Look up a running process instance by ID. Runtime-only — completed/terminated instances return
AI agents call get_process_instance to retrieve information from CIB Seven MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool retrieves information about a process instance by ID. The description explicitly indicates it is read-only ("Look up") and queries runtime data. There is no indication the tool modifies, deletes, executes code, or transfers funds.
From the tool's definition Look up a running process instance by ID. Runtime-only — completed/terminated instances return. This is a query/lookup operation that retrieves data about a process instance with no side effects.
Attacks that exploit this kind of access
Look up a running process instance by ID. Runtime-only — completed/terminated instances return. It is categorised as a Read tool in the CIB Seven MCP Server MCP Server, which means it retrieves data without modifying state.
Register the CIB Seven MCP Server MCP server in PolicyLayer and add a rule for get_process_instance: 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 CIB Seven MCP Server. Nothing to install.
get_process_instance 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 get_process_instance 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 get_process_instance. 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.
get_process_instance is provided by the CIB Seven MCP Server MCP server (krixerx/cib7-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 →