Move an application to a different interview stage.
AI agents use application_change_stage to create or update resources in Ashby MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Ashby MCP Server environment.
This tool modifies the state of an existing application by changing its interview stage. This is a reversible write operation (the stage can be changed back), not destructive. Misuse could affect candidate pipeline progression, hence medium severity.
From the tool's definition Move an application to a different interview stage
Documented attack patterns abuse exactly the kind of access application_change_stage gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Ashby MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for application_change_stage:
{
"version": "1",
"default": "deny",
"tools": {
"application_change_stage": {
"limits": [
{
"counter": "application_change_stage_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
} application_change_stage 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.
Move an application to a different interview stage. It is categorised as a Write tool in the Ashby MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Ashby MCP Server MCP server in PolicyLayer and add a rule for application_change_stage: 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 Ashby MCP Server. Nothing to install.
application_change_stage 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 application_change_stage 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 application_change_stage. 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.
application_change_stage is provided by the Ashby MCP Server MCP server (plenishai/mcp-ashby). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Ashby 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.
21 Ashby MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.