How to Use the Greptile MCP in AutoGen

Q: Can I limit Greptile usage in AutoGen?

You can implement a custom agent wrapper that checks getgreptileusage before allowing a tool call. If the budget is hit, the agent stops querying.

Enable multi-agent debate and consensus using Greptile tools within your AutoGen workflows.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Greptile MCP to AutoGen

Create your Vinkius account to connect Greptile 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 Greptile with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Coordinate agents with Greptile

Give your AutoGen agents the ability to debate codebase changes by providing access to `query_codebase`. One agent can propose a fix while another verifies the logic against the codebase. This setup allows for sophisticated multi-agent loops where the codebase itself serves as the source of truth for all arguments. It ensures that decisions are grounded in reality.

Search and verify with multiple agents

Use `search_codebase` to feed evidence into your agent conversations. Agents can compare their findings and reach a consensus based on the actual lines of code returned by the tool. This reduces hallucinations by forcing agents to look up information before they make a claim. It turns your development environment into a collaborative workspace for your AI agents.

Monitor tool usage in agent groups

Keep an eye on how many resources your agents are consuming with `get_greptile_usage`. This is critical when you have multiple agents hitting the API simultaneously. You can set up a supervisor agent that monitors these stats. If usage spikes, the supervisor can throttle the use of expensive query tools to keep costs under control.

Setup guide

Set up Greptile 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 Greptile 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="Greptile_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent Greptile 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="Greptile_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent Greptile 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 Greptile. 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 Greptile 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 Greptile MCP in AutoGen

Greptile provides the agents with a shared, factual view of your codebase. This prevents agents from making contradictory claims based on outdated assumptions.

You can implement a custom agent wrapper that checks `get_greptile_usage` before allowing a tool call. If the budget is hit, the agent stops querying.

Yes, the MCP tools provide a unified interface for all agents in your group. Any agent with access can query the same indexed repositories.

The McpToolAdapter automatically maps the Greptile tool schema to your agent's requirements. You don't need to write custom glue code for the parameters.

It relies on standard MCP over HTTP or stdio. Your API key remains secure on your end, and the data is encrypted during transit to the Greptile backend.

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