Make surgical find-and-replace text edits within a block.
AI agents use wp_edit_block_text to create or update resources in Claudaborative Editing — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Claudaborative Editing environment.
This tool creates or modifies data reversibly—it edits text within blocks but does not delete content, execute code, or cause irreversible changes. The changes can be undone via WordPress's revision system. Severity is medium because widespread misuse could corrupt post content across multiple blocks, but the reversible nature and localized scope (surgical edits within single blocks) prevent it from being high.
From the tool's definition Tool performs 'find-and-replace text edits' on block content, modifying existing data within WordPress blocks. The description explicitly indicates modification capability through surgical text replacement.
Documented attack patterns abuse exactly the kind of access wp_edit_block_text gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Claudaborative Editing, and nothing reaches the server without passing your rules. This is the rule we recommend for wp_edit_block_text:
{
"version": "1",
"default": "deny",
"tools": {
"wp_edit_block_text": {
"limits": [
{
"counter": "wp_edit_block_text_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}wp_edit_block_text stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Make surgical find-and-replace text edits within a block. It is categorised as a Write tool in the Claudaborative Editing MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Claudaborative Editing MCP server in PolicyLayer and add a rule for wp_edit_block_text: 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 Claudaborative Editing. Nothing to install.
wp_edit_block_text 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 wp_edit_block_text 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 wp_edit_block_text. 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.
wp_edit_block_text is provided by the Claudaborative Editing MCP server (pento/claudaborative-editing). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Claudaborative Editing, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
32 Claudaborative Editing tools catalogued and risk-classified — across an index of 43,000+ MCP servers.