Building with AI

Tempo documentation is built with AI-first principles, providing multiple features to make documentation accessible to LLMs and AI assistants.

llms.txt

The docs automatically generate llms.txt files for LLM consumption:

/llms.txt – A concise index of all pages with titles and descriptions
/llms-full.txt – Complete documentation content in a single file

These files are generated at build time and served at the root of the site.

Markdown Rendering for AI Agents

AI user agents are automatically detected and served raw Markdown instead of rendered HTML. This provides better token efficiency and easier parsing for LLMs.

Supported AI Agents

Popular user agents that are automatically detected:

OpenAI: GPTBot, ChatGPT-User
Anthropic: ClaudeBot, claude-web
Google: Googlebot

See the full list of supported agents for the most up-to-date list.

Manual Markdown Access

Any page can be accessed as Markdown by appending .md to the URL:

https://docs.tempo.xyz/quickstart/integrate-tempo.md

This is useful for copying documentation into AI conversations or for custom integrations.

The docs include a built-in "Ask AI" menu (⌘I / Ctrl+I) that provides:

Open in ChatGPT/Claude: Opens the current page context in popular AI assistants
Copy page for AI: Copies the page content as Markdown to your clipboard
View as Markdown: Opens the raw Markdown version of the current page
Copy MCP URL: Copies the MCP server URL for AI assistant configuration

MCP Server

The docs include a built-in Model Context Protocol (MCP) server that allows AI assistants to navigate documentation and source code programmatically.

claude mcp add --transport http tempo https://docs.tempo.xyz/api/mcp

Connecting AI Assistants

Configure your AI assistant to connect to the MCP server:

{
  "mcpServers": {
    "tempo-docs": {
      "url": "https://docs.tempo.xyz/api/mcp"
    }
  }
}

Available Tools

The MCP server exposes these tools to AI assistants:

Tool	Description
`list_pages`	List all documentation pages with their paths
`read_page`	Read the content of a specific documentation page
`search_docs`	Search documentation for a query string

The MCP server also provides access to source code repositories:

Tool	Description
`list_sources`	List available source code repositories
`list_source_files`	List files in a directory
`read_source_file`	Read a source code file
`get_file_tree`	Get a recursive file tree
`search_source`	Search source code for a pattern

Available source repositories:

tempoxyz/tempo – Tempo node implementation
tempoxyz/tempo-ts – TypeScript SDK
paradigmxyz/reth – Reth Ethereum client
foundry-rs/foundry – Foundry development toolkit
wevm/viem – TypeScript interface for Ethereum
wevm/wagmi – React hooks for Ethereum

Agent Skills

Install the Tempo Agent Skills to give AI coding agents (Amp, Claude Code, etc.) access to Tempo documentation, source code via MCP, and examples. Check out tempoxyz/agent-skills for more info on available skills.

Installation

npx skills add tempoxyz/agent-skills

Or manually:

$ git clone https://github.com/tempoxyz/agent-skills.git
$ cp -r agent-skills/skills/tempo ~/.config/agents/skills/

Or add to your project's .agents/skills/ directory for project-specific access.

Usage

Once installed, the skill is automatically available. The agent will use it when relevant tasks are detected.

Examples:

How do I create a TIP-20 stablecoin?

Show me how fee sponsorship works in Viem

Search the Tempo source for transaction validation