Create a new page in GROWI
AI agents use createPage to create or update resources in GROWI MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your GROWI MCP Server environment.
The tool creates new content (pages) in the GROWI wiki, which is a reversible write operation. It does not execute arbitrary code, delete data irreversibly, or move money. The severity is medium because unauthorized page creation could pollute the wiki namespace or be used for phishing/misinformation, but the impact is bounded to wiki content and reversible through deletion.
From the tool's definition Tool name is 'createPage' and description states 'Create a new page in GROWI' — this creates new data in the wiki system.
Attacks that exploit this kind of access
Create a new page in GROWI. It is categorised as a Write tool in the GROWI MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the GROWI MCP Server MCP server in PolicyLayer and add a rule for createPage: 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 GROWI MCP Server. Nothing to install.
createPage 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 createPage 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 createPage. 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.
createPage is provided by the GROWI MCP Server MCP server (mechanicalgirldev/growi-mcp-server-web). 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 →