AI agents call project_get_custom_fields to retrieve information from Testops without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and queries custom field definitions without modifying, deleting, or executing operations. It supports pagination for data retrieval only. No destructive, write, execute, or financial operations are involved. This is a straightforward Read operation with minimal risk.
From the tool's definition Tool description states it "Get[s] custom field definitions for a project" and "Returns { items, total, page, size } for chunked fetching." The verb 'Get' and return of paginated data indicate read-only retrieval with no side effects.
Attacks that exploit this kind of access
Get custom field definitions for a project with pagination. Returns { items, total, page, size } for chunked fetching. It is categorised as a Read tool in the Testops MCP Server, which means it retrieves data without modifying state.
Register the Testops MCP server in PolicyLayer and add a rule for project_get_custom_fields: 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 Testops. Nothing to install.
project_get_custom_fields is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the project_get_custom_fields 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 project_get_custom_fields. 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.
project_get_custom_fields is provided by the Testops MCP server (@syn7xx/testops-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 →