AI agents use candidate_add_tag to create or update resources in Ashby MCP — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Ashby MCP environment.
This action creates or modifies data (adds a tag) in a reversible manner—tags can be removed or replaced. It has no destructive effect and does not execute arbitrary code or move money. The blast radius is minimal as tag operations affect only candidate metadata without cascading system effects.
From the tool's definition Tool name 'candidate_add_tag' and description 'Add a tag to a candidate' explicitly indicate this modifies candidate metadata by appending a tag.
Attacks that exploit this kind of access
Add a tag to a candidate. It is categorised as a Write tool in the Ashby MCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Ashby MCP server in PolicyLayer and add a rule for candidate_add_tag: 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. Nothing to install.
candidate_add_tag 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 candidate_add_tag 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 candidate_add_tag. 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.
candidate_add_tag is provided by the Ashby MCP server (jaketeagle/ashby-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →