start_trace

Start trace execution for a table. Trace is asynchronous (returns 202 Accepted). For regular rules: provide inputJson with { params: {...}, runtimeContext?: {...} }. For test tables: use testRanges (e.g.

Server Openl openl-mcp-server
Category Execute
Risk class High
Parameters 00 required

What start_trace does on Openl

AI agents invoke start_trace to trigger actions in Openl. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.

Why start_trace needs a policy

The tool executes trace operations on tables with user-supplied parameters (inputJson, testRanges). While it does not permanently modify data or delete records, it performs computation/rule execution whose side effects depend on the arguments provided. This qualifies as Execute rather than Read (it's an active operation, not a query) or Write (traces are intended for testing/monitoring, not data modification).

From the tool's definition Tool name 'start_trace' and description states 'Start trace execution for a table' and 'Trace is asynchronous (returns 202 Accepted)', indicating it triggers execution of rules/test logic with provided input parameters.

Questions about start_trace

What does the start_trace tool do? +

Start trace execution for a table. Trace is asynchronous (returns 202 Accepted). For regular rules: provide inputJson with { params: {...}, runtimeContext?: {...} }. For test tables: use testRanges (e.g. It is categorised as a Execute tool in the Openl MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on start_trace? +

Register the Openl MCP server in PolicyLayer and add a rule for start_trace: 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 Openl. Nothing to install.

What risk level is start_trace? +

start_trace is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.

Can I rate-limit start_trace? +

Yes. Add a rate_limit block to the start_trace 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.

How do I block start_trace completely? +

Set action: deny in the PolicyLayer policy for start_trace. 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.

What MCP server provides start_trace? +

start_trace is provided by the Openl MCP server (openl-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

// LOOK UP ANOTHER 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 →

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.