Einen Custom-MCP-Client bauen
Mit dem Synapse-MCP-Server aus eigener Anwendung über das MCP-SDK verbinden.
Einen Custom-MCP-Client bauen
Wenn du deine eigene LLM-Anwendung baust, kannst du dich direkt über das offizielle MCP-SDK mit dem Synapse-MCP-Server verbinden. So erhält deine App Zugriff auf alle 79 Synapse-Tools.
SDKs
| Sprache | Paket |
|---|---|
| TypeScript/JavaScript | @modelcontextprotocol/sdk |
| Python | mcp |
TypeScript-Beispiel
Installation
npm install @modelcontextprotocol/sdkVia stdio verbinden
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();Via HTTP/SSE verbinden (Remote)
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 abovePython-Beispiel
Installation
pip install mcpVia stdio verbinden
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-Profile
Beim Verbinden kannst du ein spezifisches Tool-Profil über den
Mcp-Tool-Profile-Header (HTTP/SSE) oder die MCP_PROFILE-Env-Var (stdio)
anfordern:
// 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",
},
}Fehlerbehandlung
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);
}Anwendungsfälle
- Custom-AI-Assistenten — eigenen Agenten mit persistentem Memory bauen
- Workflow-Automatisierung — Synapse-Tools in Custom-Workflows verketten
- Data-Pipelines — Memories extrahieren, transformieren, woanders laden
- Monitoring-Dashboards — Memory-Stats, Chat-Verlauf, Tasks anzeigen