AI agents use create_company to create or update resources in Schematic — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Schematic environment.
The tool creates new company records or updates existing ones (upsert semantics). This is a Write operation because the changes are reversible (can be updated or potentially deleted later). Severity is medium because creating companies could have business implications but lacks the irreversibility of Destructive operations or financial obligations.
From the tool's definition Tool name is 'create_company' and description states 'Create (upsert) a company' — this creates or modifies company records reversibly.
Attacks that exploit this kind of access
Create (upsert) a company, identified by a key. Companies are looked up by one or more keys (e.g. an. It is categorised as a Write tool in the Schematic MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Schematic MCP server in PolicyLayer and add a rule for create_company: 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 Schematic. Nothing to install.
create_company 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 create_company 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 create_company. 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.
create_company is provided by the Schematic MCP server (@schematichq/schematic-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 →