AGI MCP Server

create_memory

Generate structured memories for AI systems by defining type (episodic, semantic, procedural, strategic), content, embedding, importance, and metadata to enhance context and continuity.

Instructions

Create a new memory with optional type-specific metadata

Input Schema

Name	Required	Description
`content`	Yes	The main content/text of the memory
`embedding`	Yes	Vector embedding for the memory content
`importance`	No	Importance score (0.0 to 1.0)
`metadata`	No	Type-specific metadata (action_taken, context, confidence, etc.)
`type`	Yes	Type of memory to create

Input Schema (JSON Schema)

{
  "properties": {
    "content": {
      "description": "The main content/text of the memory",
      "type": "string"
    },
    "embedding": {
      "description": "Vector embedding for the memory content",
      "items": {
        "type": "number"
      },
      "type": "array"
    },
    "importance": {
      "default": 0,
      "description": "Importance score (0.0 to 1.0)",
      "type": "number"
    },
    "metadata": {
      "default": {},
      "description": "Type-specific metadata (action_taken, context, confidence, etc.)",
      "type": "object"
    },
    "type": {
      "description": "Type of memory to create",
      "enum": [
        "episodic",
        "semantic",
        "procedural",
        "strategic"
      ],
      "type": "string"
    }
  },
  "required": [
    "type",
    "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/cognitivecomputations/agi-mcp-server'

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