ApiLogicServer 14.3.25__py3-none-any.whl → 14.4.0__py3-none-any.whl

api_logic_server_cli/prototypes/nw_no_cust/docs/graphics/count_orders_by_category.prompt

@@ -0,0 +1 @@
+Graph number of sales per category, for dashboard

api_logic_server_cli/prototypes/nw_no_cust/docs/graphics/sales_by_employee.prompt

@@ -0,0 +1 @@
+Graph Sales by Employee, for Dashboard

api_logic_server_cli/prototypes/nw_no_cust/integration/mcp/1_langchain_loader.py

@@ -0,0 +1,19 @@
+from langchain.tools.openapi.utils.openapi_utils import OpenAPISpec
+from langchain.tools.openapi.tool import OpenAPITool
+
+# Load your OpenAPI spec
+spec = OpenAPISpec.from_file("nw_swagger_3.yaml")
+
+# Create LangChain tool from a specific endpoint
+customer_tool = OpenAPITool.from_openapi_spec(
+    spec=spec,
+    operation_id="getCustomer",  # use actual operationId from your spec
+    verbose=True
+)
+
+# Run a test call
+result = customer_tool.run({
+    "filter[Country]": "USA",
+    "page[limit]": 3
+})
+print(result)

api_logic_server_cli/prototypes/nw_no_cust/integration/mcp/2_gpt_mcp_prompt.txt

@@ -0,0 +1,19 @@
+You are an AI planner that builds tool_context blocks for a JSON:API server using OpenAPI 3.0.
+
+Use this OpenAPI file: [insert contents of nw_swagger_3.yaml]
+
+Given the goal: "List all customers from Germany, limited to 2 results", generate a JSON MCP tool_context like this:
+
+{
+  "tool": "json-api",
+  "method": "GET",
+  "url": "https://your-api-domain.com/Customer",
+  "query_params": {
+    "filter[Country]": "Germany",
+    "page[limit]": 2
+  },
+  "headers": {
+    "Accept": "application/vnd.api+json"
+  },
+  "expected_output": "List of customer records"
+}

api_logic_server_cli/prototypes/nw_no_cust/integration/mcp/3_executor_test_agent.py

@@ -0,0 +1,38 @@
+import requests
+
+# MCP-style tool_context
+'''
+tool_context = {
+    "method": "GET",
+    "url": "http://localhost:5656/api/Customer",
+    "query_params": {
+        "filter[Country]": "Germany",
+        "page[limit]": 2
+    },
+    "headers": {
+        "Accept": "application/vnd.api+json"
+    }
+}
+'''
+tool_context = {
+    "method": "GET",
+    "url": "http://localhost:5656/api/Customer",
+    "query_params": {
+        "filter[Country]": "Germany"
+    },
+    "headers": {
+        "Accept": "application/vnd.api+json"
+    }
+}
+
+
+# Execute as a simulated MCP executor
+response = requests.get(
+    tool_context["url"],
+    headers=tool_context["headers"],
+    params=tool_context["query_params"]
+)
+
+# Display result
+print(response.status_code)
+print(response.json())

api_logic_server_cli/prototypes/nw_no_cust/integration/mcp/README.md

@@ -0,0 +1,17 @@
+Model Context Protocol is a way for Chat agents to discover and call external servers, be they databases, APIs, file systems, etc, and call their services.  And, for multiple such servers to be choreographed in a chain of calls.
+
+For more information:
+
+* [see here](https://modelcontextprotocol.io/introduction){:target="_blank" rel="noopener"}
+* [and here](https://apilogicserver.github.io/Docs/Integration-MCP/){:target="_blank" rel="noopener"}
+
+
+> Status: Technology Exploration
+
+## ChatGPT testing
+
+In the Manager, open `samples/nw_sample_nocust`, and explore `integration/mcp`.  This has been successfully used to invoke the server.
+
+This is just an initial experiment, without automation such as creation of openAI version 3 from version 2.  Many substantive issues need to be addressed, including but not limited to security, update, etc.
+
+We welcome participation in this exploration.  Please contact us via [discord](https://discord.gg/HcGxbBsgRF){:target="_blank" rel="noopener"}.

api_logic_server_cli/prototypes/nw_no_cust/integration/mcp/resources/curl.txt

@@ -0,0 +1,4 @@
+curl -X 'GET' \
+  'http://localhost:5656/api/Customer/?filter%5BCountry%5D=Germany' \
+  -H 'accept: application/vnd.api+json' \
+  -H 'Content-Type: application/vnd.api+json'