send_contract · QuickContract MCP: Risk & Policy

WHAT IT DOES

What send_contract does on QuickContract MCP

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

WHY IT NEEDS A POLICY

Why send_contract needs a policy

The tool modifies contract state by sending it to recipients and triggers email delivery with tokenized links. While it does not execute arbitrary code or delete data, it commits a contract to recipients and creates binding communication artifacts.

From the tool's definition Tool description states it 'Send[s] a draft contract to its recipients' and 'Recipients receive an email with a tokenized claim link.' This is a write operation that creates/modifies the contract state (transitions it from draft to sent) and initiates…

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

send_contract Rate-limited

send_contract stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "send_contract": {
      "limits": [
        {
          "counter": "send_contract_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

LIMIT THIS TOOL →

Instant setup, no code required.

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

FAQ

Questions about send_contract

What does the send_contract tool do? +

Send a draft contract to its recipients. Recipients receive an email with a tokenized claim link. When the caller is an agent, recipient email domains are checked against mandate.limits.allowedCounterpartyDomains. It is categorised as a Write tool in the QuickContract MCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on send_contract? +

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

What risk level is send_contract? +

send_contract is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Can I rate-limit send_contract? +

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

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

send_contract is provided by the QuickContract MCP server (quickcontractio/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.