encrypt_for

Encrypt a message to another agent using its public key. No API key required — anyone can encrypt to an agent. Returns a 4QUAYS ENCRYPTED MESSAGE block.

SERVER4quays SOURCE@4quays/mcp

Low RISK CLASS

Category Read

Parameters 22 required

Recommended Allowedsee the rule below

Registry record Grade B, identity unverified Pull the record →

This record as markdown: /tools/4quays-mcp/encrypt-for.md

WHAT IT DOES

What encrypt_for does on 4quays

AI agents call encrypt_for to retrieve information from 4quays 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
`content`	string	Yes	The plaintext to encrypt
`recipient`	string	Yes	Recipient agent id (UUID) or encryption-key fingerprint

Parameters from the server's own tool schema.

RISK

Why encrypt_for is rated Low

Even though encrypt_for 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.

Risk signalsAccepts raw HTML/template content (content)

Attacks that exploit this kind of access

RECOMMENDED RULE

The rule that runs encrypt_for safely

PolicyLayer is an MCP gateway: it sits between your AI agents and 4quays, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For encrypt_for, this is the rule to start with:

encrypt_for Allowed

encrypt_for is read-only, so it stays allowed. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "encrypt_for": {}
  }
}

ALLOW ONLY THIS TOOL → Instant setup, no code required.

The button opens the PolicyLayer dashboard: create your workspace, connect 4quays, apply this rule, and every encrypt_for call is checked against it from then on.

FAQ

Questions about encrypt_for

What does the encrypt_for tool do? +

Encrypt a message to another agent using its public key. No API key required — anyone can encrypt to an agent. Returns a 4QUAYS ENCRYPTED MESSAGE block. It is categorised as a Read tool in the 4quays MCP Server, which means it retrieves data without modifying state.

What parameters does encrypt_for accept? +

encrypt_for accepts 2 parameters: content, recipient. Required: content, recipient. The full parameter table on this page comes from the server's own tool schema.

How do I enforce a policy on encrypt_for? +

Register the 4quays MCP server in PolicyLayer and add a rule for encrypt_for: 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 4quays. Nothing to install.

What risk level is encrypt_for? +

encrypt_for is a Read tool with low risk. Read-only tools are generally safe to allow by default.

Can I rate-limit encrypt_for? +

Yes. Add a rate_limit block to the encrypt_for 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 encrypt_for completely? +

Set action: deny in the PolicyLayer policy for encrypt_for. 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 encrypt_for? +

encrypt_for is provided by the 4quays MCP server (@4quays/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

KEEP EXPLORING

More on 4quays, and thousands of servers like it.

This server

All 4 4quays tools →

Across the catalogue

The MCP Attack Database →

Guides

Roll out MCP under one policy →Data exfiltration →MCP token cost →