Skip to main content

DeepAgents

Connect a DeepAgents agent to Civic using the langchain-mcp-adapters package, which bridges DeepAgents' tool interface with Civic's Streamable HTTP MCP transport.

Prerequisites​

Installation​

Using uv (recommended):

uv add deepagents langchain-mcp-adapters langchain-anthropic fastapi uvicorn python-dotenv

Or with pip:

pip install deepagents langchain-mcp-adapters langchain-anthropic fastapi uvicorn python-dotenv

Environment Variables​

# Your full Civic toolkit URL (include profile param for production agents)
CIVIC_URL=https://app.civic.com/hub/mcp?profile=your-toolkit&lock=true

# Civic token generated from app.civic.com → Install → MCP URL
CIVIC_TOKEN=your-civic-token

# API key for your chosen LLM provider
ANTHROPIC_API_KEY=your-anthropic-key   # or OPENAI_API_KEY, etc.
Get Your Credentials

How to generate a Civic token and configure toolkit URL parameters

Connecting to Civic​

Use MultiServerMCPClient to connect to the Civic MCP Hub during app startup, then pass the discovered tools to create_deep_agent:

import os
from contextlib import asynccontextmanager
from fastapi import FastAPI
from deepagents import create_deep_agent
from langchain_mcp_adapters.client import MultiServerMCPClient

mcp_client = None
agent = None

@asynccontextmanager
async def lifespan(app: FastAPI):
    global mcp_client, agent

    mcp_client = MultiServerMCPClient({
        "civic-nexus": {
            "transport": "streamable_http",
            "url": os.environ["CIVIC_URL"],
            "headers": {"Authorization": f"Bearer {os.environ['CIVIC_TOKEN']}"},
        }
    })

    tools = await mcp_client.get_tools()

    agent = create_deep_agent(
        model="anthropic:claude-sonnet-4-6",  # or "openai:gpt-4o", etc.
        tools=tools,
        system_prompt="You are a helpful assistant with access to calendar and email tools.",
    )

    yield

    await mcp_client.__aexit__(None, None, None)

app = FastAPI(lifespan=lifespan)

Running the Agent​

from fastapi import FastAPI
from pydantic import BaseModel

class ChatRequest(BaseModel):
    message: str
    thread_id: str = "default"

@app.post("/chat")
async def chat(request: ChatRequest):
    result = await agent.ainvoke(
        {"messages": [{"role": "user", "content": request.message}]},
        config={"configurable": {"thread_id": request.thread_id}},
    )
    return {"response": result["messages"][-1].content}

Start the server:

uv run uvicorn main:app --reload

Production Configuration​

Lock to a Toolkit​

For production agents, always lock to a specific toolkit using the profile and lock URL parameters:

CIVIC_URL=https://app.civic.com/hub/mcp?profile=your-production-toolkit&lock=true

When locked, the agent cannot switch toolkits or modify its own guardrails — preventing prompt injection attacks from escaping the defined tool scope.

Multi-Account Setup​

For organization accounts, include the accountId parameter:

CIVIC_URL=https://app.civic.com/hub/mcp?profile=support&accountId=org_abc123

Pre-load Skills​

Load specific Skills at session start using the skills parameter:

CIVIC_URL=https://app.civic.com/hub/mcp?profile=support&skills=escalation,canned-responses

Environment Variable Reference​

VariableDescription
CIVIC_URLFull Civic toolkit URL including profile and any URL parameters
CIVIC_TOKENCivic token from app.civic.com → Install → MCP URL
ANTHROPIC_API_KEYAPI key for your LLM provider (e.g., Anthropic, OpenAI)

Reference Implementation​

A complete reference implementation including a FastAPI server, streaming chat UI, and production patterns is available at:

github.com/civicteam/deepagents-reference-implementation-civic

Next Steps​

Agent Deployment

Production deployment guide: profile locking, URL params, authentication

Guardrails

Constrain what tools your DeepAgents agent can use

Audit Trail

Query what your agent did via Civic Chat

Get Credentials

Token generation and URL parameter reference