Run an arbitrary Wiki.js GraphQL query or mutation. Use for any operation not covered by a
AI agents invoke wiki_graphql to trigger actions in Mcp Wikijs Mv. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
A tool that executes arbitrary GraphQL queries and mutations is classified as Execute because it runs code whose effects entirely depend on user-supplied arguments. The mutation surface includes potential write, destructive, and read operations.
From the tool's definition "Run an arbitrary Wiki.js GraphQL query or mutation" - the tool explicitly permits arbitrary GraphQL operations, which can query, modify, or delete wiki data depending on the mutation sent.
Attacks that exploit this kind of access
Run an arbitrary Wiki.js GraphQL query or mutation. Use for any operation not covered by a. It is categorised as a Execute tool in the Mcp Wikijs Mv MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Mcp Wikijs Mv MCP server in PolicyLayer and add a rule for wiki_graphql: 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_graphql is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the wiki_graphql 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_graphql. 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_graphql 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 →