tpa

Edit third-party API (TPA) configs used by the action-flow Call API node — configs, parameters, nested response trees, and paging. op is a schema ToolName; args is its payload. Call guide {plugin:"tpa"} for the rules and arg shapes.

Server Zion zion-mcp
Category Write
Risk class Medium
Parameters 51 required

What tpa does on Zion

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

ParameterTypeRequiredDescription
op string Yes
args object
appExId string | null
projectExId string
appVersionExId string | null

Parameters from the server's own tool schema.

Why tpa needs a policy

This tool creates or modifies API configurations reversibly. While it affects system behavior through third-party API integration settings, the changes are not destructive (can be reverted) and do not execute arbitrary code or trigger financial transactions.

From the tool's definition Tool description states it 'Edit[s] third-party API (TPA) configs' — editing is a reversible modification action. The tool operates on 'configs, parameters, nested response trees, and paging' which are configuration data structures.

Questions about tpa

What does the tpa tool do? +

Edit third-party API (TPA) configs used by the action-flow Call API node — configs, parameters, nested response trees, and paging. op is a schema ToolName; args is its payload. Call guide {plugin:"tpa"} for the rules and arg shapes. It is categorised as a Write tool in the Zion MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

What parameters does tpa accept? +

tpa accepts 5 parameters: op, args, appExId, projectExId, appVersionExId. Required: op. The full parameter table on this page comes from the server's own tool schema.

How do I enforce a policy on tpa? +

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

What risk level is tpa? +

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

Can I rate-limit tpa? +

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

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

tpa is provided by the Zion MCP server (zion-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

// THE FULL RECORD

tpa is one line of Zion's registry record.

The record carries the whole server: verified identity, auth posture, risk grade, every tool classified, recommended policy — re-checked continuously.

Teams ship this data inside their own products. See what a licence covers →

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.