Get a union task inputs and outputs.
AI agents call list_runs to retrieve information from Union MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries and retrieves information about task runs, their inputs, and outputs. It performs no side effects, does not execute code or workflows, and does not modify or delete any data. It is purely informational retrieval, fitting the 'Read' category with low severity since exposure poses minimal risk—an agent could only view existing run data, not alter system state or trigger operations.
From the tool's definition Tool name 'list_runs' and description 'Get a union task inputs and outputs' indicate retrieval of data without modification. The verb 'Get' and the read-only nature of querying task inputs/outputs confirm this is a data retrieval operation.
Documented attack patterns abuse exactly the kind of access list_runs gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Union MCP, and nothing reaches the server without passing your rules. This is the rule we recommend for list_runs:
{
"version": "1",
"default": "deny",
"tools": {
"list_runs": {}
}
}list_runs is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Get a union task inputs and outputs. It is categorised as a Read tool in the Union MCP MCP Server, which means it retrieves data without modifying state.
Register the Union MCP server in PolicyLayer and add a rule for list_runs: 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 Union MCP. Nothing to install.
list_runs is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the list_runs 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 list_runs. 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.
list_runs is provided by the Union MCP server (unionai-oss/union-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Union MCP, 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.
14 Union MCP tools catalogued and risk-classified — across an index of 43,000+ MCP servers.