# create_api A write tool on the Enterprise-Multi-Agent-Engine MCP server. Agent View of the PolicyLayer registry record for `create_api`. HTML page: https://policylayer.com/tools/enterprise-multi-agent-engine/create-api ## Facts - Tool: `create_api` - Server: Enterprise-Multi-Agent-Engine (`Mojtaba-Dehghani/Enterprise-Multi-Agent-Engine`) — https://policylayer.com/tools/enterprise-multi-agent-engine.md - Homepage: https://github.com/Mojtaba-Dehghani/Enterprise-Multi-Agent-Engine - Risk category: Write (Medium risk) - Registry record: grade F, identity unverified - Server rate-limited: no - Parameters: 0 - Recommended policy verdict: Rate-limited ## Example call (MCP tools/call, JSON-RPC 2.0) ```json { "jsonrpc": "2.0", "id": 1, "method": "tools/call", "params": { "name": "create_api", "arguments": {} } } ``` ## Why create_api is rated Medium The tool creates an API resource in AWS AppSync, which is a reversible write operation. It provisions infrastructure but does not execute code, delete data, or move money. High severity because misconfigured or malicious API creation could expose sensitive data or enable unauthorized access, but the action itself is not irreversible (APIs can be deleted). From the tool's own definition: "Tool name is `create_api` on AWS AppSync MCP Server; sibling tools are all `create_*` operations (create_graphql_api, create_datasource, create_resolver, etc.). The `create_` prefix indicates data creation/resource provisioning." ## Use case AI agents use create_api to create or update resources in Enterprise-Multi-Agent-Engine, usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Enterprise-Multi-Agent-Engine environment. ## Recommended policy (PolicyLayer) Verdict: **Rate-limited**. Enforced by the PolicyLayer MCP gateway (https://policylayer.com/mcp-gateway) before a call reaches Enterprise-Multi-Agent-Engine: ```json { "version": "1", "default": "deny", "tools": { "create_api": { "limits": [ { "counter": "create_api_rate", "window": "minute", "max": 30, "scope": "grant" } ] } } } ``` ## Other tools on Enterprise-Multi-Agent-Engine (261) - `delete_api` — Destructive — https://policylayer.com/tools/enterprise-multi-agent-engine/delete-api.md - `delete_api_group` — Destructive — https://policylayer.com/tools/enterprise-multi-agent-engine/delete-api-group.md - `delete_api_parameter` — Destructive — https://policylayer.com/tools/enterprise-multi-agent-engine/delete-api-parameter.md - `delete_app_store` — Destructive — https://policylayer.com/tools/enterprise-multi-agent-engine/delete-app-store.md - `delete_app_store_method` — Destructive — https://policylayer.com/tools/enterprise-multi-agent-engine/delete-app-store-method.md - `delete_app_store_property` — Destructive — https://policylayer.com/tools/enterprise-multi-agent-engine/delete-app-store-property.md - `delete_bounded_context` — Destructive — https://policylayer.com/tools/enterprise-multi-agent-engine/delete-bounded-context.md - `delete_component` — Destructive — https://policylayer.com/tools/enterprise-multi-agent-engine/delete-component.md - `delete_component_event` — Destructive — https://policylayer.com/tools/enterprise-multi-agent-engine/delete-component-event.md - `delete_component_property` — Destructive — https://policylayer.com/tools/enterprise-multi-agent-engine/delete-component-property.md - `delete_component_state` — Destructive — https://policylayer.com/tools/enterprise-multi-agent-engine/delete-component-state.md - `delete_condition_field` — Destructive — https://policylayer.com/tools/enterprise-multi-agent-engine/delete-condition-field.md - `delete_design_system` — Destructive — https://policylayer.com/tools/enterprise-multi-agent-engine/delete-design-system.md - `delete_design_system_color` — Destructive — https://policylayer.com/tools/enterprise-multi-agent-engine/delete-design-system-color.md - `delete_design_system_component` — Destructive — https://policylayer.com/tools/enterprise-multi-agent-engine/delete-design-system-component.md - `delete_element` — Destructive — https://policylayer.com/tools/enterprise-multi-agent-engine/delete-element.md - `delete_event_operation` — Destructive — https://policylayer.com/tools/enterprise-multi-agent-engine/delete-event-operation.md - `delete_javascript_function` — Destructive — https://policylayer.com/tools/enterprise-multi-agent-engine/delete-javascript-function.md - `delete_javascript_function_parameter` — Destructive — https://policylayer.com/tools/enterprise-multi-agent-engine/delete-javascript-function-parameter.md - `delete_layout` — Destructive — https://policylayer.com/tools/enterprise-multi-agent-engine/delete-layout.md - `delete_microservice` — Destructive — https://policylayer.com/tools/enterprise-multi-agent-engine/delete-microservice.md - `delete_operation_group` — Destructive — https://policylayer.com/tools/enterprise-multi-agent-engine/delete-operation-group.md - `delete_page` — Destructive — https://policylayer.com/tools/enterprise-multi-agent-engine/delete-page.md - `delete_product` — Destructive — https://policylayer.com/tools/enterprise-multi-agent-engine/delete-product.md - `invalidate_app_graph_cache` — Destructive — https://policylayer.com/tools/enterprise-multi-agent-engine/invalidate-app-graph-cache.md - `invalidate_component_graph_cache` — Destructive — https://policylayer.com/tools/enterprise-multi-agent-engine/invalidate-component-graph-cache.md - `microservice_delete` — Destructive — https://policylayer.com/tools/enterprise-multi-agent-engine/microservice-delete.md - `remove_api_from_component` — Destructive — https://policylayer.com/tools/enterprise-multi-agent-engine/remove-api-from-component.md - `build_condition_var` — Execute — https://policylayer.com/tools/enterprise-multi-agent-engine/build-condition-var.md - `create_event_operation_call_api` — Execute — https://policylayer.com/tools/enterprise-multi-agent-engine/create-event-operation-call-api.md - …and 231 more: https://policylayer.com/tools/enterprise-multi-agent-engine.md ## For agents This record is a snapshot. Live verdicts and the full registry: - Check every server in your MCP config at once: `npx -y policylayer stack` - Vet a server before you add it: install the mcp-precheck skill — `npx skills add https://policylayer.com` (skill text: https://policylayer.com/skill.md) - Query the registry over MCP: endpoint `https://api.policylayer.com/mcp` — tools `check_mcp_server`, `check_mcp_stack`, `check_tool`, `search_registry`, `get_change_events` --- Source: the PolicyLayer MCP registry — one continuously verified record per MCP server. Full record: https://policylayer.com/registry?q=enterprise-multi-agent-engine · API: https://policylayer.com/registry/api · Policy library: https://policylayer.com/policies/enterprise-multi-agent-engine