Reflect MCP Server for OpenAI Agents SDK 10 tools — connect in under 2 minutes
The OpenAI Agents SDK enables production-grade agent workflows in Python. Connect Reflect through Vinkius and your agents gain typed, auto-discovered tools with built-in guardrails. no manual schema definitions required.
ASK AI ABOUT THIS MCP SERVER
Vinkius supports streamable HTTP and SSE.
import asyncio
from agents import Agent, Runner
from agents.mcp import MCPServerStreamableHttp
async def main():
# Your Vinkius token. get it at cloud.vinkius.com
async with MCPServerStreamableHttp(
url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
) as mcp_server:
agent = Agent(
name="Reflect Assistant",
instructions=(
"You help users interact with Reflect. "
"You have access to 10 tools."
),
mcp_servers=[mcp_server],
)
result = await Runner.run(
agent, "List all available tools from Reflect"
)
print(result.final_output)
asyncio.run(main())
* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure
About Reflect MCP Server
Connect your Reflect account securely to your AI agent via their developer API. This integration grants your AI the ability to directly explore your networked thought graph, lookup personal notes, manage book highlights, and append daily thoughts asynchronously from your conversation interface.
The OpenAI Agents SDK auto-discovers all 10 tools from Reflect through native MCP integration. Build agents with built-in guardrails, tracing, and handoff patterns. chain multiple agents where one queries Reflect, another analyzes results, and a third generates reports, all orchestrated through Vinkius.
What you can do
- Explore Your Graph — Direct your AI to investigate connected insights within your Reflect graphs (
list_graphs). Request lists of your notes (list_notes) or retrieve the specific Markdown content of a single note (get_note). - Capture Ideas Instantly — Ask the agent to establish new permanent notes (
create_note) or quickly dump conversational insights, summaries, and tasks straight into your daily note (append_daily_note). - Analyze Connections — Instruct the AI to map out your thoughts by retrieving all backlinks pointing to a specific subject (
get_backlinks). - Save Links & Books — Let your AI automatically bookmark URLs (
create_link), browse your saved bookmarks (list_links), or explore your imported library of book highlights (list_books).
The Reflect MCP Server exposes 10 tools through the Vinkius. Connect it to OpenAI Agents SDK in under two minutes — no API keys to rotate, no infrastructure to provision, no vendor lock-in. Your configuration, your data, your control.
How to Connect Reflect to OpenAI Agents SDK via MCP
Follow these steps to integrate the Reflect MCP Server with OpenAI Agents SDK.
Install the SDK
Run pip install openai-agents in your Python environment
Replace the token
Replace [YOUR_TOKEN_HERE] with your Vinkius token from cloud.vinkius.com
Run the script
Save the code above and run it: python agent.py
Explore tools
The agent will automatically discover 10 tools from Reflect
Why Use OpenAI Agents SDK with the Reflect MCP Server
OpenAI Agents SDK provides unique advantages when paired with Reflect through the Model Context Protocol.
Native MCP integration via `MCPServerSse`, pass the URL and the SDK auto-discovers all tools with full type safety
Built-in guardrails, tracing, and handoff patterns let you build production-grade agents without reinventing safety infrastructure
Lightweight and composable: chain multiple agents and MCP servers in a single pipeline with minimal boilerplate
First-party OpenAI support ensures optimal compatibility with GPT models for tool calling and structured output
Reflect + OpenAI Agents SDK Use Cases
Practical scenarios where OpenAI Agents SDK combined with the Reflect MCP Server delivers measurable value.
Automated workflows: build agents that query Reflect, process the data, and trigger follow-up actions autonomously
Multi-agent orchestration: create specialist agents. one queries Reflect, another analyzes results, a third generates reports
Data enrichment pipelines: stream data through Reflect tools and transform it with OpenAI models in a single async loop
Customer support bots: agents query Reflect to resolve tickets, look up records, and update statuses without human intervention
Reflect MCP Tools for OpenAI Agents SDK (10)
These 10 tools become available when you connect Reflect to OpenAI Agents SDK via MCP:
append_daily_note
Optionally specify a list/heading name. Appends Markdown text to today's daily note
create_link
Reflect will automatically attempt to extract metadata. Saves a new web link/bookmark to a Reflect graph
create_note
Specify subject and Markdown content. Creates a new note in a Reflect graph
get_backlinks
Retrieves all notes that link to a specific note
get_current_user
Retrieves profile details for the authenticated Reflect user
get_note
Retrieves the full content and metadata of a Reflect note
list_books
Lists all books saved or imported into Reflect
list_graphs
Lists all Reflect graphs (workspaces) accessible by the user
list_links
Lists all saved links (bookmarks) in a graph
list_notes
Lists all notes within a specific Reflect graph
Example Prompts for Reflect in OpenAI Agents SDK
Ready-to-use prompts you can give your OpenAI Agents SDK agent to start working with Reflect immediately.
"List all available graphs in my Reflect account."
"Create a permanent note titled 'Meeting 2024 Strategy' inside my 'Personal Brain' graph with summary bullet points."
"Find notes linked by backlinks that point to my note 'React Learnings'."
Troubleshooting Reflect MCP Server with OpenAI Agents SDK
Common issues when connecting Reflect to OpenAI Agents SDK through the Vinkius, and how to resolve them.
MCPServerStreamableHttp not found
pip install --upgrade openai-agentsAgent not calling tools
Reflect + OpenAI Agents SDK FAQ
Common questions about integrating Reflect MCP Server with OpenAI Agents SDK.
How does the OpenAI Agents SDK connect to MCP?
MCPServerSse(url=...) to create a server connection. The SDK auto-discovers all tools and makes them available to your agent with full type information.Can I use multiple MCP servers in one agent?
MCPServerSse instances to the agent constructor. The agent can use tools from all connected servers within a single run.Does the SDK support streaming responses?
Connect Reflect with your favorite client
Step-by-step setup guides for every MCP-compatible client and framework:
Anthropic's native desktop app for Claude with built-in MCP support.
AI-first code editor with integrated LLM-powered coding assistance.
GitHub Copilot in VS Code with Agent mode and MCP support.
Purpose-built IDE for agentic AI coding workflows.
Autonomous AI coding agent that runs inside VS Code.
Anthropic's agentic CLI for terminal-first development.
Python SDK for building production-grade OpenAI agent workflows.
Google's framework for building production AI agents.
Type-safe agent development for Python with first-class MCP support.
TypeScript toolkit for building AI-powered web applications.
TypeScript-native agent framework for modern web stacks.
Python framework for orchestrating collaborative AI agent crews.
Leading Python framework for composable LLM applications.
Data-aware AI agent framework for structured and unstructured sources.
Microsoft's framework for multi-agent collaborative conversations.
Connect Reflect to OpenAI Agents SDK
Get your token, paste the configuration, and start using 10 tools in under 2 minutes. No API key management needed.