WebMCP

DeveloperWebMCP verified

h3.dev WebMCP tools

H(TTP) server framework built on top of web standards for high performance and composability.

6 tools1 methodsspec API surface

What can an agent do with h3.dev WebMCP tools?

H(TTP) server framework built on top of web standards for high performance and composability. This page documents every listed tool, the action or answer it provides, its installation command, and the input fields an agent should send.

WebMCP tools on h3.dev

Tool 1 of 6WebMCPAnswer

search_docs

Search pages and sections in H3. Returns ranked matches with previews, route paths and optional heading anchors. Use `read_page` to read a result.

How to install

Open the h3.dev website and ask your browser agent to use search_docs

Install browse first, then run the command in a terminal. WebMCP tools run directly on the website and do not need a package install.

Run with an agent

Use the search_docs tool on h3.dev with query: <string>, limit: <integer>. Return the structured result and cite the source page.

Input contract

  • query string Search terms, e.g. 'deploy to vercel' or 'defineNitroPlugin'.
  • limit integer Maximum number of results (1-50, default 10).

Open the source definition

Tool 2 of 6WebMCPAnswer

list_pages

List pages in the documentation navigation with titles, paths, URLs and available descriptions. Use for browsing; use `search_docs` for a specific topic.

How to install

Open the h3.dev website and ask your browser agent to use list_pages

Install browse first, then run the command in a terminal. WebMCP tools run directly on the website and do not need a package install.

Run with an agent

Use the list_pages tool on h3.dev. Return the structured result and cite the source page.

Input contract

    Open the source definition

    Tool 3 of 6WebMCPAnswer

    get_project_info

    Get project metadata and links: website, source repository, issues, releases, community, `llms.txt` bundles and versions.

    How to install

    Open the h3.dev website and ask your browser agent to use get_project_info

    Install browse first, then run the command in a terminal. WebMCP tools run directly on the website and do not need a package install.

    Run with an agent

    Use the get_project_info tool on h3.dev. Return the structured result and cite the source page.

    Input contract

      Open the source definition

      Tool 4 of 6WebMCPAnswer

      read_page

      Read a documentation page as Markdown by route path. Links in it are route paths for this tool. If `truncated`, continue with `nextOffset` as `offset`. Generated pages have no Markdown source.

      How to install

      Open the h3.dev website and ask your browser agent to use read_page

      Install browse first, then run the command in a terminal. WebMCP tools run directly on the website and do not need a package install.

      Run with an agent

      Use the read_page tool on h3.dev with path: <string>, offset: <integer>, maxLength: <integer>. Return the structured result and cite the source page.

      Input contract

      • path string Route path of the page, e.g. '/guide/getting-started'.
      • offset integer Character offset; use `nextOffset` to continue (default 0).
      • maxLength integer Maximum Markdown characters to return (1-40000, default 40000).

      Open the source definition

      Tool 5 of 6WebMCPAnswer

      get_current_page

      Get metadata for the page the user is viewing: path, URL, title, description and heading outline.

      How to install

      Open the h3.dev website and ask your browser agent to use get_current_page

      Install browse first, then run the command in a terminal. WebMCP tools run directly on the website and do not need a package install.

      Run with an agent

      Use the get_current_page tool on h3.dev. Return the structured result and cite the source page.

      Input contract

        Open the source definition

        Tool 6 of 6WebMCPAction

        navigate

        Open a documentation page in the user's browser, optionally at a heading. Use only when the user asks to navigate; use `read_page` to inspect content without moving them.

        How to install

        Open the h3.dev website and ask your browser agent to use navigate

        Install browse first, then run the command in a terminal. WebMCP tools run directly on the website and do not need a package install.

        Run with an agent

        Use the navigate tool on h3.dev with path: <string>, hash: <string>. Return the structured result and cite the source page.

        Input contract

        • path string Route path to open, e.g. '/guide/getting-started'.
        • hash string Heading anchor to scroll to, e.g. '#installation'.

        Open the source definition