AI agents use agentUpdate to create or update resources in Mcp Taskade — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Mcp Taskade environment.
The tool modifies existing agent data reversibly. While 'update' typically falls under Write category, the medium severity reflects potential blast radius if an AI agent maliciously modifies agent settings, permissions, or behavior parameters.
From the tool's definition Tool is named 'agentUpdate' with description 'Update agent', indicating modification of agent configuration or properties without deletion.
Documented attack patterns abuse exactly the kind of access agentUpdate gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Mcp Taskade, and nothing reaches the server without passing your rules. This is the rule we recommend for agentUpdate:
{
"version": "1",
"default": "deny",
"tools": {
"agentUpdate": {
"limits": [
{
"counter": "agentupdate_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}agentUpdate 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.
Update agent. It is categorised as a Write tool in the Mcp Taskade MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Mcp Taskade MCP server in PolicyLayer and add a rule for agentUpdate: 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 Mcp Taskade. Nothing to install.
agentUpdate 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 agentUpdate 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 agentUpdate. 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.
agentUpdate is provided by the Mcp Taskade MCP server (taskade/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 57 Mcp Taskade tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
57 Mcp Taskade tools catalogued and risk-classified — across an index of 42,500+ MCP servers.