What can you do with this server?

This server connects AI assistants to the Gelbooru API, enabling image search, tag exploration, and Stable Diffusion prompt generation from real character appearance data. * Search Posts (search_posts): Search images using full Gelbooru tag syntax — AND/OR/NOT logic, wildcards, meta-tags (rating, score, resolution, user), sorting (score, random, updated), and pagination. * Search Tags (search_tags): Look up tags by exact name, wildcard pattern, or ID. Returns post counts, tag types, and supports sorting by date, count, or name. * Search Users (search_users): Find user accounts by exact username or wildcard pattern. * Get Comments (get_comments): Retrieve all comments on a specific post by ID. * Get Deleted Posts (get_deleted_posts): List deleted posts, optionally filtered by a last_id to track recently removed content. * Get Character Tags (get_character_tags): Analyze top-scored posts for a character and return frequently occurring tags categorized into eye, hair, and other (clothing/accessories) buckets with frequency scores. Results are disk-cached for 24 hours. * Build Stable Diffusion Prompt (build_prompt): Auto-generate a ready-to-use prompt string (e.g. misty (pokemon), green eyes, orange hair, side ponytail, ...) from real Gelbooru tag frequency data, with optional inclusion of clothing/accessory tags.

Gelbooru MCP

by citronlegacy

Overview Schema Related Servers Score Discussions

Python

Remote

gelbooru-mcp

Python License: MIT MCP

A Python MCP server that wraps the Gelbooru API. Connect it to any MCP-compatible client (Claude Desktop, Cursor, etc.) to search posts, look up tags, and generate Stable Diffusion prompts from real character appearance data — all directly from your AI assistant.

✨ Features

🎨 Stable Diffusion Prompt Generation

Character Prompts: Auto-generate accurate SD prompts from real Gelbooru tag frequency data
Appearance Breakdown: Separate eye, hair, and clothing/accessory tag categories
Smart Caching: Results cached for 24 hours — no repeated API hits

🔍 Post & Tag Search

Advanced Filtering: Search by tags, score, resolution, rating, uploader, pool, and more
Full Tag Syntax: AND, OR, wildcard, exclusion, meta-tags, sorting, and pagination
Tag Lookup: Check tag existence, post counts, and discover related tags

👥 Community Tools

User Search: Find Gelbooru user accounts by name or wildcard pattern
Comments: Retrieve post comments for any post ID
Deleted Posts: Track removed content above a given post ID

Related MCP server: MyAnimeList MCP Server

📦 Installation

Prerequisites

Python 3.10+
git

Quick Start

Clone the repository:

git clone https://github.com/citronlegacy/gelbooru-mcp.git
cd gelbooru-mcp

Run the installer:

chmod +x install.sh && ./install.sh
# or without chmod:
bash install.sh

Or install manually:

pip install mcp

Note: Add .gelbooru_cache/ and .venv/ to your .gitignore to avoid committing cached data or your virtual environment.

Getting a Gelbooru API Key

Visit your Gelbooru account options page
Log in to your Gelbooru account
Copy your API Key and User ID
Set them as environment variables (see below)

🔑 Authentication

API credentials are optional but strongly recommended — unauthenticated requests are throttled and limited to 2 tags per query. Gelbooru Patreon supporters receive unlimited requests.

export GELBOORU_API_KEY="your_api_key"
export GELBOORU_USER_ID="your_user_id"

Both values are on your Gelbooru account options page. Without them the server still works but requests may be throttled. Patreon supporters of Gelbooru are not rate-limited.

▶️ Running the Server

python gelbooru_mcp.py
# or via the venv created by install.sh:
.venv/bin/python gelbooru_mcp.py

⚙️ Configuration

Claude Desktop

Add the following to your claude_desktop_config.json:

{
  "mcpServers": {
    "gelbooru-mcp": {
      "command": "/absolute/path/to/.venv/bin/python",
      "args": ["/absolute/path/to/gelbooru_mcp.py"],
      "env": {
        "GELBOORU_API_KEY": "your_api_key",
        "GELBOORU_USER_ID": "your_user_id"
      }
    }
  }
}

Other MCP Clients

Configure according to your client's documentation:

Command: /absolute/path/to/.venv/bin/python
Args: /absolute/path/to/gelbooru_mcp.py
Transport: stdio

💡 Usage Examples

Generate a Stable Diffusion prompt for a character

"Build me a Stable Diffusion prompt for Rem from Re:Zero."

The LLM calls build_prompt with character_name: "rem_(re:zero)" and gets back:

rem (re:zero), blue eyes, blue hair, short hair, maid, maid headdress, maid apron, ...

Find high-quality wallpaper images

"Show me the top-rated scenery images that are at least 1920px wide."

The LLM calls search_posts with tags: "scenery width:>=1920 sort:score:desc".

Look up how popular a tag is

"How many posts does the tag 'misty_(pokemon)' have on Gelbooru?"

The LLM calls search_tags with name: "misty_(pokemon)" and reads the count field.

🛠️ Available Tools

Tool	Description	Key Parameters
`build_prompt`	Generate a Stable Diffusion prompt string for a character	`character_name`, `max_images`, `include_other`
`get_character_tags`	Get structured tag breakdown with frequency counts	`character_name`, `max_images`
`search_posts`	Search posts with full tag syntax support	`tags`, `limit`, `pid`, `id`
`search_tags`	Look up tags by name, pattern, or ID	`name`, `name_pattern`, `orderby`, `limit`
`search_users`	Find Gelbooru user accounts	`name`, `name_pattern`, `limit`
`get_comments`	Retrieve comments for a post	`post_id`
`get_deleted_posts`	List recently deleted posts	`last_id`, `limit`

📖 Tools Reference

`build_prompt`

Fetches the most-tagged rating:general solo posts for a character and assembles a ready-to-paste Stable Diffusion prompt string. Internally calls get_character_tags so results are cached after the first fetch.

Parameters

Parameter	Type	Required	Default	Description
`character_name`	string	✅	—	Gelbooru character tag, e.g. `misty_(pokemon)`
`max_images`	integer	❌	`300`	Posts to analyse. More = slower first fetch, more reliable tags. Cached afterward.
`include_other`	boolean	❌	`true`	Include non-eye/hair tags (clothing, accessories, etc.). Set to `false` for appearance-only prompts.

Example response

{
  "prompt": {
    "character": "misty (pokemon)",
    "posts_analysed": 284,
    "cache_hit": false,
    "prompt_string": "misty (pokemon), green eyes, orange hair, side ponytail, gym leader, shorts, suspenders",
    "tags": {
      "eye":   ["green eyes"],
      "hair":  ["orange hair", "side ponytail"],
      "other": ["gym leader", "shorts", "suspenders"]
    }
  }
}

LLM Tip: Always use Gelbooru's underscore format (misty_(pokemon) not Misty (Pokemon)). If unsure of the exact tag, call search_tags with name_pattern first.

`get_character_tags`

Same data source as build_prompt but returns the full structured tag breakdown with frequency counts. Use this when you want to inspect, filter, or reformat tags yourself.

Parameters

Parameter	Type	Required	Default	Description
`character_name`	string	✅	—	Gelbooru character tag, e.g. `rem_(re:zero)`
`max_images`	integer	❌	`300`	Number of top-scored posts to analyse.

Example response

{
  "character_tags": {
    "name": "rem_(re:zero)",
    "posts_analysed": 300,
    "cache_hit": true,
    "eye": [
      { "tag": "blue eyes", "count": 261, "frequency": 0.87 }
    ],
    "hair": [
      { "tag": "blue hair",  "count": 274, "frequency": 0.913 },
      { "tag": "short hair", "count": 198, "frequency": 0.66  }
    ],
    "other": [
      { "tag": "maid", "count": 231, "frequency": 0.77 }
    ]
  }
}

frequency is the fraction of analysed posts that had that tag (0.0–1.0). Tags near 1.0 are near-universal; tags below 0.3 are situational.

Cache environment variables:

Env var	Default	Description
`GELBOORU_CACHE_DIR`	`.gelbooru_cache/` next to script	Custom cache folder path
`GELBOORU_CACHE_TTL`	`86400` (24 hours)	Cache lifetime in seconds

`search_posts`

Search Gelbooru posts using any tag combination. Supports the full Gelbooru tag syntax including meta-tags, sorting, and filtering.

Parameters

Parameter	Type	Required	Default	Description
`tags`	string	❌	—	Tag query string (see Tag Syntax Reference below)
`limit`	integer	❌	`20`	Posts to return (max `100`)
`pid`	integer	❌	`0`	Page number (0-indexed) for pagination
`id`	integer	❌	—	Fetch a single post by its Gelbooru post ID
`cid`	integer	❌	—	Fetch posts by change ID (Unix timestamp)

`get_deleted_posts`

Retrieve posts that have been deleted from Gelbooru, optionally filtered to those above a given post ID.

Parameters

Parameter	Type	Required	Default	Description
`last_id`	integer	❌	—	Only return deleted posts whose ID is above this value. Useful for syncing a local mirror.
`limit`	integer	❌	`20`	Posts to return (max `100`)

`search_tags`

Look up Gelbooru tags by name, wildcard pattern, or ID. Useful for checking tag existence, finding post counts, discovering related tags, or autocomplete.

Parameters

Parameter	Type	Required	Default	Description
`name`	string	❌	—	Exact tag name, e.g. `blue_hair`
`names`	string	❌	—	Space-separated list of exact tag names, e.g. `cat_ears dog_ears fox_ears`
`name_pattern`	string	❌	—	SQL LIKE wildcard: `%` = any chars, `_` = one char. E.g. `%schoolgirl%`
`id`	integer	❌	—	Look up a tag by its database ID
`after_id`	integer	❌	—	Return tags with ID greater than this value
`limit`	integer	❌	`20`	Tags to return (max `100`)
`order`	string	❌	—	`ASC` or `DESC`
`orderby`	string	❌	—	Sort field: `date`, `count`, or `name`

LLM Tip: If the user gives a character name in natural language (e.g. "Misty from Pokemon"), use name_pattern with %misty%_(pokemon)% to find the correct Gelbooru tag before calling get_character_tags or build_prompt.

`search_users`

Search for Gelbooru user accounts by name.

Parameters

Parameter	Type	Required	Default	Description
`name`	string	❌	—	Exact username
`name_pattern`	string	❌	—	SQL LIKE wildcard username search
`limit`	integer	❌	`20`	Results to return (max `100`)
`pid`	integer	❌	`0`	Page number for pagination

`get_comments`

Retrieve comments on a specific post.

Parameters

Parameter	Type	Required	Default	Description
`post_id`	integer	✅	—	The Gelbooru post ID to fetch comments for

🏷️ Tag Syntax Reference

Syntax	Meaning
`tag1 tag2`	Posts with both tag1 AND tag2
`{tag1 ~ tag2 ~ tag3}`	Posts with tag1 OR tag2 OR tag3
`-tag1`	Exclude posts with tag1
`*tag1`	Wildcard prefix (tags ending with tag1)
`tag1*`	Wildcard suffix (tags starting with tag1)
`rating:general`	Filter by rating: `general`, `questionable`, or `explicit`
`-rating:explicit`	Exclude a rating
`score:>=50`	Score at least 50
`width:>=1920`	Image width ≥ 1920px
`height:>1080`	Image height > 1080px
`user:bob`	Uploaded by user "bob"
`fav:1`	Posts favourited by user with ID 1
`pool:2`	Posts in pool ID 2
`sort:score:desc`	Sort by score (desc or asc)
`sort:random`	Random order on every request
`sort:random:1234`	Random order with a fixed seed (0–10000)
`sort:updated:desc`	Sort by most recently updated

🤖 Notes for LLMs

Character tag format: Gelbooru uses character_(series) format with underscores. Always convert natural language names before passing to tools — "Rem from Re:Zero" → rem_(re:zero), "Saber from Fate" → saber_(fate).
Workflow for character prompts: If the exact tag is unknown, call search_tags with name_pattern first → confirm the tag exists and has posts → then call build_prompt.
Pagination: search_posts returns max 100 results per call. Use pid to walk through pages. get_character_tags and build_prompt handle their own pagination internally.
Cache: get_character_tags and build_prompt cache results for 24 hours. The cache_hit field in the response indicates whether live or cached data was used.
Ratings: Gelbooru uses general, questionable, and explicit. get_character_tags and build_prompt always filter to rating:general for cleaner, more representative character data.

⚠️ Known Limitations

Tag search limit: Gelbooru enforces a maximum of 2 tags per unauthenticated search query. For complex multi-tag queries, set GELBOORU_API_KEY and GELBOORU_USER_ID.
get_character_tags accuracy: Results depend on how consistently a character is tagged on Gelbooru. Niche or recently added characters may have fewer posts and less reliable frequency data.
rating:general only for character tools: build_prompt and get_character_tags intentionally restrict to rating:general for clean, representative appearance data. Explicit posts are excluded by design.
Cache is per (character_name, max_images) pair: Changing max_images busts the cache for that character.

🐛 Troubleshooting

Server won't start:

Ensure Python 3.10+ is installed: python --version
Verify the virtual environment was created: ls .venv/
Re-run the installer: bash install.sh

API rate limiting / throttled requests:

Set GELBOORU_API_KEY and GELBOORU_USER_ID environment variables
Gelbooru Patreon supporters receive unlimited requests

Character not found / empty results:

Confirm the tag exists with search_tags using name_pattern
Check spelling — Gelbooru uses character_(series) underscore format
Some characters may have very few consistently tagged posts

Tag syntax errors / too many tags:

Unauthenticated users are limited to 2 tags per query
Authenticate with API credentials for complex multi-tag searches

🤝 Contributing

Pull requests are welcome! If you find a character tag being miscategorised (e.g. a hair style tag missing from the hair bucket, or a noise tag slipping through the purge filter), please open an issue or PR with the tag and which list it belongs in.

Development Setup

Fork the repository
Create a feature branch
Make your changes
Submit a pull request

📄 License

MIT License — see LICENSE for details.

🔗 Links

Available Tools

7 tools

build_promptA

Given a character name, returns a ready-to-use image-generation prompt string like 'misty (pokemon), green eyes, orange hair, side ponytail, ...'. Internally calls get_character_tags with caching, then assembles the prompt with tags ordered by frequency (eye → hair → other).

ParametersJSON Schema

Name	Required	Description
`character_name`	Yes	The Gelbooru tag for the character, e.g. 'misty_(pokemon)'. Use underscores as Gelbooru does.
`max_images`	No	Posts to analyse (default 300). Cached after first fetch.
`include_other`	No	Whether to include non-eye/hair tags (clothing, accessories, etc.) in the prompt. Default true.

TDQS

A4.2/5.0

Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries the full burden and discloses key behavioral traits: it describes the internal process (calls get_character_tags with caching), output assembly (tags ordered by frequency), and caching behavior ('cached after first fetch'). It lacks details on error handling or performance, but covers core operations well.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is appropriately sized and front-loaded, starting with the core purpose and following with implementation details. Every sentence adds value: the first states the output, the second explains the internal process and tag ordering. No wasted words.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's moderate complexity (3 parameters, no output schema, no annotations), the description is mostly complete. It explains the tool's purpose, behavior, and output format. However, it lacks details on error cases or the exact format of the returned prompt string, leaving some gaps for an agent.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the schema already documents all parameters thoroughly. The description adds minimal value beyond the schema, only implying that character_name uses Gelbooru tags and mentioning caching for max_images. Baseline 3 is appropriate as the schema does the heavy lifting.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's purpose with specific verbs ('returns a ready-to-use image-generation prompt string') and resources ('given a character name'). It distinguishes from sibling tools by mentioning internal calls to get_character_tags and specifying the output format, which is unique among the listed siblings.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides clear context for when to use this tool ('given a character name') and implies usage for image-generation prompts. However, it does not explicitly state when not to use it or name alternatives among siblings, such as when raw tag data from get_character_tags might be preferred.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

get_character_tagsA

Given a character name (e.g. 'misty_(pokemon)'), fetches the top highest-scored general/solo posts across multiple pages and returns the most frequently occurring tags split into three semantic buckets: eye colour/shape, hair colour/style, and other character traits. Each tag includes a frequency score. Results are cached to disk for 24 hours.

ParametersJSON Schema

Name	Required	Description	Default
`character_name`	Yes	The Gelbooru tag for the character, e.g. 'misty_(pokemon)', 'rem_(re:zero)', 'saber_(fate)'. Use underscores as Gelbooru does.
`max_images`	No	How many top-scored posts to analyse across all pages (default 300). More images = slower but more reliable results. Fetched in pages of 100.

TDQS

A3.8/5.0

Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries the full burden and does well by disclosing key behavioral traits: it fetches from multiple pages, analyzes top-scored posts, returns categorized tags with frequency scores, and implements 24-hour disk caching. It doesn't mention rate limits, authentication needs, or error handling, but covers substantial operational context.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is appropriately sized and front-loaded with the core functionality in the first clause. Each sentence adds value: the first explains the operation, the second details the output structure, and the third covers caching. No wasted words, though it could be slightly more streamlined.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a tool with 2 parameters, 100% schema coverage, and no output schema, the description provides good operational context but lacks output format details. It explains what the tool returns conceptually (tag buckets with frequencies) but not the exact structure. Given the complexity of tag categorization, more output specification would help, though the caching disclosure adds value.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the schema already fully documents both parameters. The description adds minimal value beyond the schema, mentioning 'top highest-scored posts' which relates to the max_images parameter but doesn't provide additional syntax or format details. Baseline 3 is appropriate when schema does the heavy lifting.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the specific action ('fetches the top highest-scored general/solo posts across multiple pages') and the resource ('character name'), with detailed output specification ('returns the most frequently occurring tags split into three semantic buckets'). It distinguishes from siblings like 'search_posts' or 'search_tags' by focusing on character-specific tag analysis rather than general searching.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies usage for character tag analysis but doesn't explicitly state when to use this tool versus alternatives like 'search_tags' or 'search_posts'. It mentions caching behavior which provides some context, but lacks direct guidance on tool selection among siblings.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

get_commentsC

Retrieve comments for a specific Gelbooru post.

ParametersJSON Schema

Name	Required	Description	Default
`post_id`	Yes	The post ID whose comments you want to retrieve.

TDQS

C2.9/5.0

Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries the full burden of behavioral disclosure. It states the action ('Retrieve') but does not clarify if this is a read-only operation, requires authentication, has rate limits, or describes the return format (e.g., list structure, pagination). This leaves significant gaps for a tool that fetches data.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, direct sentence with zero wasted words, efficiently stating the tool's purpose. It is appropriately sized and front-loaded, making it easy to parse without unnecessary elaboration.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the lack of annotations and output schema, the description is incomplete for a data retrieval tool. It does not explain what the return values look like (e.g., comment format, error handling) or address behavioral aspects like permissions or limitations, leaving the agent with insufficient context for effective use.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema has 100% description coverage, with the 'post_id' parameter clearly documented. The description adds no additional semantic details beyond what the schema provides, such as example values or constraints, so it meets the baseline for high schema coverage without compensating further.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the verb ('Retrieve') and resource ('comments for a specific Gelbooru post'), making the purpose unambiguous. However, it does not differentiate from sibling tools like 'search_posts' or 'get_deleted_posts' in terms of scope or functionality, which prevents a perfect score.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides no guidance on when to use this tool versus alternatives, such as whether it's for fetching all comments on a post versus filtered searches. It lacks any mention of prerequisites, exclusions, or sibling tool comparisons, leaving usage context implied at best.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

get_deleted_postsC

Retrieve deleted posts. Pass last_id to get everything deleted above that post ID.

ParametersJSON Schema

Name	Required	Description	Default
`last_id`	No	Return deleted posts whose ID is above this value.
`limit`	No

TDQS

C2.9/5.0

Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries the full burden of behavioral disclosure. It mentions the 'last_id' parameter for pagination-like behavior but fails to describe critical traits such as authentication needs, rate limits, error conditions, or the format/scope of returned data (e.g., are all deleted posts returned or only user-accessible ones?).

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is extremely concise with two sentences that directly address the tool's function and a key parameter. It is front-loaded with the core purpose and avoids any redundant or unnecessary wording, making it highly efficient.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's complexity (retrieving deleted data with pagination), lack of annotations, and no output schema, the description is incomplete. It misses essential context like what 'deleted posts' entails (e.g., soft vs. hard deletion, timeframes), behavioral constraints, and output details, leaving significant gaps for agent understanding.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 50% (only 'last_id' has a description in the schema). The description adds meaning by explaining 'last_id' usage ('get everything deleted above that post ID'), which clarifies its pagination role. However, it doesn't address the 'limit' parameter at all, leaving half the parameters without semantic context beyond the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the verb ('Retrieve') and resource ('deleted posts'), making the purpose immediately understandable. It distinguishes this tool from siblings like 'search_posts' by focusing specifically on deleted content, though it doesn't explicitly contrast with all siblings.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides no guidance on when to use this tool versus alternatives like 'search_posts' or 'get_comments'. It mentions a parameter usage ('Pass last_id...') but offers no context about appropriate scenarios, prerequisites, or exclusions for tool selection.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

search_postsA

Search Gelbooru posts by tags, page, limit, or ID. Supports all Gelbooru tag syntax: AND (tag1 tag2), OR ({t1~t2}), NOT (-tag), wildcards (tag / tag), meta-tags like rating:safe/questionable/explicit, score:>=N, width:>=N, user:name, sort:random, sort:score:desc, etc.

ParametersJSON Schema

Name	Required	Description
`tags`	No	Tag query string. Examples: 'cat_ears blue_eyes', 'touhou -rating:explicit', 'score:>=50 sort:score:desc'
`limit`	No	Number of posts to return (default 20, max 100).
`pid`	No	Page number (0-indexed).
`id`	No	Fetch a single post by its Gelbooru ID.
`cid`	No	Fetch posts by change ID (Unix timestamp).

TDQS

A3.8/5.0

Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries the full burden of behavioral disclosure. It mentions support for 'all Gelbooru tag syntax' and lists various operators, which adds context about search capabilities. However, it does not cover important behavioral aspects like rate limits, authentication needs, error handling, or response format, leaving gaps in transparency for a search tool.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is appropriately sized and front-loaded, starting with the core purpose and immediately diving into key features like tag syntax. Every sentence adds value by explaining capabilities, though it could be slightly more structured by separating syntax examples into bullet points for clarity.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the complexity of a search tool with 5 parameters and no output schema, the description is partially complete. It covers search syntax and parameters well but lacks information on return values, pagination behavior, or error scenarios. Without annotations or an output schema, these gaps reduce overall completeness for effective agent use.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the schema already documents all 5 parameters thoroughly. The description adds value by explaining the broader context of tag syntax and usage examples, but it does not provide additional semantic details beyond what the schema specifies, such as interactions between parameters or edge cases.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the specific action ('Search Gelbooru posts') and the resources involved ('by tags, page, limit, or ID'), distinguishing it from sibling tools like search_tags or search_users. It provides concrete examples of what can be searched, making the purpose unambiguous and specific.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies usage through examples of tag syntax and parameters, suggesting when to use this tool for searching posts versus other tools. However, it lacks explicit guidance on when not to use it or direct alternatives, such as distinguishing from get_deleted_posts or get_comments for specific post-related queries.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

search_tagsB

Search Gelbooru tags by name, pattern, or ID. Useful for autocomplete, tag counts, and tag type lookup.

ParametersJSON Schema

Name	Required	Description
`name`	No	Exact tag name to look up.
`names`	No	Space-separated list of tag names, e.g. 'cat dog fox'.
`name_pattern`	No	Wildcard tag search using SQL LIKE syntax. Use % for multi-char wildcard, _ for single-char. Example: '%choolgirl%'
`id`	No	Look up a tag by its database ID.
`after_id`	No	Return tags whose ID is greater than this value.
`limit`	No
`order`	No	Sort direction.
`orderby`	No	Field to sort by.

TDQS

B3.2/5.0

Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full burden of behavioral disclosure. It mentions the tool is 'useful for' specific purposes but does not describe key behaviors such as pagination (implied by 'limit' and 'after_id'), authentication needs, rate limits, error handling, or what the return format looks like. This leaves significant gaps for a search tool with multiple parameters.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is front-loaded with the core purpose in the first sentence, followed by a concise second sentence highlighting use cases. It is appropriately sized with zero wasted words, making it easy to scan and understand quickly.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the complexity (8 parameters, no output schema, and no annotations), the description is incomplete. It does not explain the return values, pagination behavior, or error conditions, which are critical for a search tool. While the schema covers parameters well, the lack of behavioral and output information leaves the agent with significant uncertainty.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is high at 88%, so the schema already documents most parameters well. The description adds minimal value beyond the schema by mentioning search methods ('by name, pattern, or ID') and use cases, but does not provide additional syntax, format details, or clarify interactions between parameters (e.g., how 'name' and 'name_pattern' differ in practice).

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the action ('Search Gelbooru tags') and resources ('tags'), specifying it can search by name, pattern, or ID. It distinguishes from sibling tools like 'search_posts' or 'search_users' by focusing on tags, though it doesn't explicitly contrast with 'get_character_tags'.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides implied usage contexts ('useful for autocomplete, tag counts, and tag type lookup'), which helps suggest when to use this tool. However, it lacks explicit guidance on when to choose this over alternatives like 'get_character_tags' or other search tools, and does not mention exclusions or prerequisites.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

search_usersC

Search Gelbooru users by name or name pattern.

ParametersJSON Schema

Name	Required	Description
`name`	No	Exact username to search for.
`name_pattern`	No	Wildcard username search (SQL LIKE syntax).
`limit`	No
`pid`	No

TDQS

C2.9/5.0

Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries the full burden of behavioral disclosure. It states the search functionality but doesn't mention whether this is a read-only operation, what permissions are needed, rate limits, pagination behavior (implied by 'limit' and 'pid' parameters but not explained), or what the output format looks like. For a search tool with 4 parameters and no annotations, this leaves significant gaps in understanding how the tool behaves.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, efficient sentence that directly states the tool's function without unnecessary words. It's appropriately sized and front-loaded, with every word contributing to understanding the tool's purpose.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's complexity (4 parameters, no output schema, no annotations), the description is insufficient. It doesn't explain the return values, how results are structured, or behavioral aspects like pagination (implied by 'pid' but not described). For a search tool with multiple parameters and no structured output documentation, more context is needed to be complete.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The description mentions searching by 'name or name pattern', which aligns with the 'name' and 'name_pattern' parameters in the schema. However, schema description coverage is only 50% (2 out of 4 parameters have descriptions), and the description doesn't add meaning for 'limit' or 'pid' beyond what the schema provides. It compensates slightly but not fully for the coverage gap, meeting the baseline for moderate schema coverage.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's purpose: searching Gelbooru users by name or name pattern. It specifies the resource (users) and the search criteria (name/name_pattern), making the verb+resource combination explicit. However, it doesn't differentiate from sibling tools like search_posts or search_tags, which would require a 5.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides no guidance on when to use this tool versus alternatives. There's no mention of prerequisites, when-not-to-use scenarios, or comparisons with sibling tools like get_comments or get_character_tags that might involve user data. Usage is implied by the search functionality but not explicitly defined.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections. Dates show when Glama detected each change.

7 tool updatesv1.0.0Mar 8, 2026
- First observedbuild_prompt
- First observedget_character_tags
- First observedget_comments
- First observedget_deleted_posts
- First observedsearch_posts
- First observedsearch_tags
- First observedsearch_users

Install Server

RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

TDQS

A3.7/5.0

Disambiguation5/5

Each tool has a clearly distinct purpose: build_prompt generates prompts, get_character_tags fetches character metadata, get_comments retrieves comments, get_deleted_posts accesses deleted content, search_posts searches posts, search_tags searches tags, and search_users searches users. There is no overlap in functionality, making tool selection unambiguous.

Naming Consistency5/5

All tool names follow a consistent verb_noun pattern using snake_case: build_prompt, get_character_tags, get_comments, get_deleted_posts, search_posts, search_tags, and search_users. The naming is predictable and readable throughout the set.

Tool Count5/5

With 7 tools, the count is well-scoped for a Gelbooru-focused server, covering key operations like searching posts/tags/users, retrieving comments/deleted posts, and building prompts from character data. Each tool earns its place without being excessive or insufficient.

Completeness4/5

The tool set provides comprehensive coverage for interacting with Gelbooru's content and metadata, including search, retrieval, and prompt generation. Minor gaps exist, such as no tools for uploading posts or managing user accounts, but these are not critical for typical agent workflows and the core operations are well-covered.

Maintenance

ActivityInactive

ResponsivenessNo issues

Resources

GitHub Repository

Need Help?

Related Servers

Unclaimed servers have limited discoverability.

Looking for Admin?

If you are the server author, to access and configure the admin panel.

Related MCP Connectors

Remote Desktop CommanderOAuth
app.desktopcommander
Hosted MCP server connecting claude.ai, ChatGPT and other AI apps to your own computer
Shell Access OS Automation
214
hithereiamaliff-mcp-nextcloudOAuth
ai.smithery
A comprehensive Model Context Protocol (MCP) server that enables AI assistants to interact with yo…
Cloud Storage File Systems Workplace & Productivity
237
gread A
io.github.NitroRCr
An MCP server that gives your AI access to the source code and docs of all public github repos
Version Control Code Analysis Documentation Access
5361
mcp-qwen-imageOAuth
io.github.AceDataCloud
MCP server for Qwen Image 3 AI image generation
AI & Machine Learning Image & Video Processing
1

Related MCP Servers

Deepghs MCP
Art & Culture RAG Systems Image & Video Processing
citronlegacy
A
license
A
quality
D
maintenance
MCP server for the DeepGHS anime AI ecosystem. Dataset discovery, tag search, character dataset finder, and training pipeline code generation.
Updated 6 months ago (2026-03-08 23:38 UTC)
8
1
MIT
MyAnimeList MCP Server
Entertainment & Media Search
nicoaguerrero
A
license
B
quality
D
maintenance
MCP Server for interacting with the MyAnimeList API, allowing LLM clients to access and interact with anime, manga and more.
Updated a year ago (2025-06-06 22:30 UTC)
15
2
MIT
LemGen AI Design MCP
Image & Video Processing AI & Machine Learning Multimedia Processing
gptimage2prompts
A
license
A
quality
C
maintenance
Open-source MCP server for AI image and video creation, enabling prompt library search, prompt enhancement, and media generation from Claude Code, Cursor, and other MCP hosts.
Updated 2 months ago (2026-07-01 13:34 UTC)
8
MIT
Booru-Pictag-Get-MCP
Image & Video Processing AI & Machine Learning
echo-xianyu
A
license
A
quality
B
maintenance
An MCP server that searches booru image boards and cleans their tags into ready-to-use AI-art prompts for Stable Diffusion and similar models.
Updated a month ago (2026-08-07 14:53 UTC)
9
10
MIT

Latest Blog Posts

Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)
By Om-Shree-0709 on July 25, 2026.
mcp
Agent Identity
OAuth 2.1
Your AI Chatbot Just Exposed Your CEO's Salary to an Intern
By Om-Shree-0709 on July 2, 2026.
Agent Identity
MCP Security
OAuth Delegation
Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)
By Om-Shree-0709 on June 30, 2026.
Agentic Ai
Prompt Injection
WebAssembly

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/citronlegacy/gelbooru-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server