Memori

Memori MCP (Model Context Protocol)

memori-mcp is the official Memori MCP server. Connect it to your AI agent to give it long-term memory: recall relevant facts before answering, store durable preferences after responding, and maintain context across sessions.

Why Memori MCP?

Memori turns stateless agents into stateful systems by providing structured, persistent memory that works across sessions and workflows.

  1. Persistent state beyond prompts — Most agents rely on prompt context and lose state between runs. Memori provides durable, structured memory so agents can retain facts, decisions, and outcomes over time.
  2. Memory from execution (not just natural language) — Traditional systems extract memory from chat. Memori builds memory from agent execution itself — including tool calls, decisions, and results. This enables true agent-native memory, not just conversational recall.
  3. Lower cost, higher accuracy — Instead of expanding prompt context, Memori retrieves only what matters.
    • Significantly reduced token usage
    • Faster responses
    • Improved accuracy vs long-context approaches
  4. Works with any MCP client and production-ready - No SDK, no code changes, just config

Memori is state infrastructure for production agents — enabling persistent memory, efficient retrieval, and structured context across both natural language and agent execution.

Server Details

PropertyValue
ServerMemori MCP
Endpointhttps://api.memorilabs.ai/mcp/
TransportStateless HTTP
AuthAPI key via request headers

Headers

  • Name
    X-Memori-API-Key
    Type
    string
    Required
    Required
    Description

    Your Memori API key from app.memorilabs.ai.

  • Name
    X-Memori-Entity-Id
    Type
    string
    Required
    Required
    Description

    Stable end-user or entity identifier (e.g. user_123).

  • Name
    X-Memori-Process-Id
    Type
    string
    Description

    Optional process, app, or workflow identifier (e.g. my_agent) for memory isolation.

session_id is derived automatically as <entity_id>-<UTC year-month-day:hour>. You do not need to provide it.

Tools

recall

Fetches relevant memories at the start of a user turn.

  • Name
    query
    Type
    string
    Required
    Required
    Description

    The latest user message — typically passed verbatim.

entity_id is read from MCP headers. process_id is read when provided. Returns a structured memory payload with relevant context.

advanced_augmentation

Stores durable memory after the agent has drafted a response.

  • Name
    user_message
    Type
    string
    Required
    Required
    Description

    The user's message for this turn.

  • Name
    assistant_response
    Type
    string
    Required
    Required
    Description

    The assistant's response for this turn.

entity_id is read from MCP headers. process_id is read when provided. Returns a confirmation: memory being created.

Example Agent Flow

Given the user message: "I prefer Python and use uv for dependency management."

  1. Agent calls recall with the user message as query
  2. Agent composes a response using any returned facts
  3. Agent sends the response to the user
  4. Agent calls advanced_augmentation with the user_message and assistant_response

On a later turn like "Write a hello world script", the agent recalls the Python + uv preference and personalizes its response.

Validation Checklist

After configuring your client, verify the setup:

  • MCP server shows as connected and healthy in your client UI
  • Tools list includes recall and advanced_augmentation
  • Calls return non-401 responses
  • recall returns memories for known entities
  • advanced_augmentation returns memory being created