `message_id` returned by rag_search).","inputSchema":{"additionalProperties":false,"properties":{"limit":{"default":10,"description":"Maximum number of similar chunks to return (1-50).","maximum":50,"minimum":1,"type":"integer"},"message_id":{"description":"The source document/message id to find similar chunks for (use a `message_id` returned by rag_search).","type":"integer"}},"required":["message_id"],"type":"object"},"name":"rag_similar"},{"description":"Send a message through Synaplan's full AI pipeline — intent classification, web search, RAG over the user's documents, long-term memories, and inference — and return the synthesized answer. This is richer than a raw model call: it uses the authenticated account's knowledge base and memories.","inputSchema":{"additionalProperties":false,"properties":{"agentId":{"description":"Optional assistant id or slug (see list_assistants). Pins the reply to that assistant; fails when it is not published, not usable by you, or does not allow connected apps.","type":["string","integer","null"]},"chat_id":{"description":"Optional existing chat id (from list_chats) to continue a conversation. Omit to start a new chat.","type":["integer","null"]},"message":{"description":"The message or question to send through Synaplan's full AI pipeline (classification, web search, RAG over the user's documents, memories, and inference).","type":"string"}},"required":["message"],"type":"object"},"name":"synaplan_chat"}]},"body_sha256":"dcbd4b3956ea404a68a54a497f30a862f42fe96136d860f0fcfb5b72996abc4a","prev_id":null,"leaf":"0xf1e5e96aa7e71c805458bd40148ddeb4bdeb7c5ee4800f96bcff09b71d59b370","leaf_text":"{\"body\":\"dcbd4b3956ea404a68a54a497f30a862f42fe96136d860f0fcfb5b72996abc4a\",\"id\":583551,\"kind\":\"mcp.tools\",\"method\":\"probe.mcp/1\",\"observed_us\":1793145672545498,\"prev\":null,\"subject\":\"6b00068e-f1cb-411b-84e0-6f57b07ac553\",\"subject_kind\":\"endpoint\"}","day":null,"proof":[]}