Create Agent With Sanity Context

Helps you set up AI agents that can query and reason over Sanity CMS content through the Agent Context MCP server. Instead of just doing semantic search over embedded text, agents get your actual schema and learn GROQ, so they can filter by real fields, follow references, and understand content relationships. Walks through Studio plugin setup, MCP connection patterns, and how to write instructions that teach the production agent your domain. The implementation works with any LLM provider. Useful when you want a chatbot or assistant that needs to navigate structured content intelligently, not just find similar text. The distinction between base URLs and document URLs matters for configuration management.

skills.sh installs: 512
GitHub stars: 4
last updated: Jul 14, 2026

View on GitHub

Install

$ npx -y skills add sanity-io/agent-context --skill create-agent-with-sanity-context --agent claude-code

Installs into .claude/skills of the current project.

Files

Build an Agent with Sanity Context

Give AI agents intelligent access to your Sanity content. Unlike embedding-only approaches, Sanity Context is schema-aware—agents can reason over your content structure, query with real field values, follow references, and combine structural filters with semantic search.

Sanity Context gives agents your schema and teaches them GROQ, but it can't know your domain. You close that gap through the Instructions field (dataset-specific query guidance) and optionally the system prompt (agent behavior and tone).

Three actors in this workflow: