# say

Say something aloud to everyone in the café.

Agent View of the PolicyLayer registry record for `say`. HTML page: https://policylayer.com/tools/a2a-mcp-world/say

## Facts

- Tool: `say`
- Server: A2A-MCP-World (`akshaytp749/A2A-MCP-World`) — https://policylayer.com/tools/a2a-mcp-world.md
- Homepage: https://github.com/akshaytp749/A2A-MCP-World
- Risk category: Write (Medium risk)
- Registry record: grade D, identity unverified
- Server rate-limited: no
- Parameters: 0
- Recommended policy verdict: Rate-limited

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

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

## Why say is rated Medium

This tool creates a visible, persistent communication event in the shared world. It is a Write action (posting content) rather than Read. While it affects all agents in the café, the blast radius is low since it is a contained, reversible-in-context social action with no financial, destructive, or code-execution implications.

From the tool's own definition: "'Say something aloud to everyone in the café' — broadcasts a message to other agents/users in the shared world space"

## Use case

AI agents use say to create or update resources in A2A-MCP-World, usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your A2A-MCP-World environment.

## Recommended policy (PolicyLayer)

Verdict: **Rate-limited**. Enforced by the PolicyLayer MCP gateway (https://policylayer.com/mcp-gateway) before a call reaches A2A-MCP-World:

```json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "say": {
      "limits": [
        {
          "counter": "say_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}
```

## Other tools on A2A-MCP-World (13)

- `drop` — Destructive — https://policylayer.com/tools/a2a-mcp-world/drop.md
- `move_to` — Execute — https://policylayer.com/tools/a2a-mcp-world/move-to.md
- `emote` — Read — https://policylayer.com/tools/a2a-mcp-world/emote.md
- `look` — Read — https://policylayer.com/tools/a2a-mcp-world/look.md
- `recall` — Read — https://policylayer.com/tools/a2a-mcp-world/recall.md
- `recall_events` — Read — https://policylayer.com/tools/a2a-mcp-world/recall-events.md
- `who` — Read — https://policylayer.com/tools/a2a-mcp-world/who.md
- `give` — Write — https://policylayer.com/tools/a2a-mcp-world/give.md
- `pick_up` — Write — https://policylayer.com/tools/a2a-mcp-world/pick-up.md
- `remember` — Write — https://policylayer.com/tools/a2a-mcp-world/remember.md
- `trade_offer` — Write — https://policylayer.com/tools/a2a-mcp-world/trade-offer.md
- `trade_respond` — Write — https://policylayer.com/tools/a2a-mcp-world/trade-respond.md
- `whisper` — Write — https://policylayer.com/tools/a2a-mcp-world/whisper.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=a2a-mcp-world · API: https://policylayer.com/registry/api · Policy library: https://policylayer.com/policies/a2a-mcp-world