Loading pattern preview
BlocksTools & Utilities
Tool API Context
Tool API Context
Pass arbitrary context from generateText/streamText to tool execution via experimental_context. Access context in tool execute functions for dynamic behavior.
Use this when you call generateText or streamText directly and want one tool definition to adapt to each user's preferences or session settings.
Loading pattern preview
Problems solved
Technical challenges this implementation handles out of the box.
- Pass request-scoped values through experimental_context
- Read shared context inside tool execute without model-supplied secrets
- Customize tool behavior per user or session without forking tool definitions
Use cases
Products and workflows this pattern is designed to support.
- User-preference-aware tools
- Per-tenant API credential injection
- Session-scoped tool configuration
- Context-aware tool demos
Compare with
Similar patterns, and when each one is the better fit.
Tool Context: experimental_contextUse this when a multi-tenant agent must scope every tool call to the authenticated request so a prompt injection cannot reach another user's data.
Tool ExecutionUse this when your chat app calls tools and you want each call's input, output, and status rendered inline as it streams.
Multi-Step Tool PatternUse this when a chat agent must call several typed tools in a row, feeding each result into the next step, with a step limit to stop runaway loops.
Dynamic ToolUse this when you need to build tools with dynamicTool whose Zod schemas change per request, like a converter whose inputs differ by conversion type.
Setup
Requirements, wiring steps, and what this pattern adds to your project.
Getting started
Pick how you want to pull this pattern in. Then wire env vars and routes the same way.
- 1
Download → Next.js app
Use Download → Next.js app in the preview toolbar. You get a zip scaffold (Pro downloads rewrite preview `/view/.../api/*` paths to `/api/*` automatically).
- 2
Extract the zip and install dependencies
Unzip the archive, then run `pnpm install` (or npm / yarn) in the project folder.
- 3
Fill .env.local
The download includes .env.local placeholders when needed. Add real values for: OPENAI_API_KEY.
- 4
Customize the agent and tool files
Adapt prompts, tools, and stop conditions in the generated project for your product.
- 5
Run the app and open the pattern route
Run `pnpm dev`, open the setup/checklist page if present, then navigate to the generated pattern route and verify responses.
Environment variables
OPENAI_API_KEYGet key
Capabilities
AI SDK APIs
streamTextconvertToModelMessagestooluseChatexperimental_contextProviders
OpenAI
Files added
6 files
app/page.tsxapp/layout.tsxapp/api/tool-context/route.tscomponents/context-demo.tsxtools/weather.tstools/weather-ui.tsx
Dependencies
15 total
npm packages
7AISDKshadcn/uilucide-reactNext.jsReactstreamdownZod
Registry components
alertemptyinput-groupseparatormessage-scrollermessagebubbletooltip
Critical files
2 files
tool-context/route.tsAPI route demonstrating experimental_context passing. Derives context from user input and passes it via experimental_context to streamText, making it available to all tools.
tools/weather.tsWeather tool demonstrating how to access experimental_context in the execute function's second parameter. Shows the receiving side of the context pattern.
Requirements
- Complexity
- Beginner
- Setup time
- ~5 minutes
- Node
- 24+
- Memory
- 512MB
