bounded_answer · Recall MCP: Risk & Policy

WHAT IT DOES

What bounded_answer does on Recall

AI agents invoke bounded_answer to trigger actions in Recall. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.

WHY IT NEEDS A POLICY

Why bounded_answer needs a policy

This tool executes a generation operation using the Recall memory graph to produce bounded answers. It's not a simple read/query — it actively processes and generates output by running logic against stored memory. Since the description is vague, confidence is moderate, but 'Generate' implies an Execute-class operation rather than a passive retrieval.

From the tool's definition 'Generate an answer bounded by Recall' — triggers a generation/execution process using the memory graph

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

bounded_answer Rate-limited

bounded_answer stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "bounded_answer": {
      "limits": [
        {
          "counter": "bounded_answer_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

RATE-LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches Recall, so you can run agents against it safely.

FAQ

Questions about bounded_answer

What does the bounded_answer tool do? +

Generate an answer bounded by Recall. It is categorised as a Execute tool in the Recall MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on bounded_answer? +

Register the Recall MCP server in PolicyLayer and add a rule for bounded_answer: 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 Recall. Nothing to install.

What risk level is bounded_answer? +

bounded_answer is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.

Can I rate-limit bounded_answer? +

Yes. Add a rate_limit block to the bounded_answer 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.

How do I block bounded_answer completely? +

Set action: deny in the PolicyLayer policy for bounded_answer. 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.

What MCP server provides bounded_answer? +

bounded_answer is provided by the Recall MCP server (yash194/recall). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.