{"title":"Membangun Klien MCP Khusus","slug":"custom-client","category":"mcp","summary":"Hubungkan ke Synapse MCP server dari aplikasi Anda sendiri menggunakan MCP SDK.","audience":["human","llm"],"tags":["mcp","custom","sdk","development"],"difficulty":"advanced","updated":"2026-06-27","word_count":156,"read_minutes":1,"lang":"id","translated":true,"requested_lang":"id","content_markdown":"\n# Membangun Klien MCP Khusus\n\nJika Anda membangun aplikasi LLM Anda sendiri, Anda dapat terhubung ke Synapse\nMCP server langsung menggunakan SDK MCP resmi. Ini memberikan aplikasi Anda\nakses ke semua 79 alat Synapse.\n\n## SDK\n\n| Bahasa | Paket |\n|----------|---------|\n| TypeScript/JavaScript | `@modelcontextprotocol/sdk` |\n| Python | `mcp` |\n\n## Contoh TypeScript\n\n### Pasang\n\n```bash\nnpm install @modelcontextprotocol/sdk\n```\n\n### Hubungkan via stdio\n\n```typescript\nimport { Client } from \"@modelcontextprotocol/sdk/client/index.js\";\nimport { StdioClientTransport } from \"@modelcontextprotocol/sdk/client/stdio.js\";\n\nconst transport = new StdioClientTransport({\n command: \"npx\",\n args: [\"-y\", \"synapse-mcp-api@latest\"],\n env: {\n SYNAPSE_MIND_KEY: process.env.SYNAPSE_MIND_KEY!,\n SYNAPSE_URL: \"https://synapse.schaefer.zone\",\n },\n});\n\nconst client = new Client(\n { name: \"my-app\", version: \"1.0.0\" },\n { capabilities: {} }\n);\n\nawait client.connect(transport);\n\n// List all available tools\nconst { tools } = await client.listTools();\nconsole.log(`Available tools: ${tools.length}`);\nfor (const tool of tools) {\n console.log(`- ${tool.name}: ${tool.description}`);\n}\n\n// Call a tool\nconst result = await client.callTool({\n name: \"memory_recall\",\n arguments: {},\n});\nconsole.log(result.content);\n\n// Store a memory\nawait client.callTool({\n name: \"memory_store\",\n arguments: {\n category: \"fact\",\n key: \"custom_client_test\",\n content: \"Built a custom MCP client\",\n tags: [\"test\", \"mcp\"],\n priority: \"normal\",\n },\n});\n\nawait client.close();\n```\n\n### Hubungkan via HTTP/SSE (remote)\n\n```typescript\nimport { Client } from \"@modelcontextprotocol/sdk/client/index.js\";\nimport { SSEClientTransport } from \"@modelcontextprotocol/sdk/client/sse.js\";\n\nconst transport = new SSEClientTransport(\n new URL(\"https://synapse-mcp.schaefer.zone/sse\"),\n {\n requestInit: {\n headers: {\n Authorization: `Bearer ${process.env.SYNAPSE_MIND_KEY}`,\n },\n },\n }\n);\n\nconst client = new Client(\n { name: \"my-app\", version: \"1.0.0\" },\n { capabilities: {} }\n);\n\nawait client.connect(transport);\n// ... use as above\n```\n\n## Contoh Python\n\n### Pasang\n\n```bash\npip install mcp\n```\n\n### Hubungkan via stdio\n\n```python\nfrom mcp import ClientSession, StdioServerParameters\nfrom mcp.client.stdio import stdio_client\n\nserver_params = StdioServerParameters(\n command=\"npx\",\n args=[\"-y\", \"synapse-mcp-api@latest\"],\n env={\n \"SYNAPSE_MIND_KEY\": \"mk_YOUR_KEY\",\n \"SYNAPSE_URL\": \"https://synapse.schaefer.zone\",\n },\n)\n\nasync with stdio_client(server_params) as (read, write):\n async with ClientSession(read, write) as session:\n await session.initialize()\n\n # List tools\n tools = await session.list_tools()\n print(f\"Available tools: {len(tools.tools)}\")\n\n # Call a tool\n result = await session.call_tool(\"memory_recall\", {})\n print(result.content)\n\n # Store a memory\n await session.call_tool(\"memory_store\", {\n \"category\": \"fact\",\n \"key\": \"python_client_test\",\n \"content\": \"Built a Python MCP client\",\n \"tags\": [\"test\", \"mcp\", \"python\"],\n \"priority\": \"normal\",\n })\n```\n\n## Tool Profiles\n\nSaat menghubungkan, Anda dapat meminta tool profile spesifik melalui header\n`Mcp-Tool-Profile` (HTTP/SSE) atau env var `MCP_PROFILE` (stdio):\n\n```typescript\n// stdio: set env var\nenv: {\n SYNAPSE_MIND_KEY: \"mk_...\",\n MCP_PROFILE: \"minimal\", // 8 tools instead of 119\n}\n\n// HTTP/SSE: set header\nrequestInit: {\n headers: {\n Authorization: \"Bearer mk_...\",\n \"Mcp-Tool-Profile\": \"minimal\",\n },\n}\n```\n\n## Penanganan Error\n\n```typescript\ntry {\n const result = await client.callTool({ name: \"memory_recall\", arguments: {} });\n if (result.isError) {\n console.error(\"Tool error:\", result.content);\n } else {\n console.log(\"Success:\", result.content);\n }\n} catch (err) {\n console.error(\"MCP error:\", err);\n}\n```\n\n## Kasus Penggunaan\n\n- **Asisten AI khusus** — bangun agen Anda sendiri dengan memori persisten\n- **Otomasi alur kerja** — rangkai alat Synapse dalam alur kerja khusus\n- **Pipeline data** — ekstrak memori, transformasi, muat di tempat lain\n- **Dashboard pemantauan** — tampilkan statistik memori, riwayat chat, tugas\n\n## Langkah Berikutnya\n\n- [Spesifikasi MCP](https://spec.modelcontextprotocol.io)\n- [Repo Synapse MCP](https://gitlab.com/schaefer-services/synapse-mcp)\n- [Ikhtisar API](/docs/api/overview)\n","content_html":"

Membangun Klien MCP Khusus

\n

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

\n

SDK

\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n
BahasaPaket
TypeScript/JavaScript@modelcontextprotocol/sdk
Pythonmcp
\n

Contoh TypeScript

\n

Pasang

\n
npm install @modelcontextprotocol/sdk

Hubungkan via stdio

\n
import { Client } from "@modelcontextprotocol/sdk/client/index.js";\nimport { StdioClientTransport } from "@modelcontextprotocol/sdk/client/stdio.js";\n\nconst transport = new StdioClientTransport({\n  command: "npx",\n  args: ["-y", "synapse-mcp-api@latest"],\n  env: {\n    SYNAPSE_MIND_KEY: process.env.SYNAPSE_MIND_KEY!,\n    SYNAPSE_URL: "https://synapse.schaefer.zone",\n  },\n});\n\nconst client = new Client(\n  { name: "my-app", version: "1.0.0" },\n  { capabilities: {} }\n);\n\nawait client.connect(transport);\n\n// List all available tools\nconst { tools } = await client.listTools();\nconsole.log(`Available tools: ${tools.length}`);\nfor (const tool of tools) {\n  console.log(`- ${tool.name}: ${tool.description}`);\n}\n\n// Call a tool\nconst result = await client.callTool({\n  name: "memory_recall",\n  arguments: {},\n});\nconsole.log(result.content);\n\n// Store a memory\nawait client.callTool({\n  name: "memory_store",\n  arguments: {\n    category: "fact",\n    key: "custom_client_test",\n    content: "Built a custom MCP client",\n    tags: ["test", "mcp"],\n    priority: "normal",\n  },\n});\n\nawait client.close();

Hubungkan via HTTP/SSE (remote)

\n
import { Client } from "@modelcontextprotocol/sdk/client/index.js";\nimport { SSEClientTransport } from "@modelcontextprotocol/sdk/client/sse.js";\n\nconst transport = new SSEClientTransport(\n  new URL("https://synapse-mcp.schaefer.zone/sse"),\n  {\n    requestInit: {\n      headers: {\n        Authorization: `Bearer ${process.env.SYNAPSE_MIND_KEY}`,\n      },\n    },\n  }\n);\n\nconst client = new Client(\n  { name: "my-app", version: "1.0.0" },\n  { capabilities: {} }\n);\n\nawait client.connect(transport);\n// ... use as above

Contoh Python

\n

Pasang

\n
pip install mcp

Hubungkan via stdio

\n
from mcp import ClientSession, StdioServerParameters\nfrom mcp.client.stdio import stdio_client\n\nserver_params = StdioServerParameters(\n    command="npx",\n    args=["-y", "synapse-mcp-api@latest"],\n    env={\n        "SYNAPSE_MIND_KEY": "mk_YOUR_KEY",\n        "SYNAPSE_URL": "https://synapse.schaefer.zone",\n    },\n)\n\nasync with stdio_client(server_params) as (read, write):\n    async with ClientSession(read, write) as session:\n        await session.initialize()\n\n        # List tools\n        tools = await session.list_tools()\n        print(f"Available tools: {len(tools.tools)}")\n\n        # Call a tool\n        result = await session.call_tool("memory_recall", {})\n        print(result.content)\n\n        # Store a memory\n        await session.call_tool("memory_store", {\n            "category": "fact",\n            "key": "python_client_test",\n            "content": "Built a Python MCP client",\n            "tags": ["test", "mcp", "python"],\n            "priority": "normal",\n        })

Tool Profiles

\n

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

\n
// stdio: set env var\nenv: {\n  SYNAPSE_MIND_KEY: "mk_...",\n  MCP_PROFILE: "minimal",  // 8 tools instead of 119\n}\n\n// HTTP/SSE: set header\nrequestInit: {\n  headers: {\n    Authorization: "Bearer mk_...",\n    "Mcp-Tool-Profile": "minimal",\n  },\n}

Penanganan Error

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

Kasus Penggunaan

\n\n

Langkah Berikutnya

\n\n","urls":{"html":"/docs/mcp/custom-client","text":"/docs/mcp/custom-client?format=text","json":"/docs/mcp/custom-client?format=json","llm":"/docs/mcp/custom-client?format=llm"},"translations_available":["en","zh","hi","es","fr","ar","pt","ru","ja","de","it","ko","nl","pl","tr","sv","vi","th","id","uk"]}