trace_search

SERVERRokha SOURCEhttps://rokha.ai/mcp/jsonrpc

Low RISK CLASS

Category Read

Parameters 70 required

Recommended Allowedsee the rule below

Registry record Grade F, identity unverified Pull the record →

This record as markdown: /tools/ai-rokha-rokha/trace-search.md

WHAT IT DOES

What trace_search does on Rokha

AI agents call trace_search to retrieve information from Rokha without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.

Parameter	Type	Required	Description
`limit`	integer	—	Newest N (default modest).
`rig_id`	string	—	Only traces from this rig.
`run_id`	string	—	One run's traces — the run id rig_run / POST /api/rigs/run hand back. Works anonymously for a PUBLIC rig's run.
`status`	string	—	e.g. success, error, partial.
`node_id`	string	—	One graph node's passes within a run.
`trace_kind`	string	—	'run' (containers) or 'atomic' (steps).
`parent_trace_id`	string	—	The atomic step traces under one run — how you see which steps actually ran.

Parameters from the server's own tool schema.

RISK

Why trace_search is rated Low

Tool retrieves execution history records without modifying or executing anything.

From the tool's definition List your Traces — the durable record of what a run DID, newest first.

Risk signalsBulk/mass operation — affects multiple targets

Attacks that exploit this kind of access

RECOMMENDED RULE

The rule that runs trace_search safely

PolicyLayer is an MCP gateway: it sits between your AI agents and Rokha, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For trace_search, this is the rule to start with:

trace_search Allowed

trace_search is read-only, so it stays allowed. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "trace_search": {}
  }
}

ALLOW ONLY THIS TOOL → Instant setup, no code required.

The button opens the PolicyLayer dashboard: create your workspace, connect Rokha, apply this rule, and every trace_search call is checked against it from then on.

FAQ

Questions about trace_search

What does the trace_search tool do? +

List your Traces — the durable record of what a run DID, newest first. This is the other half of rig_run: a run reports that it started, and the trace is where the answer lands. Without it an agent can run a rig and never learn whether it worked, which makes the run untestable. Filter by rig_id (this rig's runs), parent_trace_id (the STEPS under one run — this is how you see which steps ran and which were skipped by a guard), trace_kind ('run' for the containers, 'atomic' for individual steps), run_id (every trace ONE run wrote — the id rig_run and POST /api/rigs/run return), node_id or status. Signed in: your own traces. Anonymous: pass run_id to read a PUBLIC rig's run (anyone holding the id may; the runner's identity is stripped). A private run answers not-found, never forbidden. It is categorised as a Read tool in the Rokha MCP Server, which means it retrieves data without modifying state.

What parameters does trace_search accept? +

trace_search accepts 7 parameters: limit, rig_id, run_id, status, node_id, trace_kind, parent_trace_id. The full parameter table on this page comes from the server's own tool schema.

How do I enforce a policy on trace_search? +

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

What risk level is trace_search? +

trace_search is a Read tool with low risk. Read-only tools are generally safe to allow by default.

Can I rate-limit trace_search? +

Yes. Add a rate_limit block to the trace_search 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 trace_search completely? +

Set action: deny in the PolicyLayer policy for trace_search. 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 trace_search? +

trace_search is provided by the Rokha MCP server (https://rokha.ai/mcp/jsonrpc). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

KEEP EXPLORING

More on Rokha, and thousands of servers like it.

This server

All 216 Rokha tools →

Across the catalogue

binary_search on 010 Editor →evaluate_search_quality on ACE-MCP →search_torrents on M-Team MCP Server →aiva_search_customers on AIVA MCP Server → The MCP Attack Database →

Guides

Roll out MCP under one policy →Data exfiltration →MCP token cost →