How to Use the Convex MCP in AutoGen

Q: How does AutoGen handle errors from Convex MCP actions?

When runaction returns an error, your agents can debate the cause of the failure. They can automatically adjust the arguments and retry the execution.

Q: What is the benefit of slash paths for function calls?

Using runfunction with slash paths avoids syntax issues with standard colons. This makes it easier for LLMs to generate valid backend paths.

Let your AutoGen agents debate and execute Convex queries and mutations in real time.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Convex MCP to AutoGen

Create your Vinkius account to connect Convex to AutoGen and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup Convex with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Collaborative database operations

Multiple agents can now coordinate complex database tasks. One agent runs `run_query` to fetch the current state, while another reviews the data for validation. This prevents bad data from hitting your backend. The validator agent must approve the payload before the writer agent executes `run_mutation`.

Consensus-driven execution with this Convex MCP Server

Before triggering any external side effects, your agents can debate the necessity of the task. They call `run_action` only after reaching a shared agreement. This reduces unnecessary API calls and server load. Your performance agent can veto a heavy action if a cached query result is already sufficient.

Dividing backend tasks among specialist agents

Assign specific database duties to different specialized agents. Your reader agent focuses entirely on querying, while your writer agent handles state changes. By calling `run_function` with slash-separated paths, agents trigger specific backend operations cleanly. This modular setup keeps agent prompts short and focused.

Setup guide

Set up Convex MCP in AutoGen

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] package
Active Vinkius subscription with a valid endpoint token

1

Install AutoGen with MCP
Run pip install "autogen-ext[mcp]" autogen-agentchat. The MCP extension includes mcp_server_tools for stateless tool access.
2

Fetch tools from the MCP
Call mcp_server_tools(SseServerParams(url=...)) with your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Run your agent
Pass the tools to AssistantAgent and call agent.run(). The agent invokes Convex tools and returns structured results.

agent.py

from autogen_ext.tools.mcp import SseServerParams, mcp_server_tools
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

tools = await mcp_server_tools(server_params)

agent = AssistantAgent(
    name="Convex_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent Convex data")
print(result.messages[-1].content)

Get your connection token →

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] + autogen-agentchat
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Same packages as above. McpWorkbench is ideal when your agent needs stateful sessions across multiple tool calls.
2

Use McpWorkbench as context manager
Wrap your agent in async with McpWorkbench(...) to maintain shared state and resources. The workbench manages the full MCP session lifecycle.
3

Run with workbench
Pass workbench=workbench to your agent. State is preserved across multiple tool calls within the same session.

agent.py

from autogen_ext.tools.mcp import McpWorkbench, SseServerParams
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

async with McpWorkbench(server_params) as workbench:
    agent = AssistantAgent(
        name="Convex_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent Convex data")
    print(result.messages[-1].content)

Get your connection token →

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Convex. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect Convex now

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about Convex MCP in AutoGen

You use the Convex MCP tool adapter to convert the tools for your assistant agent. Simply pass the server URL and register the resulting tools during agent construction.

Yes, your agents can coordinate database tasks. One agent can execute `run_query` while another uses that data to build a `run_mutation` call.

When `run_action` returns an error, your agents can debate the cause of the failure. They can automatically adjust the arguments and retry the execution.

Using `run_function` with slash paths avoids syntax issues with standard colons. This makes it easier for LLMs to generate valid backend paths.

Your mutation arguments and database queries are processed inside a secure, ephemeral MCP sandbox. Vinkius never logs or inspects your actual payload content.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript