DeepInfra MCP by usefulapi

by usefulapi.io · remote · no sign-in to list tools · v1.16.3 · published by io.usefulapi

Run DeepInfra inference, list models and read account rate limits.

Deletes · 2

Compare Registry entry

18 tools: 2 can delete or cancel things and 16 only read.

Scanned Oct 21, 2026

Deletes or cancels2Claude Code: deny: see these tools
Can't be undone0Claude Code: ask
Changes things0Claude Code: ask
Only reads16Claude Code: allow: see these tools

No check matched anything in the tool definitions. No finding is not a safety guarantee. How the checks work.

claude mcp add --transport http deepinfra https://deepinfra.usefulapi.io/mcp

Tools

Open a tool for its reasons and full description. Descriptions are the publisher's own words, shown as they are.

18 tools

Deletes or cancels 2Removes, cancels or revokes something.Claude Code: deny

deepinfra_start_deploymentStart (resume) a dedicated deployment.No findings
Why it is in this group
- The name "deepinfra_start_deployment" says "start": a word for a change.
- The server marks it destructive (destructiveHint: true).
Description, as the server wrote it
Start (resume) a dedicated deployment. WARNING: this resumes a dedicated deployment and may incur GPU charges while it runs. DeepInfra REST: POST /deploy/{deploy_id}/start.
Annotations the server declares
- title: Start deployment
- destructiveHint: true
deepinfra_stop_deploymentStop (pause) a running dedicated deployment.No findings
Why it is in this group
- The name "deepinfra_stop_deployment" says "stop": a word for a change.
- The server marks it destructive (destructiveHint: true).
Description, as the server wrote it
Stop (pause) a running dedicated deployment. This halts inference and stops accruing GPU charges for it. DeepInfra REST: POST /deploy/{deploy_id}/stop.
Annotations the server declares
- title: Stop deployment
- destructiveHint: true

Only reads 16Looks things up and changes nothing.Claude Code: allow

deepinfra_get_accountGet the current DeepInfra account / user details (identity, email, quotas).No findings
Why it is in this group
- The name "deepinfra_get_account" says "get": a word for reading.
Description, as the server wrote it
Get the current DeepInfra account / user details (identity, email, quotas). DeepInfra REST: GET /v1/me.
Annotations the server declares
- title: Get account
- readOnlyHint: true
deepinfra_get_deploymentGet one dedicated deployment by id (config + current status).No findings
Why it is in this group
- The name "deepinfra_get_deployment" says "get": a word for reading.
Description, as the server wrote it
Get one dedicated deployment by id (config + current status). DeepInfra REST: GET /deploy/{deploy_id}.
Annotations the server declares
- title: Get deployment
- readOnlyHint: true
deepinfra_get_deployment_statsGet time-series stats (throughput / latency / replicas) for a dedicated deployment.No findings
Why it is in this group
- The name "deepinfra_get_deployment_stats" says "get": a word for reading.
Description, as the server wrote it
Get time-series stats (throughput / latency / replicas) for a dedicated deployment. DeepInfra REST: GET /deploy/{deploy_id}/stats2.
Annotations the server declares
- title: Get deployment stats
- readOnlyHint: true
deepinfra_get_gpu_availabilityGet GPU availability for LLM deployments (which hardware can currently be provisioned).No findings
Why it is in this group
- The name "deepinfra_get_gpu_availability" says "get": a word for reading.
Description, as the server wrote it
Get GPU availability for LLM deployments (which hardware can currently be provisioned). DeepInfra REST: GET /deploy/llm/gpu_availability.
Annotations the server declares
- title: Get GPU availability
- readOnlyHint: true
deepinfra_get_hardwareGet the hardware options / GPU configuration available for a given model.No findings
Why it is in this group
- The name "deepinfra_get_hardware" says "get": a word for reading.
Description, as the server wrote it
Get the hardware options / GPU configuration available for a given model. DeepInfra REST: GET /v2/hardware.
Annotations the server declares
- title: Get hardware
- readOnlyHint: true
deepinfra_get_live_metricsGet global live inference metrics across the account (real-time throughput / activity).No findings
Why it is in this group
- The name "deepinfra_get_live_metrics" says "get": a word for reading.
Description, as the server wrote it
Get global live inference metrics across the account (real-time throughput / activity). DeepInfra REST: GET /v1/metrics/live.
Annotations the server declares
- title: Get live metrics
- readOnlyHint: true
deepinfra_get_modelGet one model's catalog entry (pricing, context length, capabilities).No findings
Why it is in this group
- The name "deepinfra_get_model" says "get": a word for reading.
Description, as the server wrote it
Get one model's catalog entry (pricing, context length, capabilities). DeepInfra REST: GET /models/{model_name}.
Annotations the server declares
- title: Get model
- readOnlyHint: true
deepinfra_get_rate_limitGet the account's current rate limits (per-model / per-endpoint request and token limits).No findings
Why it is in this group
- The name "deepinfra_get_rate_limit" says "get": a word for reading.
Description, as the server wrote it
Get the account's current rate limits (per-model / per-endpoint request and token limits). DeepInfra REST: GET /v1/me/rate_limit.
Annotations the server declares
- title: Get rate limit
- readOnlyHint: true
deepinfra_get_usageGet spend / usage for a billing period.No findings
Why it is in this group
- The name "deepinfra_get_usage" says "get": a word for reading.
Description, as the server wrote it
Get spend / usage for a billing period. DeepInfra REST: GET /payment/usage.
Annotations the server declares
- title: Get usage
- readOnlyHint: true
deepinfra_get_usage_rentGet GPU rental (dedicated hardware) usage for a time range.No findings
Why it is in this group
- The name "deepinfra_get_usage_rent" says "get": a word for reading.
Description, as the server wrote it
Get GPU rental (dedicated hardware) usage for a time range. DeepInfra REST: GET /payment/usage/rent.
Annotations the server declares
- title: Get GPU rental usage
- readOnlyHint: true
deepinfra_get_usage_tokensGet per-model token usage for a period.No findings
Why it is in this group
- The name "deepinfra_get_usage_tokens" says "get": a word for reading.
Description, as the server wrote it
Get per-model token usage for a period. DeepInfra REST: GET /payment/usage/tokens.
Annotations the server declares
- title: Get token usage
- readOnlyHint: true
deepinfra_list_api_tokensList the account's API tokens (metadata only, not secret values).No findings
Why it is in this group
- The name "deepinfra_list_api_tokens" says "list": a word for reading.
Description, as the server wrote it
List the account's API tokens (metadata only, not secret values). DeepInfra REST: GET /v1/api-tokens.
Annotations the server declares
- title: List API tokens
- readOnlyHint: true
deepinfra_list_deploymentsList the account's dedicated deployments.No findings
Why it is in this group
- The name "deepinfra_list_deployments" says "list": a word for reading.
Description, as the server wrote it
List the account's dedicated deployments. DeepInfra REST: GET /deploy/list.
Annotations the server declares
- title: List deployments
- readOnlyHint: true
deepinfra_list_invoicesList billing invoices for the account.No findings
Why it is in this group
- The name "deepinfra_list_invoices" says "list": a word for reading.
Description, as the server wrote it
List billing invoices for the account. DeepInfra REST: GET /payment/invoices.
Annotations the server declares
- title: List invoices
- readOnlyHint: true
deepinfra_list_modelsList the DeepInfra model catalog (all available models).No findings
Why it is in this group
- The name "deepinfra_list_models" says "list": a word for reading.
Description, as the server wrote it
List the DeepInfra model catalog (all available models). DeepInfra REST: GET /models/list.
Annotations the server declares
- title: List models
- readOnlyHint: true
deepinfra_query_logsQuery inference request logs for a dedicated deployment over a time window.No findings
Why it is in this group
- The name "deepinfra_query_logs" says "query": a word for reading.
Description, as the server wrote it
Query inference request logs for a dedicated deployment over a time window. DeepInfra REST: GET /v1/logs/query.
Annotations the server declares
- title: Query logs
- readOnlyHint: true

This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.

Install

Pinned to version 1.16.3. Values in angle brackets are yours to fill in.

claude mcp add --transport http deepinfra https://deepinfra.usefulapi.io/mcp

Run in a terminal.

Claude Code permissions

Allow the reads, ask before a change, deny the deletes. Paste into .claude/settings.json.

.claude/settings.json

{
  "permissions": {
    "allow": [
      "mcp__deepinfra__deepinfra_get_account",
      "mcp__deepinfra__deepinfra_get_rate_limit",
      "mcp__deepinfra__deepinfra_list_api_tokens",
      "mcp__deepinfra__deepinfra_get_usage",
      "mcp__deepinfra__deepinfra_get_usage_tokens",
      "mcp__deepinfra__deepinfra_get_usage_rent",
      "mcp__deepinfra__deepinfra_list_invoices",
      "mcp__deepinfra__deepinfra_list_deployments",
      "mcp__deepinfra__deepinfra_get_deployment",
      "mcp__deepinfra__deepinfra_get_deployment_stats",
      "mcp__deepinfra__deepinfra_get_gpu_availability",
      "mcp__deepinfra__deepinfra_list_models",
      "mcp__deepinfra__deepinfra_get_model",
      "mcp__deepinfra__deepinfra_get_hardware",
      "mcp__deepinfra__deepinfra_query_logs",
      "mcp__deepinfra__deepinfra_get_live_metrics"
    ],
    "ask": [],
    "deny": [
      "mcp__deepinfra__deepinfra_start_deployment",
      "mcp__deepinfra__deepinfra_stop_deployment"
    ]
  }
}

Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. It assumes the server is installed as deepinfra. Review it before you use it.

Keep track

Get told when this server's tools change: a new tool, a new description, a new class.

https://anlyon.dev/servers/io.usefulapi/deepinfra/changes.xml

An Atom feed. Works in any feed reader or Slack's RSS app.

Anlyon alternative

2 of these tools change something. Run those as governed actions.

Declare what an action changes, and Anlyon puts it under a shared limit, binds every approval to the exact request, and grades the outcome. It works on any HTTPS API you can describe as an action.

Anlyon does not run, proxy or govern this MCP server. A tool your own code calls directly is not routed through Anlyon and is not governed by it.

Import an OpenAPI spec →

Compare with other servers for the same product.

Source: MCP Registry · repository. Synced Oct 21, 2026, 19:23 UTC.

For agents: Markdown · JSON · report this listing