Skip to main content

Authentication

Send the MCP token from Settings → MCP Tokens on every request.

Authorization: Bearer umx_YOUR_MCP_TOKEN

Create an MCP token under Settings → MCP Tokens after signing in. The free plan includes one token. The endpoint accepts either an api_keys credential or an mcp_tokens credential. The secret is shown once.

Associative memory in 2.0

unimatrix_recall runs associative graph activation unless activate is false. unimatrix_get_context returns the current, contested, and superseded partition. unimatrix_feedback records helped, wrong, or stale. Optional fields include space_id, limit (default 8, maximum 20), and session_id. The dedicated unimatrix_activate_memory tool also accepts analytic_fixed_point, temporal_window_seconds, and similarity_beta. Explicit seed-memory IDs are not handled by the current implementation.

{ "toolName": "unimatrix_get_context", "args": { "query": "Why did we choose idempotent retries?", "intent": "implementation review", "limit": 8 } }

The matching server, worker and AMG migration must be present. A local fallback reports activationRan: false and does not substitute a context package or a feedback write. Architecture and availability notes →

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:

  1. Call unimatrix_list_spaces
  2. Call unimatrix_get_space on the most relevant space(s)
  3. 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.

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

More Resources for Non-MCP LLMs