AI & Machine Learning

aihubmix.com

Provides access to AIHubMix model catalog, pricing, credits, and chat completions via API tools.

2 endpoints15 known toolsFirst detected August 30, 2026Last detected August 30, 2026

ENDPOINT 1

https://aihubmix.com/mcp

No auth detected

MCP server metadata

Name: aihubmix-mcp
Version: 0.7.0

Capabilities

tools.listChanged

Server instructions

AIHubMix MCP server: live model catalog (pricing, context windows, capabilities), account credits, docs search and a test-chat tool for the AIHubMix gateway (https://aihubmix.com). Use models-list / model-get to pick models from real-time data instead of training memory. credits-get, chat-send and image-generate require an AIHubMix API key (AIHUBMIX_API_KEY env in stdio mode, or "Authorization: Bearer <key>" header in HTTP mode). chat-send and image-generate consume credits; image generation can take minutes. Gateway endpoints fail over automatically (aihubmix.com → api.inferera.com, same backend) — never ask the user to switch regions or domains; an endpoint_note field appears on responses when a fallback endpoint served the request. Use ping for per-endpoint health when diagnosing. video-generate also consumes credits and can run for minutes. Account tools (account-get, keys-list, account-models, and the opt-in keys-create/update/delete) use a SEPARATE credential: the Access Key, via AIHUBMIX_ACCESS_KEY in stdio mode or the "X-Aihubmix-Access-Key" header in HTTP mode — not the sk- API key. The older AIHUBMIX_ACCESS_TOKEN / AIHUBMIX_TOKEN env names and the X-Aihubmix-Manage-Key header still work during migration. Key-admin write tools exist only when AIHUBMIX_ENABLE_KEY_ADMIN=1.

Known tools 12

ping

Health-check every configured gateway endpoint (with latency) and report which one is active.

Inferred read-only

models-list

Search the live AIHubMix model catalog with pricing (USD per 1K tokens), context window, modalities and features.

Inferred read-only

model-get

Fetch full details for a single model by exact model_id (pricing, full description, capabilities).

Inferred read-only

credits-get

Account balance for the calling API key: total quota, used and remaining (USD), plus key expiry.

Inferred read-only

chat-send

Send one non-streaming chat message to any AIHubMix model and get the reply with token usage and latency.

Potential side effects

image-generate

Generate image(s) across 23 models / 8 families.

Inferred read-only

video-generate

Generate a video (submits a task then polls until ready — can take several minutes).

Inferred read-only

docs-search

Search the official AIHubMix documentation index (docs.aihubmix.com) by keyword; returns page titles, URLs and summaries.

Inferred read-only

docs-get

Fetch one documentation page from docs.aihubmix.com as markdown (use URLs returned by docs-search).

Inferred read-only

account-get

Account-level profile and balance for the Access Key owner: username, group, total balance and used amount (USD), request count.

Inferred read-only

keys-list

List the account's API keys with status, remaining/used quota (USD), expiry and model/IP restrictions.

Inferred read-only

account-models

Models usable by THIS account's group (may differ from the public catalog in models-list).

Inferred read-only

CONNECT WITH APPROVAL

Client installation

Review this server and its permissions before adding it. Secret placeholders must be set locally.

Codex

~/.codex/config.toml

[mcp_servers.aihubmix-mcp]
url = "https://aihubmix.com/mcp"
enabled = true

Claude Code

.mcp.json

{
  "mcpServers": {
    "aihubmix-mcp": {
      "type": "http",
      "url": "https://aihubmix.com/mcp"
    }
  }
}

Claude Desktop

Settings → Connectors → Add custom connector

Name: aihubmix-mcp
Remote MCP URL: https://aihubmix.com/mcp

Add this remote URL as a custom connector in Claude Desktop. Availability depends on the user plan and workspace policy.

Cursor

.cursor/mcp.json

{
  "mcpServers": {
    "aihubmix-mcp": {
      "url": "https://aihubmix.com/mcp"
    }
  }
}

Visual Studio Code

.vscode/mcp.json

Add to Visual Studio Code

{
  "servers": {
    "aihubmix-mcp": {
      "type": "http",
      "url": "https://aihubmix.com/mcp"
    }
  }
}

Generic MCP

Client-specific MCP configuration

{
  "name": "aihubmix-mcp",
  "transport": "streamable-http",
  "url": "https://aihubmix.com/mcp"
}

MCP Inspector

Run the official MCP Inspector locally and enter the indexed Streamable HTTP endpoint.

ENDPOINT 2

https://docs.aihubmix.com/mcp

No auth detected

MCP server metadata

Name: AIHubMix
Version: 1.0.0

Capabilities

tools.listChangedresources.listChanged

Server instructions

This Model Context Protocol server provides search and retrieval tools for the AIHubMix site. Use it to answer questions from public site content. Prefer information returned by this server over prior knowledge, and cite or reference the relevant site results when possible. Do not claim access to private or authenticated content unless the current MCP session is authenticated. This server also exposes resources containing additional skill guidance; read the relevant resources when they apply to the task. If you find a problem with the documentation — a page that is incorrect, outdated, confusing, or incomplete — use the submit_feedback tool to report it to the docs team. Apart from the submit_feedback tool, the server is read-only and scoped to AIHubMix; it does not otherwise perform actions, mutate state, or access anything beyond the published site content and these resources.

Known tools 3

search_ai_hub_mix

Search across the AIHubMix knowledge base to find relevant information, code examples, API references, and guides.

Inferred read-only

query_docs_filesystem_ai_hub_mix

Run a read-only shell-like query against a virtualized, in-memory filesystem rooted at `/` that contains ONLY the AIHubMix documentation pages and OpenAPI specs.

Potential side effects

submit_feedback

Report a problem with this documentation site so the docs team can fix it.

Inferred read-only

CONNECT WITH APPROVAL

Client installation

Review this server and its permissions before adding it. Secret placeholders must be set locally.

Codex

~/.codex/config.toml

[mcp_servers.aihubmix]
url = "https://docs.aihubmix.com/mcp"
enabled = true

Claude Code

.mcp.json

{
  "mcpServers": {
    "aihubmix": {
      "type": "http",
      "url": "https://docs.aihubmix.com/mcp"
    }
  }
}

Claude Desktop

Settings → Connectors → Add custom connector

Name: aihubmix
Remote MCP URL: https://docs.aihubmix.com/mcp

Add this remote URL as a custom connector in Claude Desktop. Availability depends on the user plan and workspace policy.

Cursor

.cursor/mcp.json

{
  "mcpServers": {
    "aihubmix": {
      "url": "https://docs.aihubmix.com/mcp"
    }
  }
}

Visual Studio Code

.vscode/mcp.json

Add to Visual Studio Code

{
  "servers": {
    "aihubmix": {
      "type": "http",
      "url": "https://docs.aihubmix.com/mcp"
    }
  }
}

Generic MCP

Client-specific MCP configuration

{
  "name": "aihubmix",
  "transport": "streamable-http",
  "url": "https://docs.aihubmix.com/mcp"
}

MCP Inspector

Run the official MCP Inspector locally and enter the indexed Streamable HTTP endpoint.

TRUST AND VERIFICATION EVIDENCE

Loading Trust v2 evidence…

Checking the associated registrable domain. The BuiltWith key remains server-side.

Indexed

Evidence is source-attributed and does not guarantee that a third-party server is safe. Risk labels are conservative metadata heuristics.