Uso de la memoria del agente con un servidor MCP
Una aplicación puede utilizar el SDK de Oracle AI Agent Memory para llamar directamente a las operaciones de memoria. Cuando esas operaciones necesitan estar disponibles para varios agentes o tiempos de ejecución, un servidor MCP puede exponerlas como herramientas a través de una interfaz estándar.
En esta guía, expondrá las herramientas de Oracle AI Agent Memory como protocolo de contexto de modelo (MCP) para que los entornos de ejecución de agente compatibles puedan acceder a la memoria a través de un servidor MCP.
Lo que aprenderás
En esta guía, aprenderá a:
- crear un servidor MCP que exponga herramientas de memoria y subprocesos;
- Conecte el mismo servidor desde LangGraph y WayFlow.
Nota: Utilice un servidor MCP cuando las capacidades de memoria deban compartirse entre agentes, tiempos de ejecución o aplicaciones. Utilice el SDK directamente cuando una única aplicación controle tanto la lógica del agente como el acceso a la memoria.
Indicación: Para la configuración del paquete, consulte Get Started with Agent Memory. Para aprender a configurar una instancia local de Oracle AI Database para este ejemplo, siga Ejecución local de Oracle AI Database. En este tutorial se asume que ya tiene un pool, embebido y LLM de Oracle DB configurados.
Escribir el servidor MCP
Cree un servidor MCP que muestre las API de memoria de Oracle Agent como herramientas. En este ejemplo, se mantiene la superficie de la herramienta intencionalmente pequeña: get_or_create_thread, add_messages, get_messages, add_memory y search_memory.
El ejemplo devuelve cadenas JSON mediante json.dumps(...) para cada resultado de herramienta. Esto mantiene el esquema de salida simple y funciona correctamente entre los clientes MCP. Su herramienta add_memory acepta los valores memory_type "memory" (valor por defecto), "fact", "guideline" y "preference".
Indicación: Instale la biblioteca MCP por separado antes de ejecutar este ejemplo de servidor.
import argparse
import json
import oracledb
import os
from typing import Any, Literal
from mcp.server.fastmcp import FastMCP
from pydantic import BaseModel
from oracleagentmemory.apis.records import ScopedRecord
from oracleagentmemory.core.dbschemapolicy import SchemaPolicy
from oracleagentmemory.core.embedders.embedder import Embedder
from oracleagentmemory.core.llms.llm import Llm
from oracleagentmemory.core.oracleagentmemory import OracleAgentMemory
embedder = Embedder(
model="YOUR_EMBEDDING_MODEL",
api_base="YOUR_EMBEDDING_API_BASE",
api_key="YOUR_EMBEDDING_API_KEY",
)
llm = Llm(
model="YOUR_LLM_MODEL",
api_base="YOUR_LLM_API_BASE",
api_key="YOUR_LLM_API_KEY",
)
db_pool = oracledb.SessionPool(
user="YOUR DB USER",
password="YOUR DB PASSWORD",
dsn="localhost:1521/...",
)
memory_store_id = "T_MEM_EXTRACTION"
class MessageT(BaseModel):
role: str
content: str
id: str | None = None
timestamp: str | None = None
metadata: dict[str, Any] | None = None
def _serialize_search_result(result: Any) -> dict[str, Any]:
record = result.record
payload = {
"id": result.id,
"content": result.content,
"record_type": record.record_type,
}
if isinstance(record, ScopedRecord):
payload.update(
{
"user_id": record.user_id,
"agent_id": record.agent_id,
"thread_id": record.thread_id,
}
)
return payload
def create_server(
memory: OracleAgentMemory | None = None,
host: str | None = None,
port: int | None = None,
path: str | None = None,
) -> FastMCP:
"""Create a FastMCP server exposing Oracle Agent Memory tools."""
agent_memory = memory or OracleAgentMemory(
connection=db_pool,
embedder=embedder,
llm=llm,
memory_store_id=memory_store_id,
schema_policy=SchemaPolicy.CREATE_IF_NECESSARY,
)
resolved_path = path or os.environ.get("MEMORY_MCP_PATH", "/mcp")
if not resolved_path.startswith("/"):
resolved_path = f"/{resolved_path}"
server = FastMCP(
name="Oracle Agent Memory MCP Server",
host=host or os.environ.get("MEMORY_MCP_HOST", "localhost"),
port=int(port if port is not None else os.environ.get("MEMORY_MCP_PORT", "8003")),
streamable_http_path=resolved_path,
)
@server.tool(
description=(
"Get an existing thread by thread_id, or create one from user_id and optional "
"agent_id."
)
)
def get_or_create_thread(
thread_id: str | None = None,
user_id: str | None = None,
agent_id: str | None = None,
) -> str:
create_kwargs: dict[str, str] = {}
if thread_id is not None:
try:
thread = agent_memory.get_thread(thread_id)
return json.dumps(
{
"thread_id": thread.thread_id,
"user_id": thread.user_id,
"agent_id": thread.agent_id,
}
)
except KeyError:
create_kwargs["thread_id"] = thread_id
if user_id is not None:
create_kwargs["user_id"] = user_id
if agent_id is not None:
create_kwargs["agent_id"] = agent_id
thread = agent_memory.create_thread(**create_kwargs)
return json.dumps(
{
"thread_id": thread.thread_id,
"user_id": thread.user_id,
"agent_id": thread.agent_id,
}
)
@server.tool(
description=(
"Add durable memory content as a general memory, fact, guideline, or "
"preference; optionally scope it by user_id, agent_id, and thread_id."
)
)
def add_memory(
content: str,
memory_type: Literal["memory", "fact", "guideline", "preference"] = "memory",
user_id: str | None = None,
agent_id: str | None = None,
thread_id: str | None = None,
) -> str:
add_kwargs: dict[str, str] = {"memory_type": memory_type}
if user_id is not None:
add_kwargs["user_id"] = user_id
if agent_id is not None:
add_kwargs["agent_id"] = agent_id
if thread_id is not None:
add_kwargs["thread_id"] = thread_id
return json.dumps({"memory_id": agent_memory.add_memory(content, **add_kwargs)})
@server.tool(
description="Add messages to an existing thread using messages and thread_id."
)
def add_messages(messages: list[MessageT], thread_id: str) -> str:
thread = agent_memory.get_thread(thread_id)
payload = [message.model_dump(exclude_none=True) for message in messages]
return json.dumps({"message_ids": thread.add_messages(payload)})
@server.tool(description="Get messages from an existing thread using thread_id.")
def get_messages(thread_id: str) -> str:
thread = agent_memory.get_thread(thread_id)
return json.dumps(
{
"messages": [
{
"id": getattr(message, "id", None),
"role": message.role,
"content": message.content,
"timestamp": message.timestamp,
"metadata": message.metadata,
}
for message in thread.get_messages()
]
}
)
@server.tool(
description=(
"Search Oracle Agent Memory for durable memory and thread content. "
"Pass user_id directly, or pass thread_id so the server can resolve the user scope."
)
)
def search_memory(
query: str,
user_id: str | None = None,
agent_id: str | None = None,
thread_id: str | None = None,
) -> str:
if user_id is not None:
resolved_user_id = user_id
resolved_agent_id = agent_id
elif thread_id is not None:
thread = agent_memory.get_thread(thread_id)
if thread.user_id is None:
raise ValueError(
f"Thread `{thread_id}` is not associated with a user_id, so "
"search_memory cannot build a valid OracleAgentMemory search scope."
)
resolved_user_id = thread.user_id
resolved_agent_id = agent_id if agent_id is not None else thread.agent_id
else:
raise ValueError("search_memory requires either `user_id` or `thread_id`.")
search_kwargs: dict[str, Any] = {"query": query, "user_id": resolved_user_id}
if resolved_agent_id is not None:
search_kwargs["agent_id"] = resolved_agent_id
search_kwargs["exact_agent_match"] = True
if thread_id is not None:
search_kwargs["thread_id"] = thread_id
search_kwargs["exact_thread_match"] = True
results = agent_memory.search(**search_kwargs)
return json.dumps(
{
"results": [
_serialize_search_result(result) for result in results
]
}
)
return server| Referencia de API: OracleAgentMemory | OracleThread |
Ejecución del servidor MCP
Por defecto, el servidor recibe en http://localhost:8003/mcp. Sustituya la dirección de enlace por MEMORY_MCP_HOST, MEMORY_MCP_PORT y MEMORY_MCP_PATH cuando sea necesario.
def main(host: str, port: int) -> None:
server = create_server(host=host, port=port)
server.run(transport="streamable-http")
if __name__ == "__main__":
parser = argparse.ArgumentParser(description="Process host, port, and mode.")
parser.add_argument(
"--host", type=str, help='The host address (e.g., "localhost" or "127.0.0.1")'
)
parser.add_argument("--port", type=int, help="The port number (e.g., 8080)")
args = parser.parse_args()
main(host=args.host, port=args.port)Utilizar el servidor de LangGraph
LangGraph puede consumir herramientas MCP a través de langchain-mcp-adapters. El agente se conecta al servidor de memoria a través de streamable-http y permite que el modelo llame directamente a las herramientas de memoria del agente de Oracle.
Nota: Instale langchain-mcp-adapters para este ejemplo de cliente. Las herramientas MCP de LangGraph necesitan ejecutar el agente con métodos asíncronos como ainvoke().
Configurar el cliente LangGraph
import os
from datetime import timedelta
import anyio
from langchain.agents import create_agent
from langchain_core.messages import HumanMessage
from langchain_mcp_adapters.client import MultiServerMCPClient
from langchain_openai import ChatOpenAI
mcp_url = os.environ.get("MEMORY_MCP_URL", "http://localhost:8003/mcp")
langgraph_llm = ChatOpenAI(
model="gpt-4.1-mini",
api_key="YOUR_OPENAI_API_KEY",
)
async def build_langgraph_agent():
memory_tools = await MultiServerMCPClient(
{
"memory": {
"transport": "streamable_http",
"url": mcp_url,
"timeout": timedelta(seconds=30),
"sse_read_timeout": timedelta(seconds=30),
}
}
).get_tools()
return create_agent(
model=langgraph_llm,
tools=memory_tools,
system_prompt=(
"You are an assistant using Oracle Agent Memory through MCP. "
"Create threads before writing messages, use add_memory for durable facts, "
"and call search_memory when the user asks about prior context."
),
)Ejecución de un agente LangGraph en el servidor MCP
async def run_langgraph_agent() -> None:
agent = await build_langgraph_agent()
first_turn = await agent.ainvoke(
{
"messages": [
HumanMessage(
content=(
"Use the memory MCP tools to create thread `mcp_demo_thread` for user "
"`user_123`, add the durable memory `The user likes orange juice with "
"breakfast.`, and confirm when the memory is stored."
)
)
]
}
)
print(first_turn["messages"][-1].content)
#The durable memory has been stored successfully:
#- Thread ID: `mcp_demo_thread`
#- User ID: `user_123`
second_turn = await agent.ainvoke(
{
"messages": [
HumanMessage(
content=(
"Search memory for `orange juice` in thread `mcp_demo_thread` and tell "
"me what Oracle Agent Memory returned."
)
)
]
}
)
print(second_turn["messages"][-1].content)
#The search returned matching memory records for:
#"The user likes orange juice with breakfast."Uso del servidor desde WayFlow
WayFlow puede consumir el mismo servidor MCP mediante MCPToolBox con un StreamableHTTPTransport. Consulte los documentos de MCPToolBox de WayFlow para obtener detalles de la API.
Nota: Instale wayflowcore para este ejemplo de cliente.
Configuración del cliente WayFlow
import os
from wayflowcore.agent import Agent
from wayflowcore.mcp import MCPToolBox, StreamableHTTPTransport, enable_mcp_without_auth
from wayflowcore.models import OpenAICompatibleModel
mcp_url = os.environ.get("MEMORY_MCP_URL", "http://localhost:8003/mcp")
wayflow_llm = OpenAICompatibleModel(
model_id="gpt-4.1-mini",
base_url="YOUR_OPENAI_API_BASE",
api_key="YOUR_OPENAI_API_KEY",
)
enable_mcp_without_auth()
memory_tools = MCPToolBox(client_transport=StreamableHTTPTransport(url=mcp_url))
agent = Agent(
llm=wayflow_llm,
agent_id="memory_mcp_agent",
custom_instruction=(
"You are an assistant using Oracle Agent Memory through MCP. "
"Create threads before writing messages, use add_memory for durable facts, "
"and call search_memory when the user asks about prior context."
),
tools=[memory_tools],
)Ejecución de un agente de WayFlow en el servidor MCP
first_session = agent.start_conversation()
first_session.append_user_message(
"Use the memory MCP tools to create thread `mcp_demo_thread` for user `user_123`, "
"add the durable memory `The user likes orange juice with breakfast.`, and confirm "
"when the memory is stored."
)
first_session.execute()
print(first_session.get_last_message().content)
#The durable memory has been stored successfully:
#- Thread ID: `mcp_demo_thread`
#- User ID: `user_123`
second_session = agent.start_conversation()
second_session.append_user_message(
"Search memory for `orange juice` in thread `mcp_demo_thread` and tell me what "
"Oracle Agent Memory returned."
)
second_session.execute()
print(second_session.get_last_message().content)
#The memory search returned matching records for:
#"The user likes orange juice with breakfast."Notas de seguridad y despliegue
El servidor de ejemplo está abierto intencionadamente y es sólo local. Para uso de producción, agregue autenticación y seguridad de transporte, restrinja a qué usuarios o agentes puede acceder cada emisor de llamada y considere agregar puertas de confirmación o aprobación en torno a operaciones de escritura como add_memory o add_messages.
Para obtener más información, consulte Consideraciones de seguridad.
Pasos Siguientes
En esta guía, expusimos la memoria del agente de Oracle a través de MCP y reutilizamos la misma superficie de herramientas de LangGraph y WayFlow.
Posibles pasos siguientes:
- agregar más herramientas de memoria solo si los flujos de trabajo del agente las necesitan; consulte Hoja de referencia
- adaptar el servidor a su entorno de despliegue y a las restricciones operativas; consulte Ejecución local de Oracle AI Database
Código Completo
Servidor MCP
#Copyright © 2026 Oracle and/or its affiliates.
#This software is under the Apache License 2.0
#(LICENSE-APACHE or http://www.apache.org/licenses/LICENSE-2.0) or Universal Permissive License
#(UPL) 1.0 (LICENSE-UPL or https://oss.oracle.com/licenses/upl), at your option.
#Oracle Agent Memory Code Example - Integration with MCP Server
#--------------------------------------------------------------
##Build the MCP server
import argparse
import json
import oracledb
import os
from typing import Any, Literal
from mcp.server.fastmcp import FastMCP
from pydantic import BaseModel
from oracleagentmemory.apis.records import ScopedRecord
from oracleagentmemory.core.dbschemapolicy import SchemaPolicy
from oracleagentmemory.core.embedders.embedder import Embedder
from oracleagentmemory.core.llms.llm import Llm
from oracleagentmemory.core.oracleagentmemory import OracleAgentMemory
embedder = Embedder(
model="YOUR_EMBEDDING_MODEL",
api_base="YOUR_EMBEDDING_API_BASE",
api_key="YOUR_EMBEDDING_API_KEY",
)
llm = Llm(
model="YOUR_LLM_MODEL",
api_base="YOUR_LLM_API_BASE",
api_key="YOUR_LLM_API_KEY",
)
db_pool = oracledb.SessionPool(
user="YOUR DB USER",
password="YOUR DB PASSWORD",
dsn="localhost:1521/...",
)
memory_store_id = "T_MEM_EXTRACTION"
class MessageT(BaseModel):
role: str
content: str
id: str | None = None
timestamp: str | None = None
metadata: dict[str, Any] | None = None
def _serialize_search_result(result: Any) -> dict[str, Any]:
record = result.record
payload = {
"id": result.id,
"content": result.content,
"record_type": record.record_type,
}
if isinstance(record, ScopedRecord):
payload.update(
{
"user_id": record.user_id,
"agent_id": record.agent_id,
"thread_id": record.thread_id,
}
)
return payload
def create_server(
memory: OracleAgentMemory | None = None,
host: str | None = None,
port: int | None = None,
path: str | None = None,
) -> FastMCP:
"""Create a FastMCP server exposing Oracle Agent Memory tools."""
agent_memory = memory or OracleAgentMemory(
connection=db_pool,
embedder=embedder,
llm=llm,
memory_store_id=memory_store_id,
schema_policy=SchemaPolicy.CREATE_IF_NECESSARY,
)
resolved_path = path or os.environ.get("MEMORY_MCP_PATH", "/mcp")
if not resolved_path.startswith("/"):
resolved_path = f"/{resolved_path}"
server = FastMCP(
name="Oracle Agent Memory MCP Server",
host=host or os.environ.get("MEMORY_MCP_HOST", "localhost"),
port=int(port if port is not None else os.environ.get("MEMORY_MCP_PORT", "8003")),
streamable_http_path=resolved_path,
)
@server.tool(
description=(
"Get an existing thread by thread_id, or create one from user_id and optional "
"agent_id."
)
)
def get_or_create_thread(
thread_id: str | None = None,
user_id: str | None = None,
agent_id: str | None = None,
) -> str:
create_kwargs: dict[str, str] = {}
if thread_id is not None:
try:
thread = agent_memory.get_thread(thread_id)
return json.dumps(
{
"thread_id": thread.thread_id,
"user_id": thread.user_id,
"agent_id": thread.agent_id,
}
)
except KeyError:
create_kwargs["thread_id"] = thread_id
if user_id is not None:
create_kwargs["user_id"] = user_id
if agent_id is not None:
create_kwargs["agent_id"] = agent_id
thread = agent_memory.create_thread(**create_kwargs)
return json.dumps(
{
"thread_id": thread.thread_id,
"user_id": thread.user_id,
"agent_id": thread.agent_id,
}
)
@server.tool(
description=(
"Add durable memory content as a general memory, fact, guideline, or "
"preference; optionally scope it by user_id, agent_id, and thread_id."
)
)
def add_memory(
content: str,
memory_type: Literal["memory", "fact", "guideline", "preference"] = "memory",
user_id: str | None = None,
agent_id: str | None = None,
thread_id: str | None = None,
) -> str:
add_kwargs: dict[str, str] = {"memory_type": memory_type}
if user_id is not None:
add_kwargs["user_id"] = user_id
if agent_id is not None:
add_kwargs["agent_id"] = agent_id
if thread_id is not None:
add_kwargs["thread_id"] = thread_id
return json.dumps({"memory_id": agent_memory.add_memory(content, **add_kwargs)})
@server.tool(
description="Add messages to an existing thread using messages and thread_id."
)
def add_messages(messages: list[MessageT], thread_id: str) -> str:
thread = agent_memory.get_thread(thread_id)
payload = [message.model_dump(exclude_none=True) for message in messages]
return json.dumps({"message_ids": thread.add_messages(payload)})
@server.tool(description="Get messages from an existing thread using thread_id.")
def get_messages(thread_id: str) -> str:
thread = agent_memory.get_thread(thread_id)
return json.dumps(
{
"messages": [
{
"id": getattr(message, "id", None),
"role": message.role,
"content": message.content,
"timestamp": message.timestamp,
"metadata": message.metadata,
}
for message in thread.get_messages()
]
}
)
@server.tool(
description=(
"Search Oracle Agent Memory for durable memory and thread content. "
"Pass user_id directly, or pass thread_id so the server can resolve the user scope."
)
)
def search_memory(
query: str,
user_id: str | None = None,
agent_id: str | None = None,
thread_id: str | None = None,
) -> str:
if user_id is not None:
resolved_user_id = user_id
resolved_agent_id = agent_id
elif thread_id is not None:
thread = agent_memory.get_thread(thread_id)
if thread.user_id is None:
raise ValueError(
f"Thread `{thread_id}` is not associated with a user_id, so "
"search_memory cannot build a valid OracleAgentMemory search scope."
)
resolved_user_id = thread.user_id
resolved_agent_id = agent_id if agent_id is not None else thread.agent_id
else:
raise ValueError("search_memory requires either `user_id` or `thread_id`.")
search_kwargs: dict[str, Any] = {"query": query, "user_id": resolved_user_id}
if resolved_agent_id is not None:
search_kwargs["agent_id"] = resolved_agent_id
search_kwargs["exact_agent_match"] = True
if thread_id is not None:
search_kwargs["thread_id"] = thread_id
search_kwargs["exact_thread_match"] = True
results = agent_memory.search(**search_kwargs)
return json.dumps(
{
"results": [
_serialize_search_result(result) for result in results
]
}
)
return server
##Run the MCP server
def main(host: str, port: int) -> None:
server = create_server(host=host, port=port)
server.run(transport="streamable-http")
if __name__ == "__main__":
parser = argparse.ArgumentParser(description="Process host, port, and mode.")
parser.add_argument(
"--host", type=str, help='The host address (e.g., "localhost" or "127.0.0.1")'
)
parser.add_argument("--port", type=int, help="The port number (e.g., 8080)")
args = parser.parse_args()
main(host=args.host, port=args.port)Cliente LangGraph
#Copyright © 2026 Oracle and/or its affiliates.
#This software is under the Apache License 2.0
#(LICENSE-APACHE or http://www.apache.org/licenses/LICENSE-2.0) or Universal Permissive License
#(UPL) 1.0 (LICENSE-UPL or https://oss.oracle.com/licenses/upl), at your option.
#Oracle Agent Memory Code Example - LangGraph MCP Client
#-------------------------------------------------------
##Connect LangGraph to the MCP server
import os
from datetime import timedelta
import anyio
from langchain.agents import create_agent
from langchain_core.messages import HumanMessage
from langchain_mcp_adapters.client import MultiServerMCPClient
from langchain_openai import ChatOpenAI
mcp_url = os.environ.get("MEMORY_MCP_URL", "http://localhost:8003/mcp")
langgraph_llm = ChatOpenAI(
model="gpt-4.1-mini",
api_key="YOUR_OPENAI_API_KEY",
)
async def build_langgraph_agent():
memory_tools = await MultiServerMCPClient(
{
"memory": {
"transport": "streamable_http",
"url": mcp_url,
"timeout": timedelta(seconds=30),
"sse_read_timeout": timedelta(seconds=30),
}
}
).get_tools()
return create_agent(
model=langgraph_llm,
tools=memory_tools,
system_prompt=(
"You are an assistant using Oracle Agent Memory through MCP. "
"Create threads before writing messages, use add_memory for durable facts, "
"and call search_memory when the user asks about prior context."
),
)
##Use the MCP server from LangGraph
async def run_langgraph_agent() -> None:
agent = await build_langgraph_agent()
first_turn = await agent.ainvoke(
{
"messages": [
HumanMessage(
content=(
"Use the memory MCP tools to create thread `mcp_demo_thread` for user "
"`user_123`, add the durable memory `The user likes orange juice with "
"breakfast.`, and confirm when the memory is stored."
)
)
]
}
)
print(first_turn["messages"][-1].content)
#The durable memory has been stored successfully:
#- Thread ID: `mcp_demo_thread`
#- User ID: `user_123`
second_turn = await agent.ainvoke(
{
"messages": [
HumanMessage(
content=(
"Search memory for `orange juice` in thread `mcp_demo_thread` and tell "
"me what Oracle Agent Memory returned."
)
)
]
}
)
print(second_turn["messages"][-1].content)
#The search returned matching memory records for:
#"The user likes orange juice with breakfast."
anyio.run(run_langgraph_agent)Cliente de WayFlow
#Copyright © 2026 Oracle and/or its affiliates.
#This software is under the Apache License 2.0
#(LICENSE-APACHE or http://www.apache.org/licenses/LICENSE-2.0) or Universal Permissive License
#(UPL) 1.0 (LICENSE-UPL or https://oss.oracle.com/licenses/upl), at your option.
#Oracle Agent Memory Code Example - WayFlow MCP Client
#-----------------------------------------------------
##Connect WayFlow to the MCP server
import os
from wayflowcore.agent import Agent
from wayflowcore.mcp import MCPToolBox, StreamableHTTPTransport, enable_mcp_without_auth
from wayflowcore.models import OpenAICompatibleModel
mcp_url = os.environ.get("MEMORY_MCP_URL", "http://localhost:8003/mcp")
wayflow_llm = OpenAICompatibleModel(
model_id="gpt-4.1-mini",
base_url="YOUR_OPENAI_API_BASE",
api_key="YOUR_OPENAI_API_KEY",
)
enable_mcp_without_auth()
memory_tools = MCPToolBox(client_transport=StreamableHTTPTransport(url=mcp_url))
agent = Agent(
llm=wayflow_llm,
agent_id="memory_mcp_agent",
custom_instruction=(
"You are an assistant using Oracle Agent Memory through MCP. "
"Create threads before writing messages, use add_memory for durable facts, "
"and call search_memory when the user asks about prior context."
),
tools=[memory_tools],
)
##Use the MCP server from WayFlow
first_session = agent.start_conversation()
first_session.append_user_message(
"Use the memory MCP tools to create thread `mcp_demo_thread` for user `user_123`, "
"add the durable memory `The user likes orange juice with breakfast.`, and confirm "
"when the memory is stored."
)
first_session.execute()
print(first_session.get_last_message().content)
#The durable memory has been stored successfully:
#- Thread ID: `mcp_demo_thread`
#- User ID: `user_123`
second_session = agent.start_conversation()
second_session.append_user_message(
"Search memory for `orange juice` in thread `mcp_demo_thread` and tell me what "
"Oracle Agent Memory returned."
)
second_session.execute()
print(second_session.get_last_message().content)
#The memory search returned matching records for:
#"The user likes orange juice with breakfast."