Mark a step as completed with optional notes.
AI agents use complete_step to create or update resources in Context Engine MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Context Engine MCP Server environment.
This tool creates or modifies data (marking a step as completed, optionally adding notes) but does not delete data irreversibly or execute external code. It is a reversible write operation typical of workflow or project management systems. The blast radius is low—marking a step complete can be undone, and it does not trigger external code execution or financial transactions.
From the tool's definition Tool name 'complete_step' with description 'Mark a step as completed with optional notes' indicates state modification of a plan or workflow step.
Documented attack patterns abuse exactly the kind of access complete_step gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Context Engine MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for complete_step:
{
"version": "1",
"default": "deny",
"tools": {
"complete_step": {
"limits": [
{
"counter": "complete_step_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}complete_step 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.
Free to start. No card required.
Mark a step as completed with optional notes. It is categorised as a Write tool in the Context Engine MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Context Engine MCP Server MCP server in PolicyLayer and add a rule for complete_step: 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 Context Engine MCP Server. Nothing to install.
complete_step 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 complete_step 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 complete_step. 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.
complete_step is provided by the Context Engine MCP Server MCP server (kirachon/context-engine). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Context Engine MCP Server, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
50 Context Engine MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.