create_run_record

Create a first-class local run record for agent execution logging.

SERVERTodos SOURCE@hasna/todos

Medium RISK CLASS

Category Write

Parameters 00 required

Recommended Rate-limitedsee the rule below

Registry record Grade F, identity unverified Pull the record →

This record as markdown: /tools/todos/create-run-record.md

WHAT IT DOES

What create_run_record does on Todos

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

RISK

Why create_run_record is rated Medium

This tool creates a new run record for logging agent execution. Creation of new data is a Write operation. Severity is medium because while the action is reversible (records can be deleted), improper logging records could affect audit trails and agent behavior tracking.

From the tool's definition Tool description states it 'Create[s] a first-class local run record', indicating creation of new data. The sibling tools (add_artifact, add_comment, add_task_dependency) confirm this server performs Write operations on task and execution data.

Attacks that exploit this kind of access

RECOMMENDED RULE

The rule that runs create_run_record safely

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

create_run_record Rate-limited

create_run_record 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": {
    "create_run_record": {
      "limits": [
        {
          "counter": "create_run_record_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

LIMIT THIS TOOL → Instant setup, no code required.

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

FAQ

Questions about create_run_record

What does the create_run_record tool do? +

Create a first-class local run record for agent execution logging. It is categorised as a Write tool in the Todos MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on create_run_record? +

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

What risk level is create_run_record? +

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

Can I rate-limit create_run_record? +

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

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

create_run_record is provided by the Todos MCP server (@hasna/todos). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

KEEP EXPLORING

More on Todos, and thousands of servers like it.

This server

All 528 Todos tools →

Across the catalogue

aroflo_create_or_update_record on AroFlo MCP →create_task on 0rca Dojo MCP Server →create-task on Kanban MCP Server →create_package_backup on Android Forensics ADB MCP Server → The MCP Attack Database →

Guides

Govern customer-ops agents →Argument validation →Scoped token →