All available GraphQL mutations
AI agents call mutations to retrieve information from GraphQL Schema Explorer without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
In the context of a GraphQL Schema Explorer server focused on introspection and discovery, this tool retrieves metadata about available mutations rather than executing any. The sibling tools (field, queries, related, schema, search, types) are all read/introspection tools, confirming this tool simply lists mutation definitions. No side effects are performed.
From the tool's definition Tool is named 'mutations' and described as 'All available GraphQL mutations' — it lists/describes available mutations in the schema, it does not execute them. It is part of a schema exploration/introspection server.
Attacks that exploit this kind of access
All available GraphQL mutations. It is categorised as a Read tool in the GraphQL Schema Explorer MCP Server, which means it retrieves data without modifying state.
Register the GraphQL Schema Explorer MCP server in PolicyLayer and add a rule for mutations: 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 GraphQL Schema Explorer. Nothing to install.
mutations 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 mutations 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 mutations. 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.
mutations is provided by the GraphQL Schema Explorer MCP server (martinshumberto/mcp-server-graphql). 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 →