replace_candidate_tags
AI agents use replace_candidate_tags to create or update resources in CATS MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your CATS MCP Server environment.
This tool modifies candidate records by replacing tags, which is a reversible write operation. While it affects candidate data (potentially impacting recruiting workflows), tags are typically metadata rather than core candidate attributes. The operation is reversible (tags can be replaced again), so it does not qualify as Destructive.
From the tool's definition Tool name 'replace_candidate_tags' indicates modification of candidate tag data. Sibling tools include 'attach_candidate_tags', which contextualizes this as a tag management operation within a candidate record.
Attacks that exploit this kind of access
replace_candidate_tags. It is categorised as a Write tool in the CATS MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the CATS MCP Server MCP server in PolicyLayer and add a rule for replace_candidate_tags: 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 CATS MCP Server. Nothing to install.
replace_candidate_tags 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 replace_candidate_tags 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 replace_candidate_tags. 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.
replace_candidate_tags is provided by the CATS MCP Server MCP server (vanman2024/cats-mcp-server). 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 →