Schema | websearch-mcp

Server Configuration

Describes the environment variables required to run the server.

Name	Required	Description	Default
`LLM_MODEL`	Yes	Model name for chat completions
`VLM_MODEL`	No	Model name for image description (defaults to LLM_MODEL)
`LLM_API_KEY`	Yes	API key for the LLM endpoint
`LLM_TIMEOUT`	No	LLM request timeout in seconds	60
`SEARXNG_URL`	Yes	Base URL of SearXNG instance
`VLM_API_KEY`	No	API key for VLM endpoint (defaults to LLM_API_KEY)
`LLM_BASE_URL`	Yes	OpenAI-compatible endpoint base URL
`VLM_BASE_URL`	No	OpenAI-compatible endpoint for VLM (defaults to LLM_BASE_URL)
`FETCH_TIMEOUT`	No	Per-page fetch timeout in seconds	30
`MAX_IMAGE_SIZE`	No	Max image size in bytes (10MB)	10485760
`MAX_CONTENT_SIZE`	No	Max content size in bytes (5MB)	5242880
`CACHE_MAX_ENTRIES`	No	Max cache entries before LRU eviction	1000
`CACHE_TTL_SECONDS`	No	Cache TTL in seconds (0 to disable)	900
`DEFAULT_MAX_RESULTS`	No	Default result count for web_search	10

Capabilities

Features and capabilities supported by this server

Capability	Details
`tools`	{ "listChanged": false }
`prompts`	{ "listChanged": false }
`resources`	{ "subscribe": false, "listChanged": false }
`experimental`	{}

Tools

Functions exposed to the LLM to take actions

Name Description

Name	Description
web_search	Search the web using SearXNG, fetch top result pages, and synthesize with LLM. `Args: query: The search query string. max_results: Maximum number of results to return (default: 10). allowed_domains: Only include results from these domains. blocked_domains: Exclude results from these domains.`
webfetch	Fetch a single URL, extract content, and process with LLM. `Args: url: The URL to fetch. prompt: Optional instruction for LLM processing. If omitted, provides a general summary.`
image_description	Describe an image using a vision language model. `Args: image: Either a base64-encoded string containing the image data, or an absolute filesystem path pointing to an image file. Returns: JSON string with description, success status, and error info.`

web_search

Search the web using SearXNG, fetch top result pages, and synthesize with LLM.

Args:
    query: The search query string.
    max_results: Maximum number of results to return (default: 10).
    allowed_domains: Only include results from these domains.
    blocked_domains: Exclude results from these domains.

webfetch

Fetch a single URL, extract content, and process with LLM.

Args:
    url: The URL to fetch.
    prompt: Optional instruction for LLM processing. If omitted, provides a general summary.

image_description

Describe an image using a vision language model.

Args:
    image: Either a base64-encoded string containing the image data,
           or an absolute filesystem path pointing to an image file.

Returns:
    JSON string with description, success status, and error info.

Prompts

Interactive templates invoked by user choice

Name	Description
No prompts

Resources

Contextual data attached and managed by the client

Name	Description
No resources

websearch-mcp

Server Configuration

Capabilities

Tools

Prompts

Resources

Latest Blog Posts

MCP directory API