AI agents use write_page to create or update resources in Wikimcp — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Wikimcp environment.
The tool creates or modifies wiki pages reversibly. While 'overwrite' could suggest destructive intent, the presence of git backing means previous versions are recoverable, and the operation itself is not a permanent deletion. This fits Write (creates/modifies data reversibly) rather than Destructive.
From the tool's definition Tool description states 'Create or overwrite a wiki page' — this is reversible modification of data. The 'auto-commit' indicates the change is persisted to git, making it detectable and recoverable, but still a write operation.
Attacks that exploit this kind of access
Create or overwrite a wiki page at the given path and auto-commit. It is categorised as a Write tool in the Wikimcp MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Wiki MCP server in PolicyLayer and add a rule for write_page: 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 Wikimcp. Nothing to install.
write_page 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 write_page 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 write_page. 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.
write_page is provided by the Wiki MCP server (mohith-das/wikimcp). 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 →