NVIDIA NIM for your agents.
Connect NVIDIA NIM once and every agent you run inside Even (Claude Code, Codex, OpenCode, Even Agents) can use it: 5 curated tools, discovered on demand, with your key stored on your machine and every call going direct to NVIDIA NIM.
What agents can do with NVIDIA NIM
Curated for agents: the calls that matter, with schemas and descriptions written for tool use, not an endpoint dump.
nvidia-nim_chat_completionSend a chat completion request to an NVIDIA NIM model. `model` is the model id (e.g. meta/llama3-70b-instruct). `messages` is an array of {role, content} objects.
nvidia-nim_list_modelsList available models on NVIDIA NIM.
nvidia-nim_healthCheck the health of the NVIDIA NIM endpoint.
nvidia-nim_text_completionText completion (OpenAI-compatible). `model` is the model id; `prompt` is the input text.
nvidia-nim_create_embeddingCreate embeddings from text. `model` is an embedding NIM (e.g. nvidia/nv-embedqa-e5-v5); `input` is the text; `input_type` is query or passage (required by NVIDIA embedding models).
Connect it in a minute
The connect flow is agent-driven: Even opens the key page in its own browser and collects the key through a secure native field. It never passes through the chat.
- Paste the prompt below into any agent running inside Even, or click Connect in Even's catalog.
- Sign in to the NVIDIA API Catalog (build.nvidia.com).
- Select a model and click Get API Key.
- Copy the nvapi- key.
- Paste the key into Even's secure field. Even verifies it and your agents are live.
Connect NVIDIA NIM to Even: call connect_begin("nvidia-nim") on the even-connect MCP and walk me through it.
NVIDIA NIM runs chat completions on deployed models, lists available inference models, and creates text embeddings.
More Even Connect services
One MCP server, a handful of meta-tools, every service below. Agents search for the right tool at run time, so context stays lean.