Schema | mcp-web

mcp-web

Describes the environment variables required to run the server.

Name	Required	Description	Default
`MCPWEB_TIMEOUT`	No	Per-request timeout, in seconds.	20
`MCPWEB_ALLOWLIST`	No	Comma-separated hosts; when set, nothing else is reachable.
`MCPWEB_MAX_BYTES`	No	Response body cap in bytes.	2000000
`MCPWEB_USER_AGENT`	No	User agent string sent on every request.	Chrome-ish
`MCPWEB_ALLOW_PRIVATE`	No	Set to 1 to let the model reach localhost and your LAN.	0
`MCPWEB_MAX_REDIRECTS`	No	Redirect hop limit.	5

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.

Features and capabilities supported by this server

Protocol revision2025-11-25

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

Functions exposed to the LLM to take actions

Name	Description
web_searchA	Search the web with DuckDuckGo. Returns a list of results with title, url and snippet. Follow up with fetch_url on any result whose full text you need.
fetch_urlA	Fetch a web page and return its main content as markdown. Use this for ordinary pages and articles. If the result looks empty or is obviously a JavaScript shell, retry with render_page.
http_requestA	Make an arbitrary HTTP request and return the raw response. Use this for JSON APIs. For reading web pages prefer fetch_url, which strips navigation and boilerplate.

Interactive templates invoked by user choice

Name	Description
No prompts

Contextual data attached and managed by the client

Name	Description
No resources

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

curl -X GET 'https://glama.ai/api/mcp/v1/servers/MrDadpool/mcp-web'

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