MCP (gateway)

When MCP tool calls trigger LLM completions, route those LLM calls through the Respan gateway to use 250+ models from different providers. Only your RESPAN_API_KEY is needed — no separate provider keys required.

Setup

$
pip install respan-ai openinference-instrumentation-mcp mcp

$
export RESPAN_API_KEY="YOUR_RESPAN_API_KEY"

1
import os
2
from openai import OpenAI
3
4
llm_client = OpenAI(
5
    api_key=os.environ["RESPAN_API_KEY"],
6
    base_url="https://api.respan.ai/api",
7
)
8
9
response = llm_client.chat.completions.create(
10
    model="gpt-4.1-nano",
11
    messages=[{"role": "user", "content": "Use my MCP tool to fetch data."}],
12
)
13
print(response.choices[0].message.content)

Switch models

Change the model parameter on your LLM client to use 250+ models from different providers through the same gateway.

1
response = llm_client.chat.completions.create(model="claude-sonnet-4-5-20250929", messages=messages)
2
response = llm_client.chat.completions.create(model="gemini-2.5-flash", messages=messages)

See the full model list.