Update a term
AI agents use update_term to create or update resources in POEditor MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your POEditor MCP Server environment.
The tool modifies existing translation terms, which is a write operation. It is reversible (can be updated again), so it does not qualify as Destructive. Severity is medium because corrupting terms could disrupt translation workflows, but the scope is limited to individual term modifications within a project, and the effect is not irreversible.
From the tool's definition Tool name is 'update_term' and description states 'Update a term', indicating modification of existing data. This is a reversible operation that changes term content in POEditor's translation management system.
Attacks that exploit this kind of access
Update a term. It is categorised as a Write tool in the POEditor MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the POEditor MCP Server MCP server in PolicyLayer and add a rule for update_term: 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 POEditor MCP Server. Nothing to install.
update_term 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 update_term 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 update_term. 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.
update_term is provided by the POEditor MCP Server MCP server (r-pedraza/poeditor-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 →