Returns a summary of the AppSignal GraphQL API schema, including available Query fields, Mutation fields, and all type definitions with their names, kinds, and descriptions. This is a discovery tool - use it BEFORE constructing a custom_graphql_query to understand what data is available. The summ...
AI agents call get_graphql_schema to retrieve information from Playwright Stealth without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This is purely informational retrieval with no side effects. It introspects the GraphQL schema to help construct subsequent queries. While it reveals what mutations are possible, it does not execute them. The tool itself performs no writes, deletions, or external operations—only reads and summarizes schema metadata.
From the tool's definition Tool is explicitly described as 'a discovery tool' that 'Returns a summary' of available schema fields and types. It provides introspection-only information: 'Query fields', 'Mutation fields', 'Types', and 'field counts'.
Documented attack patterns abuse exactly the kind of access get_graphql_schema gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Playwright Stealth, and nothing reaches the server without passing your rules. This is the rule we recommend for get_graphql_schema:
{
"version": "1",
"default": "deny",
"tools": {
"get_graphql_schema": {}
}
}get_graphql_schema 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.
Returns a summary of the AppSignal GraphQL API schema, including available Query fields, Mutation fields, and all type definitions with their names, kinds, and descriptions. This is a discovery tool - use it BEFORE constructing a custom_graphql_query to understand what data is available. The summary provides: - Query fields: What data you can fetch (app, organization, viewer, timezones) - Mutation fields: What actions you can perform - Types: All available types with their kind (type/input/enum/interface/union/scalar) and field counts After reviewing this summary, use get_graphql_schema_details with specific type names to see full field definitions before writing your query. IMPORTANT: Prefer using the other specialized tools (get_exception_incident, search_logs, get_metrics, etc.) for common operations. Only use custom GraphQL queries when: - The specialized tools don. It is categorised as a Read tool in the Playwright Stealth MCP Server, which means it retrieves data without modifying state.
Register the Playwright Stealth MCP server in PolicyLayer and add a rule for get_graphql_schema: 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 Playwright Stealth. Nothing to install.
get_graphql_schema 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_graphql_schema 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_graphql_schema. 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_graphql_schema is provided by the Playwright Stealth MCP server (pulsemcp/mcp-servers). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Playwright Stealth, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
68 Playwright Stealth tools catalogued and risk-classified — across an index of 43,000+ MCP servers.