harness_author

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

High RISK CLASS

Category Execute

Parameters 60 required

Recommended Rate-limitedsee the rule below

Registry record Grade F, identity unverified Pull the record →

This record as markdown: /tools/ai-rokha-rokha/harness-author.md

WHAT IT DOES

What harness_author does on Rokha

AI agents invoke harness_author to trigger actions in Rokha. 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.

Parameter	Type	Required	Description
`tag`	string	—	Optional short label (e.g. 'fetch-prices').
`kind`	string	—	What the harness wraps: 'skill' or 'instruction'. Default 'skill'.
`tool`	string	—	Optional tool name to invoke on the endpoint.
`params`	object	—	Optional arguments for the tool / run, as key→value pairs.
`endpoint`	string	—	Optional MCP JSON-RPC endpoint URL. Empty = performed agentically.
`instruction`	string	—	Imperative instruction: what to do with the skill, or the step to perform.

Parameters from the server's own tool schema.

RISK

Why harness_author is rated High

Configures and executes external tools and skills via JSON-RPC with arbitrary parameters, enabling code execution.

From the tool's definition Configure and wire skill to run; execute via MCP endpoint, tool call, params

Risk signalsAccepts URL/endpoint input (endpoint)

Attacks that exploit this kind of access

RECOMMENDED RULE

The rule that runs harness_author 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 harness_author, this is the rule to start with:

harness_author Rate-limited

harness_author stays usable, but rate-capped: a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "harness_author": {
      "limits": [
        {
          "counter": "harness_author_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

RATE-LIMIT THIS TOOL → Instant setup, no code required.

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

FAQ

Questions about harness_author

What does the harness_author tool do? +

Configure a Harness — a skill (or instruction) wired to run — and get back its config. A harness wraps ONE unit of work via kind: 'skill' (a registry skill, configured to run) or 'instruction' (a pure agent step, no external tool). Set instruction (imperative — what to do with the skill, or the step to perform), an optional tag (short label), and for a real live tool call an optional MCP endpoint (JSON-RPC URL) + tool (name) + params (object of arguments). An empty endpoint means the skill is performed agentically. (In the Rokha UI the same tool fills the human's live Build-a-Harness form.). It is categorised as a Execute tool in the Rokha MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

What parameters does harness_author accept? +

harness_author accepts 6 parameters: tag, kind, tool, params, endpoint, instruction. The full parameter table on this page comes from the server's own tool schema.

How do I enforce a policy on harness_author? +

Register the Rokha MCP server in PolicyLayer and add a rule for harness_author: 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 harness_author? +

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

Can I rate-limit harness_author? +

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

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

harness_author 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 → High-risk tools on this server →

Across the catalogue

All high-risk MCP tools → The MCP Attack Database →

Guides

Govern code and CI agents →Agent sandbox →Least privilege for MCP →