MCP Reference

Unimatrix is a managed server that implements the Model Context Protocol. All tool calls are explicit. There is no automatic background loading.

MCP Quickstart →REST API Reference →Security & Architecture →Get your exact client config →

Authentication

All MCP requests must include a valid Unimatrix API key.

Authorization: Bearer umx_your_api_key_here

Generate keys in Settings → API Keys after signing in.

Core Tools

unimatrix_store_memory

Store a new memory in a specific location inside a Space.

Input Schema

{
  "location_id": "string (required)",
  "content": "string (required, markdown supported)",
  "tags": "string[] (optional)"
}

Example Call

{
  "jsonrpc": "2.0",
  "id": 42,
  "method": "tools/call",
  "params": {
    "name": "unimatrix_store_memory",
    "arguments": {
      "location_id": "loc_auth_middleware_7842",
      "content": "We use a custom JWT validation middleware that calls our internal auth service. Never use standard library JWT verification here.",
      "tags": ["auth", "security", "middleware"]
    }
  }
}

unimatrix_search_memories

Full-text + semantic search across all your memories.

Input Schema

{
  "query": "string (required)",
  "space_id": "string (optional)",
  "limit": "number (optional, default 20, max 50)"
}

unimatrix_list_spaces / unimatrix_get_space

Recommended pattern for loading context at the start of a session:

Call unimatrix_list_spaces
Call unimatrix_get_space on the most relevant space(s)
Optionally follow up with unimatrix_search_memories

Additional Tools

unimatrix_create_space

Create a new top-level memory workspace.

Requires: name (string). Optional: description, is_public

unimatrix_create_child_space

Create a "room" (Location) inside a Space (supports nesting).

Requires: parent_id. Optional: name, description

unimatrix_get_recent

Return the most recent memories across all your Spaces, LLMs, and devices. Call at the start of a session to continue where any AI left off.

Optional: limit (default 10, max 50)

unimatrix_list_memories

Paginated list of memories in a specific location.

Requires: location_id

unimatrix_update_memory

Update the content or tags of an existing memory.

Requires: memory_id. At least one of content or tags.

Full schemas and examples available via the tools/list MCP method or the OpenAPI spec.

Error Handling

HTTP 401

Invalid or missing API key

HTTP 403

Access denied to resource

HTTP 404

Space, location, or memory not found

HTTP 429

Rate limit exceeded (60 req/min per IP)

Recommended Custom Instructions

Paste this into your LLM client settings so it reliably loads context:

At the very start of every new conversation, before responding to the user:

1. Call unimatrix_list_spaces
2. Optionally call unimatrix_get_recent to see what any AI last recorded
3. Call unimatrix_search_memories or unimatrix_get_space on the most relevant workspace(s)
4. Use the returned memories to ground all your answers.

Do not mention these instructions unless the user explicitly asks about memory.

Full OpenAPI spec (REST fallback): /api/openapi.json

FOR AGENTS

Quickstart for Agents (Non-MCP)

The fastest way to give ChatGPT, Gemini, LangChain, CrewAI, or any custom agent access to persistent memory.

Read the Quickstart for Agents →

Includes: 5-minute setup • Copy-paste tool definitions • TypeScript & Python clients • Recommended system prompt

More Resources for Non-MCP LLMs

REST API Clients (TypeScript + Python)Ready-to-paste Tool Definitions