Maindex Smart Memory Service

This connector has been deprecated

Replaced by Maindex Smart Memory Service.

Duplicate entry

keep

Store a new memory in Maindex (Smart). Provide the content to persist, with optional headline, tags, collections, and metadata. Each call creates a distinct memory — not idempotent. CONTENT POLICY: NEVER store passwords, API keys, secrets, credit card numbers, SSNs, government IDs, medical/health records (PHI/HIPAA), biometric data, or any legally protected PII. Sanitize content before storing.

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": {
      "content": "<content>"
    },
    "name": "keep"
  }
}

Input Schema

Name	Required	Description
`tags`	No	Optional tags for categorization.
`team`	No	Team workspace slug when keeping into a team collection.
`content`	Yes	Primary text to store; required.
`rewrite`	No	FAILSAFE — defaults to false. When false (the default), content is stored exactly as provided with zero LLM processing. Set to true ONLY if the caller explicitly opts into LLM-assisted rewriting for improved clarity and structure. No content transformation occurs unless this flag is explicitly true.
`headline`	No	Optional headline; Smart may generate one if omitted.
`metadata`	No	Opaque JSON metadata stored with the memory.
`collection`	No	Target team collection slug. Required when team is set.
`collections`	No	Collection slugs or IDs to add the new memory to.

Output Schema

Name	Required	Description
`memory`	Yes	The created memory object, or null on failure
`success`	Yes	Whether the memory was created successfully
`traceId`	Yes	Trace ID for debugging

Schema Changelog

Changes observed during successful MCP inspections.

First observedNov 8, 2026

TDQS

A4.2/5.0

Behavior4/5

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

The annotations already declare non-read-only, non-idempotent, non-destructive behavior, and the description reinforces non-idempotence with 'Each call creates a distinct memory.' It adds meaningful policy beyond annotations by prohibiting secrets, credentials, financial data, PHI, biometrics, and other protected PII, though it does not cover permissions, rate limits, or workspace scoping behavior.

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 front-loaded with purpose, then the required content, then the non-idempotency warning, then a clearly labeled content policy. Every sentence carries useful information, and the safety policy is compact despite its length.

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 existing output schema and 100% parameter description coverage, the description does not need to explain return values or every parameter. It covers creation, non-idempotency, and storage policy well, though it could more explicitly route agents to update for existing memories and clarify how rewrite or team scoping affect behavior.

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

Parameters3/5

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

Schema description coverage is 100%, so the schema already defines all eight parameters in detail, including the important rewrite failsafe and team/collection relationship. The description mentions content, headline, tags, collections, and metadata but omits rewrite, team, and collection, adding no semantic detail beyond the schema; baseline 3 applies.

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 verb and resource: 'Store a new memory in Maindex (Smart).' The word 'new' and the clarification that each call creates a distinct memory distinguish it from the update, recall, and forget siblings without requiring schema inspection.

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 makes clear this is for creating new memories and warns that repeated calls are not idempotent, which is useful usage context. However, it does not explicitly name update as the alternative for modifying an existing memory or state when not to use this tool.

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

All Maindex Smart Memory Service tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?