mcpField
C
Civitai

Civitai

Remote
pipeworx.ioMedia & Design0Updated 5d ago

About Civitai

Civitai is an MCP server for searching and browsing Civitai's community catalog of AI image-generation models. It helps people compare model details, versions, base models, and trigger words, with mature content excluded by default.

Key features

  1. 01Search models by text and type
  2. 02View model details and versions
  3. 03Browse popular models by type
  4. 04Review base models and trigger words

Use cases

  1. 01Find a model for image generation
  2. 02Compare versions and model details
  3. 03Browse popular models for a base model

MCP support

Exposes Civitai model search, detail lookup, and type-based browsing tools to MCP clients. It runs locally over stdio or through the Pipeworx gateway.

Configuration

Remote servers need no local install. Pick your client, then copy the config or install in one click.

Endpointhttps://gateway.pipeworx.io/civitai/mcp
Copy install command
Claude CodeTerminal
Cursor.cursor/mcp.json
VS Code.vscode/mcp.json
Claude Desktopclaude_desktop_config.json
Windsurf~/.codeium/windsurf/mcp_config.json

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

Details

From the project README

mcp-civitai

Civitai MCP.

Part of Pipeworx — an MCP gateway connecting AI agents to 1875+ live data sources. This is an independent, unofficial integration — not affiliated with, endorsed by, or published by the upstream provider.

Tools

ToolDescription
search_modelsSearch Civitai's catalog of community AI image-generation models (Stable Diffusion checkpoints, LoRAs, textual-inversion embeddings, ControlNets) by text query and/or type. Returns download stats, base model (SDXL / Pony / Flux / SD 1.5), creator and trained trigger words. Defaults to Safe-For-Work (mature content excluded). Keyless.
get_modelGet full details for a single Civitai model by id — description, type, creator, tags, download/rating stats, and every version with its base model, trigger words and downloadable files. Try id 4201 ("Realistic Vision V6.0 B1", a SFW checkpoint). Defaults Safe-For-Work; nsfw flag is surfaced. Keyless.
list_by_typeBrowse the top community models of a given type on Civitai (most-downloaded first), optionally filtered to a specific base model. Great for "best SDXL checkpoints" or "top Flux LoRAs". Defaults to Safe-For-Work (mature excluded). Keyless.

Quick Start

Add to your MCP client (Claude Desktop, Cursor, Windsurf, etc.):

{
  "mcpServers": {
    "civitai": {
      "url": "https://gateway.pipeworx.io/civitai/mcp"
    }
  }
}
What this endpoint actually serves

tools/list at https://gateway.pipeworx.io/civitai/mcp returns the tools in the table above plus the shared Pipeworx meta-tools — ask_pipeworx, discover_tools, search_within, remember/recall and the rest of the gateway-wide set. So the tool count you see is larger than this table: a single-pack endpoint currently lists roughly 30 shared tools alongside the pack's own. The connection's initialize response states its exact scope, and is the authoritative answer for a given day.

This is deliberate, not multiplexing by accident. The meta-tools are what let a scoped connection answer a question this pack does not cover — via ask_pipeworx, which routes across the whole catalog — without you adding a second MCP server. There is currently no way to mount a pack endpoint without them; if the extra schemas cost you more context than the routing is worth, connect to the full gateway once rather than to several pack endpoints.

Or connect to the full Pipeworx gateway to get every pack's tools listed directly, instead of just this one's:

{
  "mcpServers": {
    "pipeworx": {
      "url": "https://gateway.pipeworx.io/mcp"
    }
  }
}

Both URLs reach the same gateway and the same 1875+ data sources. The only difference is which pack's tools are listed directly; ask_pipeworx reaches all of them from either one.

No MCP client? Call it over HTTP

curl -X POST https://gateway.pipeworx.io/v1/tools/civitai_search_models \
  -H 'Content-Type: application/json' \
  -d '{"query":"realistic portrait","type":"Checkpoint","sort":"Most Downloaded","limit":10}'

No account needed for the first calls. Inspect any tool: GET https://gateway.pipeworx.io/v1/tools/civitai_search_models. Find one: POST https://gateway.pipeworx.io/v1/tools/search_packs with {"query":"..."}.

Standalone (no gateway account)

This package also runs as a local stdio MCP server — no Pipeworx account, no gateway round-trip:

{
  "mcpServers": {
    "civitai": {
      "command": "npx",
      "args": ["-y", "@pipeworx/mcp-civitai"]
    }
  }
}

Or run it directly to confirm it starts:

npx -y @pipeworx/mcp-civitai

It speaks MCP over stdin/stdout and answers initialize/tools/list/tools/call for only this pack's tools — none of the shared meta-tools the gateway connection above adds. Same source, same tools, no ask_pipeworx routing.

Using with ask_pipeworx

Instead of calling tools directly, you can ask questions in plain English — this works on the pack endpoint above as well as on the full gateway:

ask_pipeworx({ question: "your question about Civitai data" })

The gateway picks the right tool and fills the arguments automatically.

More

License

MIT

Comments

Markdown supported

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.