update_harness
Update an existing harness's content or metadata. For a rig-step harness, content is the FULL config object — keep skill intact and set instruction/endpoint/tool/params/model/model_policy (see create_harness for the model-pin semantics).
This record as markdown: /tools/ai-rokha-rokha/update-harness.md
What update_harness does on Rokha
AI agents use update_harness to create or update resources in Rokha, usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Rokha environment.
| Parameter | Type | Required | Description |
|---|---|---|---|
content | string | — | New content for the harness (optional) |
metadata | object | — | New metadata for the harness (optional) |
harness_id | string | Yes | UUID of the harness to update |
Parameters from the server's own tool schema.
Why update_harness is rated Medium
Modifies harness configuration and execution parameters that control agent behavior and external calls.
From the tool's definition Update harness content, config object, instruction, endpoint, tool, params, model.
Risk signalsAccepts raw HTML/template content (content)
Attacks that exploit this kind of access
The rule that runs update_harness 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 update_harness, this is the rule to start with:
update_harness stays usable, but capped: an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect Rokha, apply this rule, and every update_harness call is checked against it from then on.
Questions about update_harness
Update an existing harness's content or metadata. For a rig-step harness, content is the FULL config object — keep skill intact and set instruction/endpoint/tool/params/model/model_policy (see create_harness for the model-pin semantics). It is categorised as a Write tool in the Rokha MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
update_harness accepts 3 parameters: content, metadata, harness_id. Required: harness_id. The full parameter table on this page comes from the server's own tool schema.
Register the Rokha MCP server in PolicyLayer and add a rule for update_harness: 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.
update_harness 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_harness 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_harness. 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_harness 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.
More on Rokha, and thousands of servers like it.
This server
Across the catalogue