get_pattern
Get the full accessibility specification for one pattern by id (ids come from list_patterns). Returns the pattern's sections: must_haves (non-negotiable WCAG 2.2 AA requirements — implement all of them), donts (anti-patterns — never produce), golden_pattern (a reference implementation to model), ...
This record as markdown: /tools/a11y-context-mcp-server/get-pattern.md
What get_pattern does on A11y Context
AI agents call get_pattern to retrieve information from A11y Context without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
| Parameter | Type | Required | Description |
|---|---|---|---|
id | string | Yes | |
stack | string | — | Target platform and framework. Defaults to 'web/react'. A stack is available only if this release bundles content for it; 'android/compose' is reserved and not |
Parameters from the server's own tool schema.
Why get_pattern is rated Low
Even though get_pattern only reads data, uncontrolled read access leaks sensitive information and racks up API costs: an agent caught in a retry loop can make thousands of calls a minute without anyone noticing.
Attacks that exploit this kind of access
The rule that runs get_pattern safely
PolicyLayer is an MCP gateway: it sits between your AI agents and A11y Context, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For get_pattern, this is the rule to start with:
get_pattern is read-only, so it stays allowed. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect A11y Context, apply this rule, and every get_pattern call is checked against it from then on.
Questions about get_pattern
Get the full accessibility specification for one pattern by id (ids come from list_patterns). Returns the pattern's sections: must_haves (non-negotiable WCAG 2.2 AA requirements — implement all of them), donts (anti-patterns — never produce), golden_pattern (a reference implementation to model), and customizable (allowed variations). Call this for each pattern you selected before writing UI code. It is categorised as a Read tool in the A11y Context MCP Server, which means it retrieves data without modifying state.
get_pattern accepts 2 parameters: id, stack. Required: id. The full parameter table on this page comes from the server's own tool schema.
Register the A11y Context MCP server in PolicyLayer and add a rule for get_pattern: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches A11y Context. Nothing to install.
get_pattern is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the get_pattern rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for get_pattern. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
get_pattern is provided by the A11y Context MCP server (@a11y-context/mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on A11y Context, and thousands of servers like it.
This server
Across the catalogue