start_process_instance_tool · Reltio MCP Server MCP

WHAT IT DOES

What start_process_instance_tool does on Reltio MCP Server

AI agents invoke start_process_instance_tool to trigger actions in Reltio MCP Server. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.

WHY IT NEEDS A POLICY

Why start_process_instance_tool needs a policy

This tool appears to start/trigger workflow process instances within Reltio's MDM platform. Starting processes is an Execute action—it triggers external operations whose effects depend on which process is initiated and its arguments. While not immediately destructive or financial, a misused process instance could cause unintended business operations, data modifications, or prolonged workflows.

From the tool's definition Tool name is 'start_process_instance_tool' which indicates triggering or initiating a process. The server description mentions 'workflow tasks' and the tool's name suggests launching workflow instances.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

start_process_instance_tool Rate-limited

start_process_instance_tool stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "start_process_instance_tool": {
      "limits": [
        {
          "counter": "start_process_instance_tool_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

RATE-LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches Reltio MCP Server, so you can run agents against it safely.

FAQ

Questions about start_process_instance_tool

What does the start_process_instance_tool tool do? +

start_process_instance_tool. It is categorised as a Execute tool in the Reltio MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on start_process_instance_tool? +

Register the Reltio MCP Server MCP server in PolicyLayer and add a rule for start_process_instance_tool: 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 Reltio MCP Server. Nothing to install.

What risk level is start_process_instance_tool? +

start_process_instance_tool is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.

Can I rate-limit start_process_instance_tool? +

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

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

start_process_instance_tool is provided by the Reltio MCP Server MCP server (reltio-ai/reltio-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.