1-Line BASE_URL & MCP Onboarding

Connect Claude Code, Codex, OpenCode, Cursor, or any SDK.

Swap a single base URL environment variable to route outbound LLM calls through ContextShim, or attach https://contextshim.com/mcp so your agent can inspect and manage wire rules autonomously.

Claude Code (ANTHROPIC_BASE_URL)

ANTHROPIC_BASE_URL=https://contextshim.com claude

OpenAI Codex CLI (OPENAI_BASE_URL)

OPENAI_BASE_URL=https://contextshim.com/v1 codex

OpenCode CLI (Cloud Ollama + MCP)

opencode mcp add --global --url https://contextshim.com/mcp contextshim

Cursor IDE (Custom OpenAI Base URL)

https://contextshim.com/v1

Cloud Ollama SDK (OLLAMA_HOST)

OLLAMA_HOST=https://contextshim.com

Streamable HTTP MCP Config (mcp.json)

{
  "mcpServers": {
    "contextshim": {
      "type": "streamable-http",
      "url": "https://contextshim.com/mcp"
    }
  }
}

Python (OpenAI & Anthropic SDKs)

from openai import OpenAI

client = OpenAI(
    base_url="https://contextshim.com/v1",
    api_key="cshim_live_replace_me",
)
res = client.chat.completions.create(
    model="glm-5.3-flash",
    messages=[{"role": "user", "content": "contextshim:ping"}],
)
print(res.choices[0].message.content)

TypeScript / Node.js (@anthropic-ai/sdk)

import Anthropic from "@anthropic-ai/sdk";

const anthropic = new Anthropic({
  baseURL: "https://contextshim.com",
  apiKey: process.env.CSHIM_API_KEY ?? "cshim_live_replace_me",
});
const msg = await anthropic.messages.create({
  model: "claude-sonnet-4-5",
  max_tokens: 512,
  messages: [{ role: "user", content: "contextshim:ping" }],
});