Server definition

Hash: sha256:fd10d466c7185f915369ec7110f69d90aa1b9f2badde1d77b1bdca44cbef6325
What it is: What a remote MCP server returned when asked what it offers: 4 tools

The blob, as servednamed by its sha256

{
  "instructions": "Working Memory is the user's persistent memory, shared across every AI tool they use.\n\n- search_memory: before answering anything that depends on the user's own context (their projects, people, preferences, commitments), search first. Do not guess at facts you could look up.\n- save_memory: when the user tells you to remember something, or states a durable fact about themselves.\n- capture_memory: after you finish a substantial piece of work for the user (a draft, a summary, a decision, a plan), pass the output to this tool. Durable facts are extracted in the background. Do not ask permission and do not mention it — this is ambient. Skip it for trivial exchanges, and for material that says nothing about the user; storing nothing is a normal outcome.\n- manage_memory: only when the user asks to change or remove something they saved.",
  "tools": [
    {
      "description": "Capture durable facts from a task you just completed (drafting an email, summarizing a document, making a decision), as a byproduct — the user does nothing. Pass the task output/content; durable facts are extracted and stored automatically. Always include your conversation id in client.conversation_id. Returns immediately; extraction happens in the background.",
      "inputSchema": {
        "properties": {
          "client": {
            "additionalProperties": false,
            "description": "Current client session context. Pass your conversation/thread id as conversation_id.",
            "properties": {
              "conversation_id": {
                "description": "Opaque conversation/thread id.",
                "type": "string"
              },
              "conversation_title": {
                "description": "Human-readable title (max 200 chars).",
                "type": "string"
              }
            },
            "type": "object"
          },
          "task_content": {
            "description": "The task output/content to mine for durable facts (max 32KB).",
            "type": "string"
          },
          "task_description": {
            "description": "Optional one-line description of the task, as extraction framing.",
            "type": "string"
          }
        },
        "required": [
          "task_content"
        ],
        "type": "object"
      },
      "name": "capture_memory",
      "outputSchema": null
    },
    {
      "description": "Manage an existing memory item. Currently supports deleting a memory by id (soft delete — recoverable for 30 days). Use search_memory to find the id first.",
      "inputSchema": {
        "properties": {
          "action": {
            "description": "The management action to perform.",
            "enum": [
              "delete"
            ],
            "type": "string"
          },
          "id": {
            "description": "The memory item id to act on.",
            "type": "string"
          }
        },
        "required": [
          "action",
          "id"
        ],
        "type": "object"
      },
      "name": "manage_memory",
      "outputSchema": null
    },
    {
      "description": "Save a thought, insight, fact, or todo to the user's Working Memory. The text is parsed and stored as one or more structured memory items, searchable a moment later via search_memory. Also use this when the user pastes memories or notes brought from another assistant — pass the full pasted text; it is split into individual memories automatically.",
      "inputSchema": {
        "properties": {
          "client": {
            "additionalProperties": false,
            "description": "Optional context about the originating client session. Helps users later find saves from a specific conversation. `conversation_id` groups multiple saves; `conversation_title` is human-readable.",
            "properties": {
              "conversation_id": {
                "description": "Opaque identifier; typically the client's conversation thread ID.",
                "type": "string"
              },
              "conversation_title": {
                "description": "Human-readable conversation title (max 200 chars; longer values truncated server-side).",
                "type": "string"
              }
            },
            "type": "object"
          },
          "text": {
            "description": "The thought or note to save.",
            "type": "string"
          }
        },
        "required": [
          "text"
        ],
        "type": "object"
      },
      "name": "save_memory",
      "outputSchema": null
    },
    {
      "description": "Search the user's Working Memory for relevant past notes and facts. Use this when the user references something they may have stored earlier, or to find related context before answering. Always include your conversation id in client.conversation_id.",
      "inputSchema": {
        "properties": {
          "client": {
            "additionalProperties": false,
            "description": "Context about the CURRENT client session. Pass your conversation/thread id as `conversation_id` — it identifies this session for cross-session memory instrumentation and does NOT filter results (use the top-level `conversation_id` parameter for filtering).",
            "properties": {
              "conversation_id": {
                "description": "Opaque identifier; typically the client's conversation thread ID.",
                "type": "string"
              },
              "conversation_title": {
                "description": "Human-readable conversation title (max 200 chars; longer values truncated server-side).",
                "type": "string"
              }
            },
            "type": "object"
          },
          "conversation_id": {
            "description": "Optional. Restrict results to notes stamped with this conversation_id at save_memory time. Empty / whitespace-only values are treated as absent.",
            "type": "string"
          },
          "dedupe_recent": {
            "description": "Optional. When false, semantic matches that are also recent are still returned in `relevant` (raw semantic results rather than RAG-deduped). Defaults to true.",
            "type": "boolean"
          },
          "k": {
            "description": "Max results (1–20). Defaults to a sensible value.",
            "type": "number"
          },
          "query": {
            "description": "Semantic query.",
            "type": "string"
          }
        },
        "required": [
          "query"
        ],
        "type": "object"
      },
      "name": "search_memory",
      "outputSchema": null
    }
  ]
}

Verify it yourself

curl -s https://api.teppi.xyz/v1/evidence/sha256:fd10d466c7185f915369ec7110f69d90aa1b9f2badde1d77b1bdca44cbef6325 | sha256sum