Memory MCP Server
Pricing
Pay per usage
Memory MCP Server
Persistent memory for AI agents via knowledge graph. Store entities, relations, and observations that persist across sessions. MCP-compatible.
Memory MCP Server
Pricing
Pay per usage
Persistent memory for AI agents via knowledge graph. Store entities, relations, and observations that persist across sessions. MCP-compatible.
Connect the Memory MCP Server Actor to an AI application through the Apify MCP server. MCP clients with OAuth support sign you in to Apify without an API token.
{ "mcpServers": { "apify": { "type": "http", "url": "https://mcp.apify.com/?tools=fetch-actor-details,constant_quadruped/memory-mcp-server" } }}Add the configuration above to your project's .mcp.json file for Claude Code, then run /mcp in Claude Code to sign in to Apify. It connects to the hosted Apify MCP server with the Memory MCP Server Actor already loaded. Clients without OAuth support can authenticate with an Authorization: Bearer header carrying an API token from API & Integrations in Apify Console.
For other MCP clients, get a client-specific configuration with the Memory MCP Server Actor preconfigured at https://mcp.apify.com/?tools=fetch-actor-details,constant_quadruped/memory-mcp-server.
You can connect to the Apify MCP server using an MCP client that supports Streamable HTTP.
If you want to learn more about our Apify MCP implementation, check out our MCP documentation. To learn more about the Model Context Protocol in general, refer to the official MCP documentation or read our blog post.