Back to FireMCP Pro
Specialized Memory MCP

FireMemory

Give your AI agents long-term memory and state persistence using Firestore.

About FireMemory

FireMemory is a dedicated MCP server designed to solve the context window limitation of LLMs. It provides a structured way for agents to store important information, recall it when relevant, and maintain a persistent state across different sessions. It runs alongside FireMCP Pro but offers a specialized set of tools focused purely on memory management.

Memory Endpoint

Use this specific URL to connect to the FireMemory MCP server.

https://mcp.firemcp.anishroy.com/memory/mcp

Required Headers

FireMemory requires the standard FireMCP headers plus an optional configuration header:

Header Name Description
x-firebase-api-key Your Firebase Project API Key
x-firebase-project-id Your Firebase Project ID
x-firebase-user-email Firebase Auth User Email
x-firebase-user-password Firebase Auth User Password
x-memory-namespace Required. Namespace to organize memories (e.g., user_id, project_name)
x-memory-collection Optional. Custom collection name (default: "firemcp_memory")

Memory Capabilities

Store Memory
Save facts, user preferences, or conversation context.
Recall Memories
Search for past memories based on keywords.
Update Memory
Refine or correct existing memories as new information becomes available.
Forget Memory
Remove outdated or irrelevant information.
List Stats
Get an overview of the memory usage and metadata.