Open Agent Search
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": true
} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
| experimental | {
"tasks": {
"list": {},
"cancel": {},
"requests": {
"tools": {
"call": {}
},
"prompts": {
"get": {}
},
"resources": {
"read": {}
}
}
}
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| search_webA | Search the web for text content. Args: query: Search query string (required) region: Region code like 'us-en', 'uk-en', 'in-en' (default: 'us-en') max_results: Maximum number of results, 1-100 (default: 10) safesearch: Safe search level: 'on', 'moderate', 'off' (default: 'moderate') Returns: List of search results with title, body, and url |
| search_imagesA | Search for images. Args: query: Image search query (required) region: Region code (default: 'us-en') max_results: Maximum results, 1-100 (default: 10) safesearch: Safe search: 'on', 'moderate', 'off' (default: 'moderate') size: Image size filter: 'small', 'medium', 'large', 'wallpaper' color: Color filter: 'color', 'monochrome', 'red', 'orange', 'yellow', 'green', 'blue', 'purple', 'pink', 'brown', 'black', 'gray', 'teal', 'white' Returns: List of images with title, image url, thumbnail, source, and more |
| search_videosB | Search for videos. Args: query: Video search query (required) region: Region code (default: 'us-en') max_results: Maximum results, 1-100 (default: 10) safesearch: Safe search: 'on', 'moderate', 'off' (default: 'moderate') resolution: Video resolution: 'high', 'standard' duration: Video duration: 'short', 'medium', 'long' Returns: List of videos with title, description, url, duration, and more |
| search_newsA | Search for news articles. Args: query: News search query (required) region: Region code (default: 'us-en') max_results: Maximum results, 1-100 (default: 10) safesearch: Safe search: 'on', 'moderate', 'off' (default: 'moderate') timelimit: Time limit: 'd' (day), 'w' (week), 'm' (month) Returns: List of news articles with title, body, url, date, and source |
| search_booksB | Search for books. Args: query: Book search query (required) max_results: Maximum results, 1-100 (default: 10) Returns: List of books with title, authors, and links |
| search_everythingA | Search all sources at once (text, images, videos, news, books). Args: query: Search query (required) region: Region code (default: 'us-en') max_results_per_type: Results per category, 1-20 (default: 5) safesearch: Safe search: 'on', 'moderate', 'off' (default: 'moderate') Returns: Dictionary with results from all search types |
| fetch_contentA | Fetch and extract content from a URL with intelligent trimming (non-blocking). Args: url: URL to fetch content from (required) timeout: Request timeout in seconds, 5-30 (default: 10) max_length: Maximum content length in characters, 100-20000 (default: 2000) Returns: Extracted content with title, description, and intelligently trimmed text |
| fetch_multiple_contentsA | Fetch and extract content from multiple URLs in parallel (max 10, non-blocking). Args: urls: List of URLs to fetch (required, max 10) timeout: Request timeout in seconds, 5-30 (default: 10) max_length: Maximum content length per URL, 100-20000 (default: 2000) Returns: Dictionary with list of extracted content from each URL |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 8 tools
Most tools are cleanly split by media type (web, books, images, videos, news) plus single vs. batch fetching, so boundaries are clear. The only real overlap is search_web versus search_everything, which both return text results, and an agent could plausibly pick the wrong one for a plain web query.
All names are snake_case and follow a predictable verb-first pattern: search_<media> for queries and fetch_content / fetch_multiple_contents for retrieval. The singular/plural contrast on the fetch pair is deliberate and readable.
Eight tools is well-scoped for a search-and-fetch server: five media-specific searches, one aggregate search, and two content fetchers. Each tool earns its place with no redundant entries.
The surface covers every common retrieval mode (text, books, images, videos, news, aggregate) plus single and parallel URL content extraction, with rich filters per media type and max_results up to 100 compensating for the lack of pagination. No obvious dead ends for a search-oriented domain.