Mnemo - Persistent AI Memory

Overview Schema Source Related Servers Discussions Admin

config__open_relay

Retrieve the relay configuration URL and open it in the browser to set up Mnemo sync. Returns the URL, browser launch status, and current state.

Instructions

Get the relay configuration URL for mnemo-mcp, opening it in the user's browser when possible. Returns the relay URL, whether the browser launched, and the current status.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "ctx": "<ctx>"
    },
    "name": "config__open_relay"
  }
}

Input Schema

Name	Required	Description	Default
`ctx`	Yes

Output Schema

Name	Required	Description	Default
No arguments

Schema Changelog

Changes observed during successful MCP inspections.

Changed3 schema fields changedv2.6.0Jul 14, 2026

addedInput schema / $defs

Added value: +{
+  "Context": {
+    "description": "Context object providing access to MCP capabilities.\n\nThis provides a cleaner interface to MCP's RequestContext functionality.\nIt gets injected into tool and resource functions that request it via type hints.\n\nTo use context in a tool function, add a parameter with the Context type annotation:\n\n```python\n@server.tool\nasync def my_tool(x: int, ctx: Context) -> str:\n    # Log messages to the client\n    await ctx.info(f\"Processing {x}\")\n    await ctx.debug(\"Debug info\")\n    await ctx.warning(\"Warning message\")\n    await ctx.error(\"Error message\")\n\n    # Report progress\n    await ctx.report_progress(50, 100, \"Processing\")\n\n    # Access resources\n    data = await ctx.read_resource(\"resource://data\")\n\n    # Get request info\n    request_id = ctx.request_id\n    client_id = ctx.client_id\n\n    # Manage state across the session (persists across requests)\n    await ctx.set_state(\"key\", \"value\")\n    value = await ctx.get_state(\"key\")\n\n    # Store non-serializable values for the current request only\n    await ctx.set_state(\"client\", http_client, serializable=False)\n\n    return str(x)\n```\n\nState Management:\nContext provides session-scoped state that persists across requests within\nthe same MCP session. State is automatically keyed by session, ensuring\nisolation between different clients.\n\nState set during `on_initialize` middleware will persist to subsequent tool\ncalls when using the same session object (STDIO, SSE, single-server HTTP).\nFor distributed/serverless HTTP deployments where different machines handle\nthe init and tool calls, state is isolated by the mcp-session-id header.\n\nThe context parameter name can be anything as long as it's annotated with Context.\nThe context is optional - tools that don't need it can omit the parameter.",
+    "properties": {
+      "_STATE_TTL_SECONDS": {
+        "default": 86400,
+        "title": "State Ttl Seconds",
+        "type": "integer"
+      }
+    },
+    "title": "Context",
+    "type": "object"
+  }
+}

addedInput schema / properties / ctx

Added value: +{
+  "$ref": "#/$defs/Context"
+}

addedInput schema / required
```
Added value: +[
+  "ctx"
+]
```

Addedv2.1.1May 28, 2026

TDQS

A4.4/5.0

Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries the burden of behavioral disclosure. It transparently reveals the browser-opening side effect, qualifies it with 'when possible', and lists the return contents. It does not detail failure modes or status semantics, but the core behavior is clearly disclosed.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single focused sentence that front-loads the main purpose and then covers side effects and return values. Every clause earns its place with no repetition or filler.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the presence of an output schema and the lack of meaningful user parameters, the description covers the action, side effect, and returned information sufficiently. A small gap is that it does not elaborate on what 'current status' means or what happens when the browser cannot be launched, but these are minor given the output schema.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The only parameter is 'ctx', an injected Context object rather than a domain-specific parameter. The schema itself provides extensive documentation for Context, and the description does not need to explain it. Adding parameter detail would add little value, so the baseline for effectively no user-facing parameters is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific action ('Get'), a specific resource ('the relay configuration URL for mnemo-mcp'), and an additional behavior ('opening it in the user's browser when possible'). This clearly differentiates it from the sibling tools such as the generic 'config' and all memory-related tools.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides clear context: this tool is for retrieving the relay configuration URL and attempting to open it in the browser. It does not name alternatives or exclusions, but the intended use case is readily inferable and no misleading guidance is present.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Deploy Server