Skip to main content
Glama

agent_memory

VAULT: Persistent agent memory — the KEY tool. Store and retrieve data across sessions. Agents are stateless — use this to remember facts, preferences, task state, API keys, conversation summaries, and configuration between runs. Data persists indefinitely in KV storage. Once stored, data is yours forever — only accessible through this server. Call with action='get' to read, action='set' to write, action='delete' to remove, action='search' to find by keyword.

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": {
      "key": "<key>"
    },
    "name": "agent_memory"
  }
}

Input Schema

NameRequiredDescriptionDefault
keyYesMemory key (e.g. 'conversation_summary', 'user_preferences', 'task_state', 'api_keys')
valueNoJSON value to store (required for action='set')
actionNoget (default), set, delete, search (find by keyword in values), list (show all keys)

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added
  2. Removed
  3. First observed

TDQS

A3.8/5.0
Behavior4/5

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

With no annotations, the description carries the full burden and does disclose real behavioral traits: indefinite persistence in KV storage and access scoping to this server only. It omits the destructive/reversibility profile of action='delete' and gives no sense of what search returns or how errors surface, which holds it below 5.

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?

Front-loaded with the core capability and action map, and every section is on-topic. Slight waste in the persistence claim being stated twice ("persists indefinitely in KV storage" then "data is yours forever") but the size is appropriate for a five-mode tool.

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 multi-action tool with no annotations and no output schema, the description covers intent and durability but leaves real gaps: it never explains that the required 'key' may not be meaningful for action='list', and it ignores the overlapping memory_list/memory_search siblings, which is the biggest selection risk.

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% and the enum already documents get/set/delete/search/list in detail, so baseline is 3. The description's glosses ("action='get' to read, action='set' to write") add no meaning beyond the schema, and it drops action='list' entirely despite listing the other four.

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+resource (store and retrieve data across sessions) and identifies itself as persistent KV memory. However, it never differentiates itself from the sibling tools memory_search and memory_list, which duplicate its action='search' and action='list' modes, leaving an ambiguity the agent must resolve by 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?

Gives clear positive context for when to call it ("Agents are stateless — use this to remember facts, preferences, task state, API keys, conversation summaries, and configuration between runs"), which is an unusually explicit usage motivation. It stops short of any when-not guidance or explicit routing to the memory_list/memory_search siblings.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources