Set a runtime configuration key (e.g. company_id or project_id) for the
AI agents use procore_set_config to create or update resources in Procore MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Procore MCP Server environment.
This tool creates or modifies configuration state that affects subsequent API calls but is reversible—configuration can be changed again. It does not execute arbitrary operations, delete data, or move money.
From the tool's definition Tool name 'procore_set_config' and description 'Set a runtime configuration key (e.g. company_id or project_id)' indicates the tool modifies runtime state by setting configuration values.
Attacks that exploit this kind of access
Set a runtime configuration key (e.g. company_id or project_id) for the. It is categorised as a Write tool in the Procore MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Procore MCP Server MCP server in PolicyLayer and add a rule for procore_set_config: 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 Procore MCP Server. Nothing to install.
procore_set_config 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 procore_set_config 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 procore_set_config. 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.
procore_set_config is provided by the Procore MCP Server MCP server (tylerilunga/procore-mcp-server). 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 →