How to Use the Greptile MCP in OpenAI Agents SDK

Q: How do I ensure Greptile tools in OpenAI Agents SDK don't hallucinate file paths?

The server provides exact paths via searchbyfilepath. Your agent receives verified strings, not guesses, which prevents the typical issues found in loose context retrieval.

Plug Greptile directly into your OpenAI Agents SDK workflow to index, query, and search codebases with production-grade reliability.

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 OpenAI Agents SDK

Create your Vinkius account to connect Greptile to OpenAI Agents SDK 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 OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Full Indexing Control for OpenAI Agents SDK

Trigger `index_repository` or `reindex_repository` directly from your agent logic. You get immediate feedback on the state of your codebase through `get_repository_status`. Your agent handles the lifecycle of your indexed projects without leaving the Python runtime. This keeps your indexing operations locked into the same trace logs as your core agent logic.

Search and Query with Greptile MCP Server

Use `query_codebase` to feed your agent raw context from any repository. You can drill down into specific files using `search_by_filepath` to isolate relevant code sections. This MCP Server provides the raw data your agent needs to reason over complex logic. It bridges the gap between your agent's decision-making and your actual source files.

Track Usage and Metadata in OpenAI Agents SDK

Monitor your token spend with `get_greptile_usage` to ensure your agents stay within budget. Fetch specific details about your codebase using `get_file_info` or `list_repositories`. Knowing exactly what your agents are accessing is critical for production deployments. These tools expose the metadata you need to audit agent behavior and refine your search strategy.

Setup guide

Set up Greptile MCP in OpenAI Agents SDK

Prerequisites

Python 3.10+ installed
openai-agents package (pip install openai-agents)
Active Vinkius subscription with a valid endpoint token

1

Install the SDK

Run pip install openai-agents to install the OpenAI Agents SDK. The MCP integration is built-in — no extra dependencies needed.
2

Connect via SSE transport

Use MCPServerSse with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. The SDK auto-discovers all Greptile tools at runtime.
3

Create your Agent

Pass the MCP to Agent(mcp_servers=[server]). The agent receives Greptile tools as native definitions — JSON schemas resolve automatically.
4

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate Greptile tools and returns structured results. Copy the full example on the right to get started.

agent.py

import asyncio
from agents import Agent, Runner
from agents.mcp import MCPServerSse

async def main():
    async with MCPServerSse(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as server:
        agent = Agent(
            name="Greptile Agent",
            instructions="You have access to Greptile tools.",
            mcp_servers=[server],
        )
        result = await Runner.run(agent, "List recent transactions")
        print(result.final_output)

asyncio.run(main())

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 OpenAI Agents SDK

Yes. You just pass the server to your agent constructor and call the discovery tools directly. It maps your repo list into the agent's available toolset.

The server provides exact paths via `search_by_filepath`. Your agent receives verified strings, not guesses, which prevents the typical issues found in loose context retrieval.

It manages indexing asynchronously. You can trigger an index and verify its completion status via `get_repository_status` before your agent attempts to query the files.

Yes. You need a valid Greptile API key to authorize the server. The connection is handled via the HTTP transport defined in your agent setup.

Your codebase is processed in an ephemeral, isolated environment. Only the snippets retrieved by your queries are transmitted to your agent, ensuring the rest of your private logic remains untouched.

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