From 487b1cfac5fcd89d4c91f88903ef8b601da8269d Mon Sep 17 00:00:00 2001
From: Ian Hodge <ian@warp.dev>
Date: Wed, 17 Dec 2025 13:41:54 -0500
Subject: [PATCH] docs: add environment and config usage documentation

Add documentation for the config parameter including:
- environment_id for cloud environments
- model_id, name, and base_prompt options
- MCP server configuration examples

Link to Warp docs for environment setup instructions.

Co-Authored-By: Warp <agent@warp.dev>
---
 README.md | 58 +++++++++++++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 58 insertions(+)

diff --git a/README.md b/README.md
index 1db9ce1..725935a 100644
--- a/README.md
+++ b/README.md
@@ -38,6 +38,64 @@ response = client.agent.run(
 print(response.task_id)
 ```
 
+### Using environments and configuration
+
+You can configure the agent with a custom environment and other settings using the `config` parameter:
+
+```python
+from warp_sdk import WarpAPI
+
+client = WarpAPI()
+
+response = client.agent.run(
+    prompt="Fix the bug in auth.go",
+    config={
+        "environment_id": "your-environment-id",  # UID of a cloud environment
+        "model_id": "claude-sonnet-4",  # Optional: specify the LLM model
+        "name": "bug-fix-config",  # Optional: config name for traceability
+        "base_prompt": "You are a helpful coding assistant.",  # Optional: custom base prompt
+    },
+)
+print(response.task_id)
+```
+
+#### Configuration options
+
+The `config` parameter accepts the following fields:
+
+- `environment_id`: UID of a cloud environment to run the agent in. Environments define the Docker image, GitHub repositories, and setup commands for agent execution. See [Creating an Environment](https://docs.warp.dev/integrations/integrations-overview/integrations-and-environments#creating-an-environment) for setup instructions.
+- `model_id`: LLM model to use (uses workspace default if not specified)
+- `name`: Config name for searchability and traceability
+- `base_prompt`: Custom base prompt for the agent
+- `mcp_servers`: Map of MCP server configurations by name
+
+#### MCP server configuration
+
+You can configure MCP servers to extend the agent's capabilities:
+
+```python
+response = client.agent.run(
+    prompt="Check my GitHub issues",
+    config={
+        "environment_id": "your-environment-id",
+        "mcp_servers": {
+            "github": {
+                "warp_id": "your-shared-mcp-server-id",  # Reference a Warp shared MCP server
+            },
+            "custom-server": {
+                "command": "npx",
+                "args": ["-y", "@modelcontextprotocol/server-filesystem"],
+                "env": {"PATH": "/usr/local/bin"},
+            },
+            "remote-server": {
+                "url": "https://mcp.example.com/sse",
+                "headers": {"Authorization": "Bearer token"},
+            },
+        },
+    },
+)
+```
+
 While you can provide an `api_key` keyword argument,
 we recommend using [python-dotenv](https://pypi.org/project/python-dotenv/)
 to add `WARP_API_KEY="My API Key"` to your `.env` file