Get full surrounding code context for a specific WordPress hook. Provide a hook ID (from search results) or exact hook name. Returns the code window around the hook, including the enclosing function, docblock, and parameters.
AI agents call get_hook_context to retrieve information from Wp Devdocs without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This is a read-only query tool that fetches documentation and code context from a static indexed database of WordPress hooks. It has no side effects, cannot modify the codebase, and poses minimal risk even if accessed by an untrusted agent. The worst outcome is exposure of existing source code that is already publicly available in WordPress repositories.
From the tool's definition Tool retrieves and returns code context for WordPress hooks without modifying data. Description states it 'Returns the code window around the hook' - a pure retrieval operation.
Documented attack patterns abuse exactly the kind of access get_hook_context gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Wp Devdocs, and nothing reaches the server without passing your rules. This is the rule we recommend for get_hook_context:
{
"version": "1",
"default": "deny",
"tools": {
"get_hook_context": {}
}
}get_hook_context is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Get full surrounding code context for a specific WordPress hook. Provide a hook ID (from search results) or exact hook name. Returns the code window around the hook, including the enclosing function, docblock, and parameters. It is categorised as a Read tool in the Wp Devdocs MCP Server, which means it retrieves data without modifying state.
Register the Wp Devdocs MCP server in PolicyLayer and add a rule for get_hook_context: 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 Wp Devdocs. Nothing to install.
get_hook_context is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the get_hook_context 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 get_hook_context. 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.
get_hook_context is provided by the Wp Devdocs MCP server (pluginslab/wp-devdocs-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 9 Wp Devdocs tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
9 Wp Devdocs tools catalogued and risk-classified — across an index of 42,500+ MCP servers.