Skip to content

AI Tools for Aptos Development

Aptos provides first-class support for AI-powered development workflows. Whether you’re using an AI coding assistant or an AI chat tool, you can give it deep knowledge of the Aptos blockchain, Move language, SDKs, and APIs.

The AskAptos chatbot is built into the documentation site — look for it in the top-right corner of the navigation bar. It can answer questions about Aptos concepts, help you plan implementations, and point you to the right documentation pages.

The Model Context Protocol (MCP) lets AI coding tools directly call Aptos APIs, query on-chain data, and generate correct Aptos code — without needing to copy-paste documentation.

Aptos Agent Skills provides pre-built AI skills that give coding assistants deep Aptos expertise — covering Move smart contracts, the TypeScript SDK, and full-stack dApp scaffolding.

Terminal window
npx skills add aptos-labs/aptos-agent-skills

This command uses the Skills CLI, which is invoked via npx. If npx skills is not available in your environment, ensure you have Node.js and npm installed and refer to the Skills CLI documentation for installation and troubleshooting details.

The LLMs.txt standard provides machine-readable documentation feeds that AI tools can ingest to understand the full Aptos documentation. We publish three feeds to suit different context window sizes:

FeedURLBest for
llms.txt/llms.txtStructured index with page titles, descriptions, and per-page .md links
llms-small.txt/llms-small.txtCondensed docs for smaller context windows
llms-full.txt/llms-full.txtFull documentation — all pages concatenated

Some clients resolve /.well-known/llms.txt; production serves the same index via a redirect to /llms.txt (https://aptos.dev/.well-known/llms.txt).

The llms.txt router also surfaces machine-readable API links—/aptos-spec.json (OpenAPI 3 JSON for the node REST API) and /rest-api (HTML reference)—plus MCP, Agent Skills, Explorer, GitHub, standards, and Indexer GraphQL .md links in one place.

The docs site publishes a handful of standardized discovery documents so coding agents can bootstrap from a single root. Every page also returns a Link response header and matching <link rel="…"> tags that advertise the same URLs.

EndpointPurpose
/.well-known/api-catalogRFC 9727 linkset pointing at the REST API spec, documentation, Indexer GraphQL, and the LLMs.txt feeds.
/.well-known/mcp/server-card.jsonMCP Server Card (SEP-2127) describing the @aptos-labs/aptos-mcp server.
/.well-known/agent-skills/index.jsonAgent Skills Discovery index for aptos-agent-skills with per-skill SHA-256 digests.
/.well-known/oauth-protected-resourceOAuth 2.0 Protected Resource Metadata (RFC 9728) for the Google-authenticated Aptos Testnet Faucet. Lists the resource identifier, authorization servers, and supported scopes.
/.well-known/openid-configurationOpenID Connect Discovery 1.0 document advertising the issuer, authorization/token endpoints, JWKS URI, and supported grant types used by the Aptos Testnet Faucet sign-in flow.
/.well-known/oauth-authorization-serverOAuth 2.0 Authorization Server Metadata (RFC 8414) mirror of the OIDC discovery document for clients that prefer the pure OAuth 2.0 endpoint name.
/robots.txtIncludes Content Signals (ai-train=yes, search=yes, ai-input=yes) so agents know Aptos docs are opted in.

The OAuth/OIDC discovery documents apply only to the Aptos Testnet Faucet; the rest of aptos.dev is unauthenticated public documentation. Agents that need to fund a testnet account can call /.well-known/oauth-protected-resource to discover the faucet’s resource identifier and the OIDC issuers (Firebase + Google) that mint the bearer tokens it accepts on Authorization: Bearer ….

Any docs URL that has a .md mirror (for example /build/sdks/build/sdks.md) will also respond to Accept: text/markdown with Content-Type: text/markdown:

Terminal window
curl -H "Accept: text/markdown" https://aptos.dev/build/sdks

HTML stays the default for browsers that send the usual Accept: text/html.

Chrome and other browsers that implement the WebMCP proposal can discover the following tools on every docs page via navigator.modelContext: aptos-docs.search, aptos-docs.open-doc, aptos-docs.fetch-doc-markdown, and aptos-docs.list-llms-feeds.