Integration

Mammouth AI integration

Mammouth AI gives one OpenAI-compatible API to about a hundred models from several providers (GPT, Claude, Gemini, Mistral, DeepSeek, Grok, Llama and more). Generate chat replies (with tool calling, JSON output, image input or image generation where the model supports it), create text embeddings, and look up every model's id, limits, capabilities, per-token price and deprecation date. Calls are billed per token from the account's API credits (subscribers get monthly credits; credits can also be bought alone). Left out: streaming, the legacy text-completion route, the OpenAI Responses API routes, the proxy's own health routes and per-key spend tracking, whose answer is undocumented. Authentication is an API key created in the Mammouth API settings, sent as a Bearer token.

Connect Mammouth AI How integrations work

Ask it in chat

Say what should happen.
The workflow builds itself.

When this happens, do that in Mammouth AI.Built from the 6 Mammouth AI tools below, on the connection you add once.

What you can do with Mammouth AI

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.

Each badge shows the default agent permission of an endpoint (allowed: an agent calls it without asking; ask first: you are asked before an agent calls it, when the agent or chat asks permission for sensitive actions; never: no agent may call it), which every user can change endpoint by endpoint in their credential settings.

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

Model, 2 operations

list_model_detailsList model detailsGETAgents: ask firstLists each model's detailed capabilities and pricing: underlying provider route, mode, token limits, per-token prices (cached input included), supported OpenAI parameters and supports_* flags. Needs no API key.
list_modelsList modelsGETAgents: ask firstLists every model the Mammouth API serves: its id (the value to pass as model), input and output token limits and price per input and output token in US dollars. Needs no API key.

Chat completion, 1 operation

create_chat_completionCreate chat completionPOSTAgents: ask firstGenerates a reply from the chosen model in the OpenAI chat format: pass model and messages; the text is in choices[0].message.content. Billed per input and output token at the model's rate (see list_models).

Embedding, 1 operation

create_embeddingsCreate embeddingsPOSTAgents: ask firstTurns texts into embedding vectors for semantic search or clustering: one vector per input, in the same order. Billed per input token at the model's rate (see list_models).

Model deprecation, 1 operation

list_model_deprecationsList model deprecationsGETAgents: ask firstLists the served models that have a known deprecation date, in three lists: already deprecated (calls may fail at any time), imminent (within warn_within_days) and upcoming.

Model group, 1 operation

list_model_groupsList model groupsGETAgents: ask firstLists the model groups the API serves (each name is a model id for create_chat_completion or create_embeddings), with providers, token limits, per-token prices and supported parameters.

Use Mammouth AI from Claude Code, Cursor or Codex

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

Create your workspace
Sign up free. Nothing to install.
Connect Mammouth AI once
Add your Mammouth AI 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.