All Frameworks

Claude Code / MCP Quickstart

Give Claude Code persistent memory using the Model Context Protocol.

1Install & Configure

Install the MCP server package and set your API key.

npm install agenticmemoryai

export AGENTICMEMORY_API_KEY="amk_your_key_here"

2Create the MCP Server

Build a lightweight MCP server that exposes AgenticMemory as tools for Claude Code.

// mcp-memory-server.js
const { AgenticMemory } = require('agenticmemoryai');
const { McpServer } = require('@modelcontextprotocol/sdk/server/mcp.js');
const { StdioServerTransport } = require('@modelcontextprotocol/sdk/server/stdio.js');
const { z } = require('zod');

const memory = new AgenticMemory();
const SPACE_ID = process.env.MEMORY_SPACE_ID;

const server = new McpServer({ name: 'agenticmemory', version: '1.0.0' });

server.tool('store',
  'Store a message to short-term memory',
  { role: z.enum(['user', 'assistant', 'system']), content: z.string() },
  async ({ role, content }) => {
    await memory.store(SPACE_ID, { role, content });
    return { content: [{ type: 'text', text: 'Stored.' }] };
  }
);

server.tool('recall',
  'Recall recent messages from memory',
  { limit: z.number().optional().default(20) },
  async ({ limit }) => {
    const msgs = await memory.recall(SPACE_ID, { limit });
    return { content: [{ type: 'text', text: JSON.stringify(msgs.messages, null, 2) }] };
  }
);

server.tool('search',
  'Search memory by semantic relevance',
  { query: z.string(), limit: z.number().optional().default(10) },
  async ({ query, limit }) => {
    const results = await memory.search(SPACE_ID, query, { limit, scope: 'all' });
    return { content: [{ type: 'text', text: JSON.stringify(results.results, null, 2) }] };
  }
);

server.tool('remember',
  'Store a long-term entry (fact, summary, decision)',
  { title: z.string(), content: z.string(), tags: z.array(z.string()).optional() },
  async ({ title, content, tags }) => {
    await memory.addEntry(SPACE_ID, { type: 'fact', title, content, tags: tags || [] });
    return { content: [{ type: 'text', text: 'Saved to long-term memory.' }] };
  }
);

server.tool('bootstrap',
  'Load full context (messages, entries, entities, shared)',
  { query: z.string().optional() },
  async ({ query }) => {
    const ctx = await memory.bootstrap(SPACE_ID, {
      entries: 5, messages: 20, semantic: !!query, query
    });
    return { content: [{ type: 'text', text: JSON.stringify(ctx, null, 2) }] };
  }
);

const transport = new StdioServerTransport();
server.connect(transport);

3Add to Claude Code Config

Add the server to your .claude/settings.json or claude_desktop_config.json:

{
  "mcpServers": {
    "agenticmemory": {
      "command": "node",
      "args": ["mcp-memory-server.js"],
      "env": {
        "AGENTICMEMORY_API_KEY": "amk_your_key_here",
        "MEMORY_SPACE_ID": "your_space_id"
      }
    }
  }
}

Claude Code will now have access to store, recall, search, remember, and bootstrap tools.

---

Free tier: 1 space, 1K messages/month. Upgrade to Pro ($24.99/mo) for semantic search, entries, and entities.