Integration

Cody integration

Cody by Sourcegraph - AI coding assistant internal API. Provides LLM chat completions (streaming and non-streaming) and code autocomplete through Sourcegraph's internal completions endpoints. Authenticated via Sourcegraph access tokens. Note: This is an internal API documented from the official Sourcegraph OpenAPI specification (sourcegraph/openapi); it is not a public API intended for third-party consumption.

Connect Cody How integrations work

Ask it in chat

Say what should happen.
The workflow builds itself.

When this happens, do that in Cody.Built from the 4 Cody tools below, on the connection you add once.

Common Cody use cases

IDE code completion
AI-assisted coding chat
checking available features
discovering available models
model selection
client initialization
real-time coding assistance
streaming code explanations
feature gate checking
boilerplate generation

What you can do with Cody

Each of these is one operation on one endpoint, available both as a workflow step and as a tool an AI agent can call on its own. Nothing bundles several operations into one action, so what a run did stays readable afterwards.

Most endpoints run on the free plan. A few, mainly the ones that publish on your behalf, need a paid plan.

Chat completion, 1 operation

chat_completionsChat completionsPOSTSends messages to Sourcegraph for streaming LLM chat completions. Returns AI-powered responses via SSE stream.

Client config, 1 operation

get_client_configGet client configGETRetrieves Cody client configuration for the authenticated user including enabled features and API version support.

Code completion, 1 operation

code_completionsCode completionsPOSTGenerates code completions as a non-streaming response. Used for inline IDE autocomplete.

Model catalog, 1 operation

get_supported_modelsGet supported modelsGETRetrieves the catalog of supported LLM models including providers, capabilities, and default model selections.

Use Cody from Claude Code, Cursor or Codex

Connect Cody in LiveContext, create an API key in Settings, then add the LiveContext MCP server to your client. Its Cody operations become tools the client can call, next to every other integration you connected.

Claude Code

claude mcp add --transport http livecontext https://livecontext.ai/mcp --header "X-API-Key: YOUR_API_KEY"

Codex (~/.codex/config.toml)

[mcp_servers.livecontext]
url = "https://livecontext.ai/mcp"

[mcp_servers.livecontext.http_headers]
"X-API-Key" = "YOUR_API_KEY"

Cursor, Claude Desktop and other JSON configs

{
  "mcpServers": {
    "livecontext": {
      "type": "http",
      "url": "https://livecontext.ai/mcp",
      "headers": {
        "X-API-Key": "YOUR_API_KEY"
      }
    }
  }
}

Set up the MCP server step by step

How to connect Cody

Create your workspace
Sign up free. Nothing to install.
Connect Cody once
Add your Cody connection in Settings. Every tool from this integration reuses it, and secrets are encrypted at rest and visible only to you.
Describe the job in chat
The workflow builds itself in front of you and picks the endpoints it needs. Drag the steps yourself on the canvas whenever you would rather be explicit.

Cody integration FAQ

What can you do with the Cody integration?

LiveContext exposes 4 operations on Cody, covering chat completion, client config, code completion and model catalog. Common uses include IDE code completion, AI-assisted coding chat and checking available features.