Respond to a pending approval request (approve, reject, or request modifications).
AI agents invoke respond_approval to trigger actions in Context Engine MCP Server. 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.
This tool triggers an action on a pending workflow approval — approving, rejecting, or modifying a request. This drives downstream execution of whatever was awaiting approval (e.g., a plan step, code change, or operation), making it an Execute-class tool. Misuse by an AI agent could cause unintended operations to proceed or be blocked, with potentially high blast radius depending on what the approved action entails.
From the tool's definition Respond to a pending approval request (approve, reject, or request modifications)
Documented attack patterns abuse exactly the kind of access respond_approval 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 respond_approval:
{
"version": "1",
"default": "deny",
"tools": {
"respond_approval": {
"limits": [
{
"counter": "respond_approval_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}respond_approval 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.
Free to start. No card required.
Respond to a pending approval request (approve, reject, or request modifications). It is categorised as a Execute tool in the Context Engine MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Context Engine MCP Server MCP server in PolicyLayer and add a rule for respond_approval: 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.
respond_approval 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 respond_approval 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 respond_approval. 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.
respond_approval 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.