Submit a plan modification diff.
AI agents use tasks_diff to create or update resources in Conductor — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Conductor environment.
This tool modifies task plan state by accepting and applying diffs. While it changes persisted plan data, diffs are typically reversible (can be undone by submitting inverse diffs), making it a Write rather than Destructive action.
From the tool's definition Tool name 'tasks_diff' combined with description 'Submit a plan modification diff' indicates the tool creates or modifies plan data. The verb 'submit' paired with 'modification' suggests a reversible write operation that updates existing task plans.
Documented attack patterns abuse exactly the kind of access tasks_diff gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Conductor, and nothing reaches the server without passing your rules. This is the rule we recommend for tasks_diff:
{
"version": "1",
"default": "deny",
"tools": {
"tasks_diff": {
"limits": [
{
"counter": "tasks_diff_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}tasks_diff 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.
Free to start. No card required.
Submit a plan modification diff. It is categorised as a Write tool in the Conductor MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Conductor MCP server in PolicyLayer and add a rule for tasks_diff: 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 Conductor. Nothing to install.
tasks_diff 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 tasks_diff 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 tasks_diff. 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.
tasks_diff is provided by the Conductor MCP server (shannonbay/conductor). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Conductor, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
16 Conductor tools catalogued and risk-classified — across an index of 43,000+ MCP servers.