What can you do with this server?

civitai-mcp-ultimate is a comprehensive MCP server covering the Civitai public REST API, enabling AI assistants to search, browse, download, and analyze AI models and images. Model Discovery & Search * Search models by text (Meilisearch or REST) with filters for type, base model, tag, creator, NSFW status, commercial use, sort order, and more * Get full model details, specific versions, or look up versions by file hash (SHA256, AutoV2, CRC32, BLAKE3) * Browse top checkpoints or LoRAs by base model (SDXL, Flux, Pony, etc.) * Retrieve valid enum values for API filters Image Browsing & Analysis * Browse AI-generated images/videos with filters for NSFW level, content type, tags, base model, tools, and techniques * Get top-ranked images and example images for specific models, including full generation parameters (prompt, CFG, sampler, seed, LoRAs) Downloads * Generate authenticated download URLs for model versions * Get ready-to-use curl or PowerShell download commands with optional auto-mapping to ComfyUI model directories Creators & Tags * Browse and search model creators and tags to refine content discovery Account * Verify API key validity and retrieve authenticated user details (username, tier, membership) TRAIL Content Tracking * Log and query content usage history (posted, selected, skipped) to manage pipelines and avoid duplicate posts * Get summary statistics from the content usage log Configuration * Set API keys for NSFW access and higher rate limits, specify output language (English or Russian), and define custom ComfyUI model paths

Which integrations are available for this server?

Provides a donation link to support the author's work, though this is a funding platform rather than a functional integration target of the MCP server itself. Generates curl download commands for Civitai models with authentication, enabling users to download LoRAs, checkpoints, and other model files directly from the command line. Provides Meilisearch-powered text search capabilities for Civitai models, offering fast and accurate search functionality as an alternative to Civitai's broken REST API search. Created by the same author (Nerual Dreming) who also maintains a Telegram API MCP server, though this specific server focuses on Civitai integration rather than Telegram functionality.

How do I use civitai-mcp-ultimate?

1. Click on "Deploy Server". 2. Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state. 3. In the chat, type @ followed by the MCP server name and your instructions, e.g., "@civitai-mcp-ultimate Find the top trending Flux LoRAs this month" That's it! The server will respond to your query, and you can continue using it as needed. Here is a step-by-step guide with screenshots.

de en es ja ko ru zh

civitai-mcp-ultimate

by timoncool

Overview Schema Source Related Servers Discussions Admin

Python

Remote

civitai-mcp-ultimate

The most complete MCP server for Civitai API — search models, browse images with prompts, download LoRAs/Checkpoints, analyze trends.

All from your AI assistant. 14 tools covering 100% of the Civitai public REST API v1.

All API parameters verified against real Civitai API on 2026-03-24. No guessing, no copying from broken implementations.

Features

Meilisearch-powered search — fast, accurate text search (Civitai REST API search is broken since May 2025)
Search models — Checkpoints, LoRAs, ControlNets with 40+ base model filters (SD 1.5 → Flux.2)
Top images with prompts — sort by reactions, comments, collections. Get full generation params
Download commands — curl/PowerShell commands with auth, ComfyUI path auto-mapping
NSFW support — full NSFW access with API key (None/Soft/Mature/X filtering)
Image/video cache — auto-download previews to ~/.civitai-mcp-cache/, 24h auto-cleanup
Bilingual output — English and Russian (CIVITAI_MCP_LANG=ru)
Async & fast — httpx async client, retry with backoff on rate limits
14 tools covering 100% of the Civitai public REST API v1

Related MCP server: good-comfyui-mcp

Quick Start

Install from PyPI

pip install civitai-mcp-ultimate

Claude Code

claude mcp add civitai -e CIVITAI_API_KEY=your_key_here -- uvx civitai-mcp-ultimate

Claude Desktop

Add to claude_desktop_config.json:

{
  "mcpServers": {
    "civitai": {
      "command": "uvx",
      "args": ["civitai-mcp-ultimate"],
      "env": {
        "CIVITAI_API_KEY": "your_key_here"
      }
    }
  }
}

pip

pip install civitai-mcp-ultimate
civitai-mcp-ultimate

Tools

Models (6 tools)

Tool	Description
`search_models`	Search via Meilisearch (text) or REST API (filters). Type, base model, tag, creator, sort
`get_model`	Full model details by ID
`get_model_version`	Version details: files, trigger words, download URLs
`get_model_version_by_hash`	Find model by file hash
`get_top_checkpoints`	Top checkpoints by base model (SDXL, Flux, Pony...)
`get_top_loras`	Top LoRAs by base model

Images (4 tools)

Tool	Description
`browse_images`	Browse images with filters and sorting
`get_top_images`	Top images by reactions/comments/collections
`get_model_images`	Example images for a model with prompts
`get_image_generation_data`	Full generation params from top images

Creators & Tags (2 tools)

Tool	Description
`get_creators`	Browse/search model creators
`get_tags`	Browse/search model tags

Downloads (2 tools)

Tool	Description
`get_download_url`	Authenticated download URL
`get_download_info`	Download commands (curl/PowerShell) + ComfyUI path mapping

Supported Filters

Base Models (all verified working)

SD 1.5, SD 1.5 LCM, SD 1.5 Hyper, SD 2.0, SD 2.1, SDXL 1.0, SDXL Lightning, SDXL Hyper, Flux.1 S, Flux.1 D, Flux.1 Krea, Flux.1 Kontext, Flux.2 D, Flux.2 Klein 9B/4B, Pony, Pony V7, Illustrious, NoobAI, Anima, ZImageBase, AuraFlow, Chroma, HiDream, Hunyuan 1, Kolors, PixArt a/E, Lumina, CogVideoX, Hunyuan Video, LTXV/LTXV2, Mochi, Wan Video (all variants)

Model Types

Checkpoint, LORA, LoCon, TextualInversion, Hypernetwork, Controlnet, Poses, AestheticGradient, Wildcards, MotionModule, VAE, Upscaler, Workflows, Other

Image Sort

Most Reactions, Most Comments, Most Collected, Newest, Oldest

Configuration

Variable	Required	Default	Description
`CIVITAI_API_KEY`	Recommended	—	API key for NSFW access + higher rate limits
`CIVITAI_MCP_LANG`	No	`en`	Output language: `en` or `ru`
`COMFYUI_MODELS_PATH`	No	—	ComfyUI models path for download commands
`MEILISEARCH_KEY`	No	built-in	Meilisearch search-only key (public, has default)

Get your API key: Civitai Account Settings

Examples

> Search for the top Flux LoRAs this month
> Show me the most popular SDXL checkpoints
> Get the best prompts for model 12345
> Give me download commands for this LoRA into my ComfyUI
> Find NSFW LoRAs for Illustrious sorted by reactions

Development

git clone https://github.com/timoncool/civitai-mcp-ultimate
cd civitai-mcp-ultimate
pip install -e ".[dev]"
pytest

Автор

Nerual Dreming (t.me/nerual_dreming) — neuro-cartel.com | основатель ArtGeneration.me

Other Projects by @timoncool

Project	Description
telegram-api-mcp	Full Telegram Bot API as MCP server
trail-spec	TRAIL — cross-MCP content tracking protocol
ACE-Step Studio	AI music studio — songs, vocals, covers, videos
VideoSOS	AI video production in the browser
Bulka	Live-coding music platform
GitLife	Your life in weeks — interactive calendar

Support the Author

I build open-source software and do AI research. Most of what I create is free and available to everyone. Your donations help me keep creating without worrying about where the next meal comes from =)

All donation methods | dalink.to/nerual_dreming | boosty.to/neuro_art

BTC: 1E7dHL22RpyhJGVpcvKdbyZgksSYkYeEBC
ETH (ERC20): 0xb5db65adf478983186d4897ba92fe2c25c594a0c
USDT (TRC20): TQST9Lp2TjK6FiVkn4fwfGUee7NmkxEE7C

Star History

License

MIT

Available Tools

21 tools

browse_imagesA

Read-onlyIdempotent

Browse AI-generated images/videos on Civitai.

Sort: Most Reactions, Most Comments, Most Collected, Newest, Oldest. NSFW filter: None, Soft, Mature, X. content_type: "image" or "video". browsing_level: "PG", "PG-13", "R", "X", "XXX" (comma-separated for multiple). tag: filter by tag (e.g. "anime", "animal", "architecture"). base_model: filter by base model (e.g. "Flux.1 D", "SDXL 1.0", "Pony"). tools: filter by tool (e.g. "ComfyUI", "Automatic1111"). techniques: filter by technique (e.g. "txt2img", "img2img"). has_meta: true = only with generation metadata. made_on_site: true = only generated on Civitai. originals_only/remixes_only: filter originals vs remixes. exclude_used: true = skip images/videos already in history (avoid duplicates). requester: who is requesting (e.g. "pikabu", "telegram", "scheduled:daily-post"). Always specify when fetching content for another MCP tool. Previews are cached locally for viewing via Read tool.

Inputs: model_id, model_version_id, post_id, username, +17 more. Returns: result

get_creatorsB

Read-onlyIdempotent

Browse and search model creators on Civitai.

Inputs: query, limit, page. Returns: result

get_current_userA

Read-onlyIdempotent

Get info about the currently authenticated user (requires CIVITAI_API_KEY).

Returns: username, tier, membership status. Use to verify API key is valid.

Inputs: no named parameters. Returns: result

get_download_infoA

Read-onlyIdempotent

Get download URLs + curl/PowerShell commands for a model.

If version_id not specified, uses latest version. Set comfyui_path to auto-map to correct ComfyUI model directory. Generates ready-to-paste download commands with authentication.

Inputs: model_id (required), version_id, comfyui_path. Returns: result

get_download_urlB

Read-onlyIdempotent

Get authenticated download URL for a model version.

Inputs: version_id (required). Returns: result

get_enumsA

Read-onlyIdempotent

Get all valid enum values for Civitai API filters.

Returns valid values for: ModelType, BaseModel, ActiveBaseModel, BaseModelType, ModelFileType. Use this to discover currently supported model types and base models.

Inputs: no named parameters. Returns: result

get_image_generation_dataA

Read-onlyIdempotent

Get full generation parameters from top images of a model.

Focused on extracting the best prompts, settings, and LoRA combinations. Only returns images that have generation metadata. exclude_used: true = skip already-used images. requester: who is requesting (e.g. "pikabu", "telegram").

Inputs: model_id (required), sort, limit, exclude_used, +1 more. Returns: result

get_modelA

Read-onlyIdempotent

Get detailed info about a specific model by ID.

Returns: description, all versions, files, trigger words, stats, creator, tags, download URLs.

Inputs: model_id (required). Returns: result

get_model_imagesA

Read-onlyIdempotent

Get example images generated with a specific model.

Returns images with full generation params: prompt, negative prompt, steps, CFG, sampler, seed, LoRAs used. Learn how to use a model well. exclude_used: true = skip already-used images. requester: who is requesting (e.g. "pikabu", "telegram").

Inputs: model_id (required), limit, exclude_used, requester. Returns: result

get_model_versionA

Read-onlyIdempotent

Get details about a specific model version by version ID.

Returns: download URLs, trigger words, base model, files, example images.

Inputs: version_id (required). Returns: result

get_model_version_by_hashA

Read-onlyIdempotent

Find a model version by its file hash (SHA256, AutoV2, CRC32, BLAKE3).

Inputs: hash (required). Returns: result

get_model_version_miniA

Read-onlyIdempotent

Quick check for a model version — availability, size, hashes, generation support.

Faster than get_model_version. Use for download/compatibility checks.

Inputs: version_id (required). Returns: result

get_tagsA

Read-onlyIdempotent

Browse and search model tags. Use tags in search_models filter.

Inputs: query, limit, page. Returns: result

get_top_checkpointsB

Read-onlyIdempotent

Get top checkpoint models for a specific base model.

Best for finding SDXL, Flux, Pony, Illustrious checkpoints. Base models: SD 1.5, SDXL 1.0, Flux.1 D, Flux.2 D, Pony, Pony V7, Illustrious, NoobAI, Chroma, HiDream, etc.

Inputs: base_model, period, sort, limit. Returns: result

get_top_imagesA

Read-onlyIdempotent

Get top images/videos from Civitai — best for finding great prompts.

Sort: Most Reactions, Most Comments, Most Collected, Newest, Oldest. Period: Day, Week, Month, Year, AllTime. content_type: "image" or "video". browsing_level: "PG", "PG-13", "R", "X", "XXX" (comma-separated). tag/base_model/tools/techniques: additional filters. has_meta/made_on_site/originals_only/remixes_only: boolean modifiers. exclude_used: true = skip images/videos already in history (avoid duplicate posts). requester: who is requesting (e.g. "pikabu", "telegram", "scheduled:daily-post"). Always specify for publishing workflows. Previews cached locally for Read tool.

Inputs: sort, period, nsfw, limit, +12 more. Returns: result

get_top_lorasB

Read-onlyIdempotent

Get top LoRA models for a specific base model.

Find the most popular LoRAs for SDXL, Flux, Pony, Illustrious. Set nsfw=true to include NSFW LoRAs (requires API key).

Inputs: base_model, period, sort, limit, +1 more. Returns: result

get_trailA

Read-onlyIdempotent

Query the TRAIL content log. Use to check what content was fetched, selected, posted, or skipped.

content_id: filter by content ID (exact or prefix like "civitai:image:"). action: filter by action(s) — "fetched", "selected", "posted", "failed", "skipped". String or list. requester: filter by workflow/task ID. trace_id: filter by pipeline trace ID. since: ISO 8601 timestamp — only entries after this time. limit: max entries, newest first (0 = all). offset: entries to skip for pagination.

Inputs: content_id, action, requester, trace_id, +3 more. Returns: result

get_trail_statsA

Read-onlyIdempotent

Get summary statistics from the TRAIL content log.

requester: filter by workflow/task ID. since: ISO 8601 timestamp — only count entries after this time.

Inputs: requester, since. Returns: result

mark_as_usedA

Idempotent

Mark images/videos as used (e.g. after sending to Pikabu, Telegram, etc.).

Call this AFTER successfully publishing content to another platform. image_ids: list of Civitai image IDs that were used. action: TRAIL action — "posted", "selected", "skipped", etc. requester: which workflow used this (e.g. "prompthub-daily", "txt2vid-daily"). context: optional note (e.g. "posted to community Stable Diffusion"). trace_id: optional TRAIL trace ID for pipeline correlation.

Inputs: image_ids (required), action, requester, context, +1 more. Returns: result

mark_trailA

Idempotent

Write an entry to the TRAIL content log.

content_id: content ID in format source:type:id (e.g. "civitai:image:12345"). action: what happened — fetched, selected, posted, failed, skipped. requester: workflow/task ID (e.g. "prompthub-daily"). details: optional platform-specific data. trace_id: optional pipeline trace ID. tags: optional labels for filtering.

Inputs: content_id (required), action (required), requester (required), details, +2 more. Returns: result

search_modelsA

Read-onlyIdempotent

Search for AI models on Civitai with flexible filters.

Uses Meilisearch for text queries (fast, accurate results). Falls back to REST API for filter-only queries, batch IDs, favorites, etc.

Find checkpoints, LoRAs, ControlNets and more. Types: Checkpoint, LORA, LoCon, DoRA, TextualInversion, Hypernetwork, Controlnet, Poses, VAE, Upscaler, Wildcards, MotionModule, Workflows, Detection, Other. Base models: SD 1.5, SDXL 1.0, Flux.1 D, Flux.2 D, Pony, Illustrious, NoobAI, Hunyuan 1, Kolors, Chroma, ZImageBase, etc. Sort: Highest Rated, Most Downloaded, Most Collected, Most Comments, Most Tipped, Newest. Period: AllTime, Year, Month, Week, Day (REST API only). Commercial use filter: None, Image, Rent, RentCivit, Sell (REST API only). cursor: pagination cursor from previous response (REST API).

Tips: text search works best via Meilisearch. Use get_model if you know the ID. Set favorites=true or hidden=true to filter your own models (requires API key, REST API). Set ids to fetch specific models by ID in batch (REST API).

Inputs: query, types, base_model, tag, +16 more. Returns: result

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

Deploy Server

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

TDQS

A3.9/5.0

Scored 2026-04-17 00:35 across 21 tools

Disambiguation4/5

Most tools have distinct purposes, such as browsing images, searching models, or managing download info, but there is some overlap between browse_images and get_top_images, both of which fetch top images with similar filters, which could cause confusion. Additionally, get_model and get_model_version serve related but slightly different functions, but their descriptions help clarify the distinction.

Naming Consistency5/5

Tool names follow a consistent verb_noun pattern throughout, such as browse_images, get_creators, search_models, and mark_as_used. All tools use snake_case, and the naming convention is predictable and readable, making it easy for agents to understand the action and target.

Tool Count3/5

With 21 tools, the count is on the higher side for a Civitai-focused server, which may feel heavy but is somewhat justified by the comprehensive coverage of browsing, searching, downloading, and logging functionalities. However, it borders on being excessive, as some tools like get_download_info and get_download_url could potentially be consolidated, and the TRAIL-related tools (get_trail, get_trail_stats, mark_trail, mark_as_used) add complexity that might not be essential for all use cases.

Completeness5/5

The tool set provides complete coverage for interacting with Civitai, including browsing and searching images and models, fetching detailed model info, handling downloads, managing user data, and logging content usage via TRAIL. There are no obvious gaps; agents can perform full workflows from discovery to download and tracking, with tools like get_enums and get_current_user supporting auxiliary needs effectively.

Maintenance

ActivityActive

ResponsivenessNo recent community issues

Resources

Related MCP Connectors

mcp-flux-pro
io.github.AceDataCloud
MCP server for Flux AI image generation
Image & Video Processing Multimedia Processing
23
https://flux.mcp.acedata.cloud/mcp
mcpA
com.budgetpixel
Generate AI images, video, music, and sound effects, and upscale them, from any MCP client.
AI & Machine Learning Image & Video Processing Audio Processing
3113
https://mcp.budgetpixel.com/mcp
mcp-qwen-image
io.github.AceDataCloud
MCP server for Qwen Image 3 AI image generation
AI & Machine Learning Image & Video Processing
1
https://qwen-image.mcp.acedata.cloud/mcp
Danushkumar-V-mcp-discord
ai.smithery
An MCP server that integrates with Discord to provide AI-powered features.
Communication Social Media App Automation
2
https://server.smithery.ai/@Danushkumar-V/mcp-discord/mcp

Related MCP Servers

ComfyUI MCP Server
Image & Video Processing App Automation Multimedia Processing
Overseer66
A
license
B
quality
D
maintenance
A server that integrates ComfyUI with MCP, allowing users to generate images and download them through natural language interactions.
Updated a year ago (2025-11-04 02:06 UTC)
4
22
Apache 2.0
good-comfyui-mcp
Image & Video Processing AI & Machine Learning Browser Automation
xingxue-ux
A
license
Not graded
quality
C
maintenance
MCP server for generating AI images with local ComfyUI, featuring a reference-image-to-replication toolchain including Danbooru tag lookup, local Ollama vision, deobfuscation, and Civitai LoRA search/download.
Updated 3 months ago (2026-08-11 07:51 UTC)
3
MIT
ComfyUI MCP Server
Image & Video Processing AI & Machine Learning
a-misen
F
license
A
quality
D
maintenance
An MCP server for generating images and checking generation status through ComfyUI's API. It allows interaction with local ComfyUI instances by providing workflow-based image generation and status checking tools.
Updated 3 months ago (2026-08-11 15:42 UTC)
3
-
comfygenmcp
Image & Video Processing AI & Machine Learning
aschet
A
license
A
quality
B
maintenance
MCP server that connects an AI assistant to a running ComfyUI instance, allowing it to fetch saved workflows, inject a prompt and seed, run generation, and return the image inline in chat.
Updated 2 months ago (2026-09-06 21:52 UTC)
2
GPL 3.0

civitai-mcp-ultimate

Features

Quick Start

Install from PyPI

Claude Code

Claude Desktop

pip

Tools

Models (6 tools)

Images (4 tools)

Creators & Tags (2 tools)

Downloads (2 tools)

Supported Filters

Base Models (all verified working)

Model Types

Image Sort

Configuration

Examples

Development

Автор

Other Projects by @timoncool

Support the Author

Star History

License

Available Tools

Tool Schema Changelog

TDQS

Maintenance

Resources

Related MCP Connectors

Related MCP Servers

ComfyUI MCP Server

good-comfyui-mcp

ComfyUI MCP Server

comfygenmcp