simple_rag_mcp_agent¶

SimpleRAG Agent for MCP Server Discovery.

This agent uses the enhanced retriever to help users find and understand MCP servers. It can answer questions about server capabilities, suggest servers based on needs, and provide detailed information about specific servers.

Attributes¶

`app`
`rag_agent`

Classes¶

`MCPRetrieverWrapper`	Wrapper to make our enhanced retriever compatible with LangChain.
`MCPSimpleRAGAgent`	SimpleRAG agent specialized for MCP server discovery.
`QueryRequest`	!!! abstract "Usage Documentation"
`QueryResponse`	!!! abstract "Usage Documentation"

Functions¶

`ask_agent`(request)	Ask the RAG agent a question about MCP servers.
`create_mcp_rag_agent`(→ MCPSimpleRAGAgent)	Factory function to create configured MCP RAG agent.
`demo_mcp_rag_agent`()	Demonstrate the MCP RAG agent.
`root`()	Simple web UI for testing the agent.
`startup_event`()	Initialize the RAG agent on startup.

Module Contents¶

class simple_rag_mcp_agent.MCPRetrieverWrapper(enhanced_retriever: haive.mcp.working_enhanced_retriever.WorkingEnhancedRetriever)¶

Bases: langchain_core.retrievers.BaseRetriever

Wrapper to make our enhanced retriever compatible with LangChain.

enhanced_retriever¶

property llm¶: Llm.

class simple_rag_mcp_agent.MCPSimpleRAGAgent(name: str = 'mcp_rag_agent', **kwargs)¶

Bases: haive.agents.rag.simple.agent.SimpleRAGAgent

SimpleRAG agent specialized for MCP server discovery.

get_system_prompt() → str¶: Custom system prompt for MCP assistance.

mcp_retriever¶

class simple_rag_mcp_agent.QueryRequest(/, **data: Any)¶

Bases: pydantic.BaseModel

!!! abstract “Usage Documentation”: [Models](../concepts/models.md)

A base class for creating Pydantic models.

__class_vars__¶: The names of the class variables defined on the model.

__private_attributes__¶: Metadata about the private attributes of the model.

__signature__¶: The synthesized __init__ [Signature][inspect.Signature] of the model.

__pydantic_complete__¶: Whether model building is completed, or if there are still undefined fields.

__pydantic_core_schema__¶: The core schema of the model.

__pydantic_custom_init__¶: Whether the model has a custom __init__ function.

__pydantic_decorators__¶: Metadata containing the decorators defined on the model. This replaces Model.__validators__ and Model.__root_validators__ from Pydantic V1.

__pydantic_generic_metadata__¶: Metadata for generic models; contains data used for a similar purpose to __args__, __origin__, __parameters__ in typing-module generics. May eventually be replaced by these.

__pydantic_parent_namespace__¶: Parent namespace of the model, used for automatic rebuilding of models.

__pydantic_post_init__¶: The name of the post-init method for the model, if defined.

__pydantic_root_model__¶: Whether the model is a [RootModel][pydantic.root_model.RootModel].

__pydantic_serializer__¶: The pydantic-core SchemaSerializer used to dump instances of the model.

__pydantic_validator__¶: The pydantic-core SchemaValidator used to validate instances of the model.

__pydantic_fields__¶: A dictionary of field names and their corresponding [FieldInfo][pydantic.fields.FieldInfo] objects.

__pydantic_computed_fields__¶: A dictionary of computed field names and their corresponding [ComputedFieldInfo][pydantic.fields.ComputedFieldInfo] objects.

__pydantic_extra__¶: A dictionary containing extra values, if [extra][pydantic.config.ConfigDict.extra] is set to ‘allow’.

__pydantic_fields_set__¶: The names of fields explicitly set during instantiation.

__pydantic_private__¶: Values of private attributes set on the model instance.

max_documents: int = 5¶

query: str¶

class simple_rag_mcp_agent.QueryResponse(/, **data: Any)¶

Bases: pydantic.BaseModel

!!! abstract “Usage Documentation”: [Models](../concepts/models.md)

A base class for creating Pydantic models.

__class_vars__¶: The names of the class variables defined on the model.

__private_attributes__¶: Metadata about the private attributes of the model.

__signature__¶: The synthesized __init__ [Signature][inspect.Signature] of the model.

__pydantic_complete__¶: Whether model building is completed, or if there are still undefined fields.

__pydantic_core_schema__¶: The core schema of the model.

__pydantic_custom_init__¶: Whether the model has a custom __init__ function.

__pydantic_decorators__¶: Metadata containing the decorators defined on the model. This replaces Model.__validators__ and Model.__root_validators__ from Pydantic V1.

__pydantic_generic_metadata__¶: Metadata for generic models; contains data used for a similar purpose to __args__, __origin__, __parameters__ in typing-module generics. May eventually be replaced by these.

__pydantic_parent_namespace__¶: Parent namespace of the model, used for automatic rebuilding of models.

__pydantic_post_init__¶: The name of the post-init method for the model, if defined.

__pydantic_root_model__¶: Whether the model is a [RootModel][pydantic.root_model.RootModel].

__pydantic_serializer__¶: The pydantic-core SchemaSerializer used to dump instances of the model.

__pydantic_validator__¶: The pydantic-core SchemaValidator used to validate instances of the model.

__pydantic_fields__¶: A dictionary of field names and their corresponding [FieldInfo][pydantic.fields.FieldInfo] objects.

__pydantic_computed_fields__¶: A dictionary of computed field names and their corresponding [ComputedFieldInfo][pydantic.fields.ComputedFieldInfo] objects.

__pydantic_extra__¶: A dictionary containing extra values, if [extra][pydantic.config.ConfigDict.extra] is set to ‘allow’.

__pydantic_fields_set__¶: The names of fields explicitly set during instantiation.

__pydantic_private__¶: Values of private attributes set on the model instance.

query: str¶

response: str¶

retrieved_servers: list[dict[str, Any]]¶

timestamp: str¶

async simple_rag_mcp_agent.ask_agent(request: QueryRequest)¶: Ask the RAG agent a question about MCP servers.

async simple_rag_mcp_agent.create_mcp_rag_agent(model: str = 'gpt-3.5-turbo') → MCPSimpleRAGAgent¶: Factory function to create configured MCP RAG agent.

async simple_rag_mcp_agent.demo_mcp_rag_agent()¶: Demonstrate the MCP RAG agent.

async simple_rag_mcp_agent.root()¶: Simple web UI for testing the agent.

async simple_rag_mcp_agent.startup_event()¶: Initialize the RAG agent on startup.

simple_rag_mcp_agent.app¶

simple_rag_mcp_agent.rag_agent = None¶