# Membangun Klien MCP Khusus

Jika Anda membangun aplikasi LLM Anda sendiri, Anda dapat terhubung ke Synapse
MCP server langsung menggunakan SDK MCP resmi. Ini memberikan aplikasi Anda
akses ke semua 79 alat Synapse.

## SDK

| Bahasa | Paket |
|----------|---------|
| TypeScript/JavaScript | `@modelcontextprotocol/sdk` |
| Python | `mcp` |

## Contoh TypeScript

### Pasang

```bash
npm install @modelcontextprotocol/sdk
```

### Hubungkan via stdio

```typescript
import { Client } from "@modelcontextprotocol/sdk/client/index.js";
import { StdioClientTransport } from "@modelcontextprotocol/sdk/client/stdio.js";

const transport = new StdioClientTransport({
  command: "npx",
  args: ["-y", "synapse-mcp-api@latest"],
  env: {
    SYNAPSE_MIND_KEY: process.env.SYNAPSE_MIND_KEY!,
    SYNAPSE_URL: "https://synapse.schaefer.zone",
  },
});

const client = new Client(
  { name: "my-app", version: "1.0.0" },
  { capabilities: {} }
);

await client.connect(transport);

// List all available tools
const { tools } = await client.listTools();
console.log(`Available tools: ${tools.length}`);
for (const tool of tools) {
  console.log(`- ${tool.name}: ${tool.description}`);
}

// Call a tool
const result = await client.callTool({
  name: "memory_recall",
  arguments: {},
});
console.log(result.content);

// Store a memory
await client.callTool({
  name: "memory_store",
  arguments: {
    category: "fact",
    key: "custom_client_test",
    content: "Built a custom MCP client",
    tags: ["test", "mcp"],
    priority: "normal",
  },
});

await client.close();
```

### Hubungkan via HTTP/SSE (remote)

```typescript
import { Client } from "@modelcontextprotocol/sdk/client/index.js";
import { SSEClientTransport } from "@modelcontextprotocol/sdk/client/sse.js";

const transport = new SSEClientTransport(
  new URL("https://synapse-mcp.schaefer.zone/sse"),
  {
    requestInit: {
      headers: {
        Authorization: `Bearer ${process.env.SYNAPSE_MIND_KEY}`,
      },
    },
  }
);

const client = new Client(
  { name: "my-app", version: "1.0.0" },
  { capabilities: {} }
);

await client.connect(transport);
// ... use as above
```

## Contoh Python

### Pasang

```bash
pip install mcp
```

### Hubungkan via stdio

```python
from mcp import ClientSession, StdioServerParameters
from mcp.client.stdio import stdio_client

server_params = StdioServerParameters(
    command="npx",
    args=["-y", "synapse-mcp-api@latest"],
    env={
        "SYNAPSE_MIND_KEY": "mk_YOUR_KEY",
        "SYNAPSE_URL": "https://synapse.schaefer.zone",
    },
)

async with stdio_client(server_params) as (read, write):
    async with ClientSession(read, write) as session:
        await session.initialize()

        # List tools
        tools = await session.list_tools()
        print(f"Available tools: {len(tools.tools)}")

        # Call a tool
        result = await session.call_tool("memory_recall", {})
        print(result.content)

        # Store a memory
        await session.call_tool("memory_store", {
            "category": "fact",
            "key": "python_client_test",
            "content": "Built a Python MCP client",
            "tags": ["test", "mcp", "python"],
            "priority": "normal",
        })
```

## Tool Profiles

Saat menghubungkan, Anda dapat meminta tool profile spesifik melalui header
`Mcp-Tool-Profile` (HTTP/SSE) atau env var `MCP_PROFILE` (stdio):

```typescript
// stdio: set env var
env: {
  SYNAPSE_MIND_KEY: "mk_...",
  MCP_PROFILE: "minimal",  // 8 tools instead of 119
}

// HTTP/SSE: set header
requestInit: {
  headers: {
    Authorization: "Bearer mk_...",
    "Mcp-Tool-Profile": "minimal",
  },
}
```

## Penanganan Error

```typescript
try {
  const result = await client.callTool({ name: "memory_recall", arguments: {} });
  if (result.isError) {
    console.error("Tool error:", result.content);
  } else {
    console.log("Success:", result.content);
  }
} catch (err) {
  console.error("MCP error:", err);
}
```

## Kasus Penggunaan

- **Asisten AI khusus** — bangun agen Anda sendiri dengan memori persisten
- **Otomasi alur kerja** — rangkai alat Synapse dalam alur kerja khusus
- **Pipeline data** — ekstrak memori, transformasi, muat di tempat lain
- **Dashboard pemantauan** — tampilkan statistik memori, riwayat chat, tugas

## Langkah Berikutnya

- [Spesifikasi MCP](https://spec.modelcontextprotocol.io)
- [Repo Synapse MCP](https://gitlab.com/schaefer-services/synapse-mcp)
- [Ikhtisar API](/docs/api/overview)