Integration

NVIDIA NIM integration

NVIDIA NIM, the hosted model catalogue behind build.nvidia.com. Run any catalogue model through the OpenAI-compatible chat completions endpoint, build retrieval embeddings with the NeMo Retriever models, list the models your key can reach, and rerank candidate passages against a query. The hosted surface is intentionally narrow: only chat completions, embeddings and the model list live on the main host, and reranking sits on a separate one.

Connect NVIDIA NIM How integrations work

Ask it in chat

Say what should happen.
The workflow builds itself.

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

Common NVIDIA NIM use cases

embedding a document corpus for retrieval augmented generation
reordering vector search hits before building a grounding context
discovering which model ids a key can use before wiring a workflow
running an open weights model through a hosted endpoint without self-hosting
forcing a model to answer with a fixed JSON schema

What you can do with NVIDIA NIM

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

create_chat_completionCreate chat completionPOSTGenerates a model reply from a list of chat messages.

Embedding, 1 operation

create_embeddingCreate embeddingPOSTCreates embedding vectors for one or more texts.

Model, 1 operation

list_modelsList modelsGETLists the models available to the key.

Ranking, 1 operation

rerank_passagesRerank passagesPOSTReranks candidate passages by relevance to a query.

Use NVIDIA NIM from Claude Code, Cursor or Codex

Connect NVIDIA NIM in LiveContext, create an API key in Settings, then add the LiveContext MCP server to your client. Its NVIDIA NIM 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 NVIDIA NIM

Create your workspace
Sign up free. Nothing to install.
Connect NVIDIA NIM once
Add your NVIDIA NIM 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.

NVIDIA NIM integration FAQ

What can you do with the NVIDIA NIM integration?

LiveContext exposes 4 operations on NVIDIA NIM, covering chat completion, embedding, model and ranking. Common uses include embedding a document corpus for retrieval augmented generation, reordering vector search hits before building a grounding context and discovering which model ids a key can use before wiring a workflow.