tokrepo_codex_install · TokRepo — AI Asset Registry MCP

WHAT IT DOES

What tokrepo_codex_install does on TokRepo — AI Asset Registry

AI agents use tokrepo_codex_install to create or update resources in TokRepo — AI Asset Registry — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your TokRepo — AI Asset Registry environment.

WHY IT NEEDS A POLICY

Why tokrepo_codex_install needs a policy

The tool modifies the local Codex by installing assets (skills, prompts, configs, workflows). While primarily a Write operation (creates/installs files), the ability to install arbitrary AI assets—especially those flagged as 'risky'—combined with the context of installing executable workflows and the existence of a rollback mechanism (suggesting potential side effects) elevates this to high severity.

From the tool's definition 'Safely install a TokRepo asset into local Codex' and 'To write files, set dry_run=false and confirm=true' indicate creation/modification of files.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

tokrepo_codex_install Rate-limited

tokrepo_codex_install 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.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "tokrepo_codex_install": {
      "limits": [
        {
          "counter": "tokrepo_codex_install_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches TokRepo — AI Asset Registry, so you can run agents against it safely.

FAQ

Questions about tokrepo_codex_install

What does the tokrepo_codex_install tool do? +

STEP 3 of ATOMIC ACTION 2 (install safely into this repo). Safely install a TokRepo asset into local Codex. Defaults to dry_run=true. To write files, set dry_run=false and confirm=true. Risky assets require stage=true or approve_risk=true. Always call tokrepo_install_plan + tokrepo_verify first. On any failure call tokrepo_rollback (STEP 4 — the escape). It is categorised as a Write tool in the TokRepo — AI Asset Registry MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on tokrepo_codex_install? +

Register the TokRepo — AI Asset Registry MCP server in PolicyLayer and add a rule for tokrepo_codex_install: 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 TokRepo — AI Asset Registry. Nothing to install.

What risk level is tokrepo_codex_install? +

tokrepo_codex_install is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Can I rate-limit tokrepo_codex_install? +

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

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

tokrepo_codex_install is provided by the TokRepo — AI Asset Registry MCP server (tokrepo-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.