AI agents use tani_submit to create or update resources in Tani — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Tani environment.
tani_submit creates new records in a registry system, which is a reversible write operation. It does not delete data (not Destructive), execute arbitrary code (not Execute), move money (not Financial), or merely read (not Read).
From the tool's definition Tool description explicitly states 'Publish a surface (tool/API/MCP server) to the registry' — this is a create/add operation that modifies the registry state by introducing new indexed entries.
Attacks that exploit this kind of access
Publish a surface (tool/API/MCP server) to the registry for discovery. Lands as indexed/unproven until the prober fleet earns its trust. Requires a registered publisher agent. It is categorised as a Write tool in the Tani MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Tani MCP server in PolicyLayer and add a rule for tani_submit: 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 Tani. Nothing to install.
tani_submit 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 tani_submit 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 tani_submit. 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.
tani_submit is provided by the Tani MCP server (naylalabs-org/tani-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →