AI agents use intentProposeNani to create or update resources in Agentek Eth — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Agentek Eth environment.
This tool creates a governance proposal, which is fundamentally a Write operation (creates new data/state). However, the severity is elevated to 'high' because: (1) governance proposals in DAOs can control significant financial resources and protocol parameters, (2) a malicious agent could create spam proposals or hijack governance if wallet access is compromised, and (3) while the proposal creation itself is…
From the tool's definition Tool name 'intentProposeNani' and description 'Create a new governance proposal for NANIDAO' indicate creating a new governance proposal, which is a reversible write operation.
Documented attack patterns abuse exactly the kind of access intentProposeNani gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Agentek Eth, and nothing reaches the server without passing your rules. This is the rule we recommend for intentProposeNani:
{
"version": "1",
"default": "deny",
"tools": {
"intentProposeNani": {
"limits": [
{
"counter": "intentproposenani_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}intentProposeNani 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.
Create a new governance proposal for NANIDAO. It is categorised as a Write tool in the Agentek Eth MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Agentek Eth MCP server in PolicyLayer and add a rule for intentProposeNani: 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 Agentek Eth. Nothing to install.
intentProposeNani 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 intentProposeNani 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 intentProposeNani. 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.
intentProposeNani is provided by the Agentek Eth MCP server (nanidao/agentek). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Agentek Eth, 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.
165 Agentek Eth tools catalogued and risk-classified — across an index of 43,000+ MCP servers.