About DeepInfra MCP by usefulapi
DeepInfra MCP by usefulapi is a hosted MCP server for accessing DeepInfra account and inference services. It serves users who want to inspect models, usage and deployments or run inference from an MCP client, without a local install.
Key features
- 01Run DeepInfra inference
- 02List and inspect models
- 03Check account and rate limits
- 04Review usage, invoices and deployments
- 05Inspect GPU availability and live metrics
- 06Start or stop deployments
Use cases
- 01Run model inference through an MCP client
- 02Check account usage and token consumption
- 03Review deployment status and logs
- 04Start or stop a deployment
MCP support
Exposes DeepInfra inference and account-management tools to MCP clients through a hosted endpoint. Users connect with their DeepInfra credentials.
Configuration
Remote servers need no local install. Pick your client, then copy the config or install in one click.
https://deepinfra.usefulapi.io/mcpclaude mcp add --transport http io-usefulapi-deepinfra https://deepinfra.usefulapi.io/mcp{"mcpServers":{"io-usefulapi-deepinfra":{"type":"http","url":"https://deepinfra.usefulapi.io/mcp"}}}Open in Cursor{"servers":{"io-usefulapi-deepinfra":{"type":"http","url":"https://deepinfra.usefulapi.io/mcp"}}}Open in VS Code{"mcpServers":{"io-usefulapi-deepinfra":{"type":"http","url":"https://deepinfra.usefulapi.io/mcp"}}}{"mcpServers":{"io-usefulapi-deepinfra":{"serverUrl":"https://deepinfra.usefulapi.io/mcp"}}}Run commands in a terminal; paste JSON into the client’s MCP config and restart. Servers that need sign-in will prompt on first connect.
Tools
18| Parameter | Type | Required | Description |
|---|---|---|---|
| checklist | boolean | No | Include the onboarding checklist state in the response. |
Details
From the project READMEDeepInfra MCP by usefulapi
Run DeepInfra inference, list models and read account rate limits. Hosted, no local install.
Live endpoint: https://deepinfra.usefulapi.io/mcp · Homepage: https://usefulapi.io
Connect
- Claude (claude.ai, Desktop): open Customize → Connectors, click + Add → Add custom connector, and paste
https://deepinfra.usefulapi.io/mcp. - Claude Code:
claude mcp add --transport http deepinfra https://deepinfra.usefulapi.io/mcp, then run/mcpto log in. - VS Code: Add to VS Code.
- Cursor and other clients: add the URL as a remote MCP server:
{
"mcpServers": {
"deepinfra": {
"url": "https://deepinfra.usefulapi.io/mcp"
}
}
}
Add only the URL. Do not add an Authorization header or an API key to the client config: the server signs you in with OAuth, and the login page asks for your DeepInfra credentials.
Step-by-step setup, where to find your credentials, and FAQ: https://usefulapi.io/deepinfra/
On first connect you'll paste your DeepInfra credentials. They are validated, stored per-user, and scoped to you — no keys in config files.
Tools
| Tool | Type | What it does |
|---|---|---|
deepinfra_get_account | read | Get account |
deepinfra_get_rate_limit | read | Get rate limit |
deepinfra_list_api_tokens | read | List API tokens |
deepinfra_get_usage | read | Get usage |
deepinfra_get_usage_tokens | read | Get token usage |
deepinfra_get_usage_rent | read | Get GPU rental usage |
deepinfra_list_invoices | read | List invoices |
deepinfra_list_deployments | read | List deployments |
deepinfra_get_deployment | read | Get deployment |
deepinfra_get_deployment_stats | read | Get deployment stats |
deepinfra_get_gpu_availability | read | Get GPU availability |
deepinfra_list_models | read | List models |
deepinfra_get_model | read | Get model |
deepinfra_get_hardware | read | Get hardware |
deepinfra_query_logs | read | Query logs |
deepinfra_get_live_metrics | read | Get live metrics |
deepinfra_start_deployment | write | Start deployment |
deepinfra_stop_deployment | write | Stop deployment |
deepinfra_usage_status | meta | Usage status (free-tier meter) |
deepinfra_request_feature | meta | Request a missing feature |
deepinfra_upgrade | meta | Upgrade to Pro (unlimited*) |
deepinfra_cancel_subscription | meta | Cancel the Pro subscription |
read tools are read-only; write tools mutate data (clients should confirm them); meta tools report usage, manage your subscription or send a feature request.
Pricing
| Plan | Price | Limit |
|---|---|---|
| Free | $0 | 50 tool calls / month |
| Pro | $9/mo or $90/yr (2 months free) | Unlimited* |
*Pro has a fair use limit of 10,000 tool calls a month on this server. For more, write to [email protected].
Pro covers this server only. Subscribe with deepinfra_upgrade (it returns a Stripe Checkout link). Cancel any time with deepinfra_cancel_subscription: Pro continues to the end of the paid period, with no refund for the current period, and running deepinfra_upgrade before then undoes the cancel. Or write to [email protected].
License
MIT
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.