This record as markdown: /tools/delimit/delimit-deploy-plan.md
What delimit_deploy_plan does on Delimit
AI agents invoke delimit_deploy_plan to trigger actions in Delimit. 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 delimit_deploy_plan is rated High
The name 'deploy_plan' indicates triggering deployment operations whose effects depend on the plan contents and could impact production systems. While description is absent (lowering confidence from 0.85 to 0.75), the name and sibling tool context (dispatch, complete, handoff) suggest this executes workflows with external side effects.
From the tool's definition Tool name 'delimit_deploy_plan' suggests execution of a deployment plan. Combined with server context of 'AI coding assistant' workspace with tools like 'delimit_agent_dispatch' and 'delimit_agent_complete', this appears to trigger external operations.
Attacks that exploit this kind of access
The rule that runs delimit_deploy_plan safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Delimit, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For delimit_deploy_plan, this is the rule to start with:
delimit_deploy_plan 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.
The button opens the PolicyLayer dashboard: create your workspace, connect Delimit, apply this rule, and every delimit_deploy_plan call is checked against it from then on.
Questions about delimit_deploy_plan
delimit_deploy_plan is a execute tool on the Delimit MCP server. It is categorised as a Execute tool in the Delimit MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Delimit MCP server in PolicyLayer and add a rule for delimit_deploy_plan: 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 Delimit. Nothing to install.
delimit_deploy_plan is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the delimit_deploy_plan 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 delimit_deploy_plan. 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.
delimit_deploy_plan is provided by the Delimit MCP server (delimit-cli). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Delimit, and thousands of servers like it.
Across the catalogue