Tumia CleanTextLab na Strands Agents (MCP)

Strands Agents hurahisisha kujenga mawakala kwa Python. CleanTextLab huleta zana za deterministic (formatting, cleaning, converting) kupitia MCP ili wakala wako aandike matokeo sahihi bila kuyarudia.

Mwongozo huu unaonyesha chaguo mbili:

Local MCP (stdio) kwa npx cleantextlab-mcp
Hosted MCP (SSE) kwa https://cleantextlab.com/api/mcp/sse

Mahitaji

Python 3.10+
API key ya CleanTextLab Pro
Strands Agents imewekwa

python -m venv .venv
source .venv/bin/activate
pip install strands-agents

Chaguo A: Local MCP via npx (inapendekezwa kwa local dev)

from strands import Agent
from strands.tools.mcp import MCPClient
from mcp import stdio_client, StdioServerParameters

cleantextlab = MCPClient(
    lambda: stdio_client(
        StdioServerParameters(
            command="npx",
            args=["-y", "cleantextlab-mcp"],
            env={"CLEANTEXTLAB_API_KEY": "ctl_live_YOUR_KEY"},
        )
    )
)

with cleantextlab:
    agent = Agent(tools=cleantextlab.list_tools_sync())
    agent("Remove line breaks from: Hello\\nworld")

Chaguo B: Hosted MCP (SSE)

from strands import Agent
from strands.tools.mcp import MCPClient
from mcp import sse_client, SSEServerParameters

cleantextlab = MCPClient(
    lambda: sse_client(
        SSEServerParameters(
            url="https://cleantextlab.com/api/mcp/sse",
            headers={"x-api-key": "ctl_live_YOUR_KEY"},
        )
    )
)

with cleantextlab:
    agent = Agent(tools=cleantextlab.list_tools_sync())
    agent("Generate an ASCII tree from: src/app/page.tsx")

Kwa nini MCP kwa mawakala?

Matokeo ya deterministic kwa kazi za formatting
Token chache kwa kuhamisha kazi nzito
Zana zinazotumika tena kwenye workflows za mawakala

Hatua zinazofuata

Uko tayari kuanza? Pata API key na uunganishe CleanTextLab na mawakala wako.