Skip to main content
Glama

membridge_remember

Idempotent

Save a durable fact into your local portable brain file so it persists across Claude, Cursor, and other MCP clients. Categorizes and redacts secrets by default.

Instructions

Save a durable memory fact into your local portable brain file (~/.membridge/brain.json) so it persists across Claude, Cursor, Antigravity, and other MCP clients.

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": {
      "text": "<text>"
    },
    "name": "membridge_remember"
  }
}

Input Schema

NameRequiredDescriptionDefault
textYesFact, preference, project, or rule to remember.
redactNoMask secrets before saving (default true).
categoryNoOptional category (auto-detected if omitted).

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A3.5/5.0
Behavior3/5

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

Annotations already declare non-destructive, idempotent, local-only writes, so the safety profile is covered. The description adds genuinely new context—the exact file written and the cross-client portability—but says nothing about what happens when the same fact already exists (merge vs skip vs overwrite), despite idempotentHint=true making that question salient.

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

Conciseness4/5

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

A single front-loaded sentence with the action first and the payoff last; every clause earns its place. It is lean without being cryptic.

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

Completeness3/5

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

For a simple one-required-parameter write tool with annotations and full schema coverage, the definition is nearly sufficient, but with no output schema it never says what a successful call returns (confirmation, stored id, dedupe notice). That is the one remaining gap an agent would want closed.

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?

Schema coverage is 100%, so all three parameters are already documented including the redact default and the category enum. The description adds a bit of framing by calling out the file the fact lands in, but nothing parameter-specific beyond the schema, which is the expected baseline-plus for a fully documented schema.

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

Purpose4/5

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

States a specific verb and resource ("Save a durable memory fact") plus the concrete storage target (~/.membridge/brain.json) and the benefit (cross-client persistence). It is clear what the tool does, but it never distinguishes this write path from siblings like membridge_extract or membridge_recall, leaving the agent to infer that this is the only persistence entry point.

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

Usage Guidelines3/5

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

The word "durable" implies a when-to-use criterion (long-lived facts rather than transient context), but there is no explicit when-not guidance, no prerequisites, and no named alternative for reads or extraction. Usage is implied rather than taught.

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