graphql_query
AI agents invoke graphql_query to trigger actions in ReliaQuest GreyMatter MCP Server. 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.
The server description explicitly labels this tool an 'escape hatch', strongly suggesting it allows arbitrary GraphQL query/mutation execution. GraphQL can perform both reads and writes (mutations), and as a generic escape hatch it likely bypasses normal guardrails.
From the tool's definition Tool name 'graphql_query' combined with server description explicitly calling it a 'generic graphql_query escape hatch' — implies arbitrary query execution capability
Attacks that exploit this kind of access
graphql_query. It is categorised as a Execute tool in the ReliaQuest GreyMatter MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the ReliaQuest GreyMatter MCP Server MCP server in PolicyLayer and add a rule for graphql_query: 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 ReliaQuest GreyMatter MCP Server. Nothing to install.
graphql_query 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 graphql_query 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 graphql_query. 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.
graphql_query is provided by the ReliaQuest GreyMatter MCP Server MCP server (space-c0wboy/reliaquest-greymatter-mcp-server). 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 →