# get_foundations

Get the cross-cutting Foundations rules for a stack — accessibility requirements not tied to a single component: focus states, landmarks, headings, contrast, page structure, use of color. Retrieve these on every UI task, not just page-level work: each rule carries a scope (utility, style, component, layout, page) that determines whether it applies to the current change. Optionally pass scope to return only rules matching one or more of those buckets.

Agent View of the PolicyLayer registry record for `get_foundations`. HTML page: https://policylayer.com/tools/a11y-context-mcp-server/get-foundations

## Facts

- Tool: `get_foundations`
- Server: A11y Context (`@a11y-context/mcp-server`) — https://policylayer.com/tools/a11y-context-mcp-server.md
- Install: `npx -y @a11y-context/mcp-server`
- Homepage: https://www.npmjs.com/package/@a11y-context/mcp-server
- Risk category: Read (Low risk)
- Registry record: grade A, identity unverified
- Server rate-limited: no
- Parameters: 2
- Recommended policy verdict: Allowed

## Parameters

| Parameter | Type | Required | Description |
| --- | --- | --- | --- |
| `scope` | array | no | Optional. Return only rules whose `scope` includes at least one of these buckets. Valid buckets differ by stack and are declared by that stack's own ruleset: we |
| `stack` | string | no | 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.

## Example call (MCP tools/call, JSON-RPC 2.0)

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "get_foundations",
    "arguments": {}
  }
}
```

## Why get_foundations is rated Low

Even though get_foundations 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.

## Use case

AI agents call get_foundations 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.

## Recommended policy (PolicyLayer)

Verdict: **Allowed**. Enforced by the PolicyLayer MCP gateway (https://policylayer.com/mcp-gateway) before a call reaches A11y Context:

```json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "get_foundations": {}
  }
}
```

## Other tools on A11y Context (2)

- `get_pattern` — Read — https://policylayer.com/tools/a11y-context-mcp-server/get-pattern.md
- `list_patterns` — Read — https://policylayer.com/tools/a11y-context-mcp-server/list-patterns.md

## For agents

This record is a snapshot. Live verdicts and the full registry:

- Check every server in your MCP config at once: `npx -y policylayer stack`
- Vet a server before you add it: install the mcp-precheck skill — `npx skills add https://policylayer.com` (skill text: https://policylayer.com/skill.md)
- Query the registry over MCP: endpoint `https://api.policylayer.com/mcp` — tools `check_mcp_server`, `check_mcp_stack`, `check_tool`, `search_registry`, `get_change_events`

---

Source: the PolicyLayer MCP registry — one continuously verified record per MCP server. Full record: https://policylayer.com/registry?q=a11y-context-mcp-server · API: https://policylayer.com/registry/api · Policy library: https://policylayer.com/policies/a11y-context-mcp-server