AGI MCP Server

create_working_memory

Generate a temporary working memory with a specified time-to-live, enabling AI systems to store and manage content and embeddings for short-term task continuity and context retention.

Instructions

Create a temporary working memory with expiration

Input Schema

Name	Required	Description
`content`	Yes	Content of the working memory
`context`	No
`embedding`	Yes	Vector embedding for the content

Input Schema (JSON Schema)

{
  "properties": {
    "content": {
      "description": "Content of the working memory",
      "type": "string"
    },
    "context": {
      "default": {},
      "properties": {
        "ttl": {
          "default": 3600,
          "description": "Time to live in seconds",
          "type": "integer"
        }
      },
      "type": "object"
    },
    "embedding": {
      "description": "Vector embedding for the content",
      "items": {
        "type": "number"
      },
      "type": "array"
    }
  },
  "required": [
    "content",
    "embedding"
  ],
  "type": "object"
}

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/QuixiAI/agi-mcp-server'

If you have feedback or need assistance with the MCP directory API, please join our Discord server