agent_draft_create
Stage an action (e.g. send a nudge, upsert a CRM contact, export a CSV) as a PENDING draft in the workspace for the human to approve. The draft is persisted in max-agent
This record as markdown: /tools/digital-crew-technologies-max-mcp-server/agent-draft-create.md
What agent_draft_create does on Max MCP Server
AI agents use agent_draft_create to create or update resources in Max MCP Server, usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Max MCP Server environment.
Why agent_draft_create is rated Medium
The tool creates or modifies data (stages drafts, upserts contacts) in a reversible manner. While it prepares actions for execution, the actual execution requires human approval, making it a Write rather than Execute operation. The severity is medium because upserted CRM contacts and staged actions could affect business workflows, but the reversibility and approval gate limit the blast radius.
From the tool's definition Tool description states it will "Stage an action" and "upsert a CRM contact" and "persist[] in max-agent", which are reversible write operations. The draft is explicitly marked PENDING and requires human approval before execution.
Attacks that exploit this kind of access
The rule that runs agent_draft_create safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Max MCP Server, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For agent_draft_create, this is the rule to start with:
agent_draft_create 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.
The button opens the PolicyLayer dashboard: create your workspace, connect Max MCP Server, apply this rule, and every agent_draft_create call is checked against it from then on.
Questions about agent_draft_create
Stage an action (e.g. send a nudge, upsert a CRM contact, export a CSV) as a PENDING draft in the workspace for the human to approve. The draft is persisted in max-agent. It is categorised as a Write tool in the Max MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Max MCP Server MCP server in PolicyLayer and add a rule for agent_draft_create: 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 Max MCP Server. Nothing to install.
agent_draft_create is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the agent_draft_create 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.
Set action: deny in the PolicyLayer policy for agent_draft_create. 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.
agent_draft_create is provided by the Max MCP Server MCP server (digital-crew-technologies/max-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Max MCP Server, and thousands of servers like it.
This server
Across the catalogue