Get the full site configuration.
AI agents call wiki_site_config to retrieve information from Mcp Wikijs Mv without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves site configuration, which is a Read operation. However, severity is elevated to 'medium' rather than 'low' because site configuration typically contains sensitive details (database credentials, API keys, authentication settings, email server configs, or other operational secrets) that could enable further attacks if exposed to an unauthorized AI agent.
From the tool's definition Tool name 'wiki_site_config' with description 'Get the full site configuration' indicates retrieval of configuration data with no modification. The 'Get' verb confirms read-only semantics.
Attacks that exploit this kind of access
Get the full site configuration. It is categorised as a Read tool in the Mcp Wikijs Mv MCP Server, which means it retrieves data without modifying state.
Register the Mcp Wikijs Mv MCP server in PolicyLayer and add a rule for wiki_site_config: 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 Mcp Wikijs Mv. Nothing to install.
wiki_site_config 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 wiki_site_config 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 wiki_site_config. 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.
wiki_site_config is provided by the Mcp Wikijs Mv MCP server (janschachtschabel/mcp-for-wiki-js). 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 →