From 61700f9e0f9b03db0c80d2efaf3cf14b0c3bffb2 Mon Sep 17 00:00:00 2001 From: ivanmilevtues Date: Sat, 26 Jul 2025 08:38:17 +0000 Subject: [PATCH] docs: update mcp-agent codeboarding documentation --- .codeboarding/Agent_Core_LLM_Integration.json | 2 +- .../Agent_Execution_Workflow_Engine.json | 2 +- .codeboarding/Agent_Workflow_Patterns.json | 2 +- .codeboarding/Core_Application_Setup.json | 2 +- .codeboarding/Human_Interaction_Layer.json | 2 +- .codeboarding/MCP_Service_Integration.json | 2 +- .codeboarding/analysis.json | 20 ++++++++---- .codeboarding/codeboarding_version.json | 4 +-- .../Agent_Core_LLM_Integration.mdx | 18 ++--------- .../Agent_Execution_Workflow_Engine.mdx | 18 ++--------- docs/codeboarding/Agent_Workflow_Patterns.mdx | 18 ++--------- docs/codeboarding/Core_Application_Setup.mdx | 18 ++--------- docs/codeboarding/Human_Interaction_Layer.mdx | 18 ++--------- docs/codeboarding/MCP_Service_Integration.mdx | 18 ++--------- docs/codeboarding/on_boarding.mdx | 32 ++++++++----------- 15 files changed, 47 insertions(+), 129 deletions(-) diff --git a/.codeboarding/Agent_Core_LLM_Integration.json b/.codeboarding/Agent_Core_LLM_Integration.json index 86daaa209..03d376a1a 100644 --- a/.codeboarding/Agent_Core_LLM_Integration.json +++ b/.codeboarding/Agent_Core_LLM_Integration.json @@ -138,4 +138,4 @@ "dst_name": "Provider to MCP Converters" } ] -} \ No newline at end of file +} diff --git a/.codeboarding/Agent_Execution_Workflow_Engine.json b/.codeboarding/Agent_Execution_Workflow_Engine.json index 2dc5cc681..0b2425e5a 100644 --- a/.codeboarding/Agent_Execution_Workflow_Engine.json +++ b/.codeboarding/Agent_Execution_Workflow_Engine.json @@ -135,4 +135,4 @@ "dst_name": "Decorator Registry" } ] -} \ No newline at end of file +} diff --git a/.codeboarding/Agent_Workflow_Patterns.json b/.codeboarding/Agent_Workflow_Patterns.json index 14c0c506c..0a13b2da1 100644 --- a/.codeboarding/Agent_Workflow_Patterns.json +++ b/.codeboarding/Agent_Workflow_Patterns.json @@ -224,4 +224,4 @@ "dst_name": "LLM Augmentation Layer" } ] -} \ No newline at end of file +} diff --git a/.codeboarding/Core_Application_Setup.json b/.codeboarding/Core_Application_Setup.json index 577b8dcf8..8d3da23b9 100644 --- a/.codeboarding/Core_Application_Setup.json +++ b/.codeboarding/Core_Application_Setup.json @@ -192,4 +192,4 @@ "dst_name": "Configuration Management (Settings)" } ] -} \ No newline at end of file +} diff --git a/.codeboarding/Human_Interaction_Layer.json b/.codeboarding/Human_Interaction_Layer.json index cb676d10e..9692c1813 100644 --- a/.codeboarding/Human_Interaction_Layer.json +++ b/.codeboarding/Human_Interaction_Layer.json @@ -72,4 +72,4 @@ "dst_name": "Console Interface" } ] -} \ No newline at end of file +} diff --git a/.codeboarding/MCP_Service_Integration.json b/.codeboarding/MCP_Service_Integration.json index 1b55ab249..124438928 100644 --- a/.codeboarding/MCP_Service_Integration.json +++ b/.codeboarding/MCP_Service_Integration.json @@ -99,4 +99,4 @@ "dst_name": "mcp_agent.config" } ] -} \ No newline at end of file +} diff --git a/.codeboarding/analysis.json b/.codeboarding/analysis.json index 3a73d561e..44a52ac41 100644 --- a/.codeboarding/analysis.json +++ b/.codeboarding/analysis.json @@ -17,7 +17,8 @@ "reference_start_line": 1, "reference_end_line": 1 } - ] + ], + "can_expand": true }, { "name": "Agent Execution & Workflow Engine", @@ -53,7 +54,8 @@ "reference_start_line": 1, "reference_end_line": 1 } - ] + ], + "can_expand": true }, { "name": "Agent Core & LLM Integration", @@ -77,7 +79,8 @@ "reference_start_line": 1, "reference_end_line": 1 } - ] + ], + "can_expand": true }, { "name": "MCP Service Integration", @@ -101,7 +104,8 @@ "reference_start_line": 1, "reference_end_line": 1 } - ] + ], + "can_expand": true }, { "name": "Agent Workflow Patterns", @@ -137,7 +141,8 @@ "reference_start_line": 1, "reference_end_line": 1 } - ] + ], + "can_expand": true }, { "name": "Human Interaction Layer", @@ -155,7 +160,8 @@ "reference_start_line": 1, "reference_end_line": 1 } - ] + ], + "can_expand": true } ], "components_relations": [ @@ -210,4 +216,4 @@ "dst_name": "Agent Execution & Workflow Engine" } ] -} \ No newline at end of file +} diff --git a/.codeboarding/codeboarding_version.json b/.codeboarding/codeboarding_version.json index b6a90e34c..f8a00cf9f 100644 --- a/.codeboarding/codeboarding_version.json +++ b/.codeboarding/codeboarding_version.json @@ -1,4 +1,4 @@ { - "commit_hash": "13c378d8bceee2b4b325ff4a294fba046c835e72", + "commit_hash": "15d5cb9610d79b65276c4f13e94bd9bc3bff6231", "code_boarding_version": "0.1.0" -} \ No newline at end of file +} diff --git a/docs/codeboarding/Agent_Core_LLM_Integration.mdx b/docs/codeboarding/Agent_Core_LLM_Integration.mdx index 0bba6fe02..f9fe1cd55 100644 --- a/docs/codeboarding/Agent_Core_LLM_Integration.mdx +++ b/docs/codeboarding/Agent_Core_LLM_Integration.mdx @@ -1,9 +1,4 @@ ---- -title: "Agent Core LLM Integration" -description: "Agent Core LLM Integration component details" ---- - - +# Agent Core LLM Integration ```mermaid graph LR Agent_Core["Agent Core"] @@ -17,11 +12,7 @@ graph LR LLM_Provider_Implementations -- "uses" --> Provider_to_MCP_Converters ``` - -This documentation was generated by [CodeBoarding](https://github.com/CodeBoarding/GeneratedOnBoardings) to provide comprehensive architectural insights into the mcp-agent framework. - - -## Details +### Details This subsystem defines the fundamental interface and capabilities of an AI agent, encapsulating interactions with Large Language Models (LLMs), external tools, prompts, and resources. It provides a consistent and extensible model for agent behavior and offers a standardized, augmented interface for interacting with various LLM providers. @@ -77,8 +68,3 @@ These utility classes are crucial for ensuring data consistency and interoperabi - `mcp_agent.workflows.llm.augmented_llm_bedrock.BedrockMCPTypeConverter` (437:499) - `mcp_agent.workflows.llm.augmented_llm_google.GoogleMCPTypeConverter` (403:518) - `mcp_agent.workflows.llm.augmented_llm_openai.MCPOpenAITypeConverter` (949:1055) - - - - -### [FAQ](https://github.com/CodeBoarding/GeneratedOnBoardings/tree/main?tab=readme-ov-file#faq) \ No newline at end of file diff --git a/docs/codeboarding/Agent_Execution_Workflow_Engine.mdx b/docs/codeboarding/Agent_Execution_Workflow_Engine.mdx index 29a2949b5..2543b363d 100644 --- a/docs/codeboarding/Agent_Execution_Workflow_Engine.mdx +++ b/docs/codeboarding/Agent_Execution_Workflow_Engine.mdx @@ -1,9 +1,4 @@ ---- -title: "Agent Execution Workflow Engine" -description: "Agent Execution Workflow Engine component details" ---- - - +# Agent Execution Workflow Engine ```mermaid graph LR Execution_Engine["Execution Engine"] @@ -21,11 +16,7 @@ graph LR Execution_Engine -- "potentially uses" --> Decorator_Registry ``` - -This documentation was generated by [CodeBoarding](https://github.com/CodeBoarding/GeneratedOnBoardings) to provide comprehensive architectural insights into the mcp-agent framework. - - -## Details +### Details Abstract Components Overview @@ -85,8 +76,3 @@ This component is responsible for registering and providing access to defined wo - `mcp_agent/executor/workflow_registry.py` - `mcp_agent/executor/temporal/workflow_registry.py` - - - - -### [FAQ](https://github.com/CodeBoarding/GeneratedOnBoardings/tree/main?tab=readme-ov-file#faq) \ No newline at end of file diff --git a/docs/codeboarding/Agent_Workflow_Patterns.mdx b/docs/codeboarding/Agent_Workflow_Patterns.mdx index 9d87cbcce..98a651799 100644 --- a/docs/codeboarding/Agent_Workflow_Patterns.mdx +++ b/docs/codeboarding/Agent_Workflow_Patterns.mdx @@ -1,9 +1,4 @@ ---- -title: "Agent Workflow Patterns" -description: "Agent Workflow Patterns component details" ---- - - +# Agent Workflow Patterns ```mermaid graph LR LLM_Augmentation_Layer["LLM Augmentation Layer"] @@ -24,11 +19,7 @@ graph LR Evaluation_Optimization_Workflow -- "uses" --> LLM_Augmentation_Layer ``` - -This documentation was generated by [CodeBoarding](https://github.com/CodeBoarding/GeneratedOnBoardings) to provide comprehensive architectural insights into the mcp-agent framework. - - -## Details +### Details Abstract Components Overview @@ -116,8 +107,3 @@ Provides mechanisms for evaluating the performance, quality, and effectiveness o **Related Classes/Methods**: - `mcp_agent.workflows.evaluator_optimizer.evaluator_optimizer.EvaluatorOptimizerLLM` (47:475) - - - - -### [FAQ](https://github.com/CodeBoarding/GeneratedOnBoardings/tree/main?tab=readme-ov-file#faq) \ No newline at end of file diff --git a/docs/codeboarding/Core_Application_Setup.mdx b/docs/codeboarding/Core_Application_Setup.mdx index 072d28dd0..abe6fe272 100644 --- a/docs/codeboarding/Core_Application_Setup.mdx +++ b/docs/codeboarding/Core_Application_Setup.mdx @@ -1,9 +1,4 @@ ---- -title: "Core Application Setup" -description: "Core Application Setup component details" ---- - - +# Core Application Setup ```mermaid graph LR Application_Core_MCPApp_["Application Core (MCPApp)"] @@ -25,11 +20,7 @@ graph LR LLM_Selection -- "depends on" --> Configuration_Management_Settings_ ``` - -This documentation was generated by [CodeBoarding](https://github.com/CodeBoarding/GeneratedOnBoardings) to provide comprehensive architectural insights into the mcp-agent framework. - - -## Details +### Details This component is the foundational layer of the `mcp-agent` application. It is responsible for the initial bootstrapping of the entire agent framework, establishing the global application context, and managing the loading, parsing, and provision of all application settings and sensitive information. It acts as the central orchestrator for the agent's environment, ensuring that all subsequent components operate with the correct parameters and have access to essential services. Its design emphasizes modularity and extensibility, crucial for an AI agent development framework. @@ -103,8 +94,3 @@ Responsible for selecting and managing Large Language Models (LLMs), including t - `mcp_agent.workflows.llm.llm_selector.ModelSelector` (96:413) - `mcp_agent.workflows.llm.augmented_llm.AugmentedLLM` (218:668) - - - - -### [FAQ](https://github.com/CodeBoarding/GeneratedOnBoardings/tree/main?tab=readme-ov-file#faq) \ No newline at end of file diff --git a/docs/codeboarding/Human_Interaction_Layer.mdx b/docs/codeboarding/Human_Interaction_Layer.mdx index a651fe218..23a9d788f 100644 --- a/docs/codeboarding/Human_Interaction_Layer.mdx +++ b/docs/codeboarding/Human_Interaction_Layer.mdx @@ -1,9 +1,4 @@ ---- -title: "Human Interaction Layer" -description: "Human Interaction Layer component details" ---- - - +# Human Interaction Layer ```mermaid graph LR Human_Input_Handler["Human Input Handler"] @@ -16,11 +11,7 @@ graph LR Progress_Display -- "uses" --> Console_Interface ``` - -This documentation was generated by [CodeBoarding](https://github.com/CodeBoarding/GeneratedOnBoardings) to provide comprehensive architectural insights into the mcp-agent framework. - - -## Details +### Details The `Human Interaction Layer` is a critical subsystem designed to facilitate seamless human-in-the-loop workflows within the AI agent framework. Its primary purpose is to enable agents to request information, receive feedback, and process responses from human users, thereby integrating human intelligence and decision-making into automated processes. This layer adheres to the project's architectural biases by promoting modularity, clear separation of concerns, and an asynchronous design, ensuring that human interactions do not block core agent operations. @@ -58,8 +49,3 @@ This foundational component provides the low-level interface for interacting wit **Related Classes/Methods**: - `Console Interface` (1:1) - - - - -### [FAQ](https://github.com/CodeBoarding/GeneratedOnBoardings/tree/main?tab=readme-ov-file#faq) \ No newline at end of file diff --git a/docs/codeboarding/MCP_Service_Integration.mdx b/docs/codeboarding/MCP_Service_Integration.mdx index a59b7ecc4..da61dff0b 100644 --- a/docs/codeboarding/MCP_Service_Integration.mdx +++ b/docs/codeboarding/MCP_Service_Integration.mdx @@ -1,9 +1,4 @@ ---- -title: "MCP Service Integration" -description: "MCP Service Integration component details" ---- - - +# MCP Service Integration ```mermaid graph LR MCPAggregator["MCPAggregator"] @@ -20,11 +15,7 @@ graph LR MCPClientSession -- "Uses" --> mcp_agent_config ``` - -This documentation was generated by [CodeBoarding](https://github.com/CodeBoarding/GeneratedOnBoardings) to provide comprehensive architectural insights into the mcp-agent framework. - - -## Details +### Details Abstract Components Overview @@ -71,8 +62,3 @@ This module contains auto-generated client code that provides concrete methods f **Related Classes/Methods**: - `mcp_agent.mcp.gen_client` (15:40) - - - - -### [FAQ](https://github.com/CodeBoarding/GeneratedOnBoardings/tree/main?tab=readme-ov-file#faq) \ No newline at end of file diff --git a/docs/codeboarding/on_boarding.mdx b/docs/codeboarding/on_boarding.mdx index 0f73455dc..83633fd54 100644 --- a/docs/codeboarding/on_boarding.mdx +++ b/docs/codeboarding/on_boarding.mdx @@ -1,6 +1,7 @@ --- title: "Architecture Overview" description: "Comprehensive architectural overview of the mcp-agent framework" +icon: "network" --- @@ -22,23 +23,23 @@ graph LR Agent_Workflow_Patterns -- "Orchestrates" --> Agent_Core_LLM_Integration Agent_Workflow_Patterns -- "Leverages" --> MCP_Service_Integration Human_Interaction_Layer -- "Provides input to" --> Agent_Execution_Workflow_Engine - click Core_Application_Setup href "/codeboarding/Core_Application_Setup.mdx" "Details" - click Agent_Execution_Workflow_Engine href "/codeboarding/Agent_Execution_Workflow_Engine.mdx" "Details" - click Agent_Core_LLM_Integration href "/codeboarding/Agent_Core_LLM_Integration.mdx" "Details" - click MCP_Service_Integration href "/codeboarding/MCP_Service_Integration.mdx" "Details" - click Agent_Workflow_Patterns href "/codeboarding/Agent_Workflow_Patterns.mdx" "Details" - click Human_Interaction_Layer href "/codeboarding/Human_Interaction_Layer.mdx" "Details" + click Core_Application_Setup href "/codeboarding/Core_Application_Setup.md" "Details" + click Agent_Execution_Workflow_Engine href "/codeboarding/Agent_Execution_Workflow_Engine.md" "Details" + click Agent_Core_LLM_Integration href "/codeboarding/Agent_Core_LLM_Integration.md" "Details" + click MCP_Service_Integration href "/codeboarding/MCP_Service_Integration.md" "Details" + click Agent_Workflow_Patterns href "/codeboarding/Agent_Workflow_Patterns.md" "Details" + click Human_Interaction_Layer href "/codeboarding/Human_Interaction_Layer.md" "Details" ``` This documentation was generated by [CodeBoarding](https://github.com/CodeBoarding/GeneratedOnBoardings) to provide comprehensive architectural insights into the mcp-agent framework. -## Details +### Details The `mcp-agent` project provides a robust framework for developing AI agents. At its core, the **Core Application & Setup** component initializes the entire system and manages configurations. The **Agent Execution & Workflow Engine** then takes over, orchestrating the execution of various **Agent Workflow Patterns** (like orchestration, routing, or parallel processing) which define the agent's high-level behaviors. These workflows, in turn, leverage the **Agent Core & LLM Integration** component to interact with Large Language Models and perform agent-specific actions. The **MCP Service Integration** component is crucial for discovering and connecting to external Model Context Protocol (MCP) servers, providing the necessary tools and resources to the agents. Finally, the **Human Interaction Layer** enables human-in-the-loop capabilities, allowing agents to request and receive input from users, which is then processed by the Execution Engine. -### Core Application & Setup [[Expand]](./Core_Application_Setup) +### Core Application & Setup Initializes the entire agent framework, establishes the global application context, and manages the loading, parsing, and provision of application settings and sensitive information. It acts as the central orchestrator for the agent's environment and ensures all components operate with correct parameters. @@ -48,7 +49,7 @@ Initializes the entire agent framework, establishes the global application conte - `mcp_agent/config.py` (1:1) -### Agent Execution & Workflow Engine [[Expand]](./Agent_Execution_Workflow_Engine) +### Agent Execution & Workflow Engine Manages the lifecycle and execution of tasks, activities, and complex workflows. It provides mechanisms for registering executable units and handling their state, supporting both immediate asynchronous execution and durable, long-running workflows. @@ -61,7 +62,7 @@ Manages the lifecycle and execution of tasks, activities, and complex workflows. - `mcp_agent/executor/workflow.py` (1:1) -### Agent Core & LLM Integration [[Expand]](./Agent_Core_LLM_Integration) +### Agent Core & LLM Integration Defines the fundamental interface and capabilities of an AI agent. It encapsulates interactions with Large Language Models (LLMs), external tools, prompts, and resources, providing a consistent and extensible model for agent behavior. It also offers a standardized and augmented interface for interacting with various LLM providers. @@ -72,7 +73,7 @@ Defines the fundamental interface and capabilities of an AI agent. It encapsulat - `mcp_agent/workflows/llm/llm_selector.py` (1:1) -### MCP Service Integration [[Expand]](./MCP_Service_Integration) +### MCP Service Integration Serves as a central point for discovering, collecting, and managing capabilities (tools, prompts, resources) exposed by various Model Context Protocol (MCP) servers. It also manages the underlying network connections and communication sessions with these external services. @@ -83,7 +84,7 @@ Serves as a central point for discovering, collecting, and managing capabilities - `mcp_agent/mcp/mcp_server_registry.py` (1:1) -### Agent Workflow Patterns [[Expand]](./Agent_Workflow_Patterns) +### Agent Workflow Patterns Implements various complex, multi-step agent behaviors and patterns. This includes orchestrating sequences of actions, routing requests, classifying user intents, parallelizing LLM calls, and facilitating collaborative problem-solving among multiple agents. @@ -96,7 +97,7 @@ Implements various complex, multi-step agent behaviors and patterns. This includ - `mcp_agent/workflows/swarm/swarm.py` (1:1) -### Human Interaction Layer [[Expand]](./Human_Interaction_Layer) +### Human Interaction Layer Handles all interactions requiring human input or feedback. It provides mechanisms for agents to request information from users and process their responses, enabling human-in-the-loop workflows. @@ -104,8 +105,3 @@ Handles all interactions requiring human input or feedback. It provides mechanis - `mcp_agent/human_input/handler.py` (1:1) - `mcp_agent/human_input/types.py` (1:1) - - - - -### [FAQ](https://github.com/CodeBoarding/GeneratedOnBoardings/tree/main?tab=readme-ov-file#faq) \ No newline at end of file