How to Use the Greptile MCP in CrewAI

Q: How does CrewAI handle a situation where a Greptile repository isn't indexed yet?

Your coordinator agent can use getrepositorystatus to check if the index is ready. If it isn't, the agent can call indexrepository and wait until the status returns active before delegating tasks to the rest of the crew.

Q: What's the best way to clean up old indexes in CrewAI?

You can task a cleanup agent with running listrepositories to find stale codebases. The agent then calls deleterepository on any project that hasn't been queried recently, keeping your index storage tidy.

Deploy a team of autonomous agents to audit, search, and analyze codebases using the Greptile MCP Server and CrewAI.

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 CrewAI

Create your Vinkius account to connect Greptile to CrewAI 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 CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Specialized Code Auditing Crews

The `query_codebase` tool serves as the primary interface for your specialized research agents to inspect repository architecture. You can assign one agent to analyze security vulnerabilities while another maps out database schemas. They share their findings through CrewAI's common memory pool. This collaborative setup allows your agents to cross-reference code patterns without stepping on each other's toes. A coordinator agent can coordinate the entire process, passing file paths discovered by the researcher to the security analyst.

Autonomous Repository Management with CrewAI

The `list_repositories` tool allows your crew to discover available codebases before planning their analysis tasks. An active list checks the active list and determines if the required codebase is already indexed on the MCP Server. If it's missing, the agent triggers `index_repository` to prepare the workspace. The crew monitors the indexing progress using `get_repository_status` before starting their main analysis. This automated check prevents agents from executing queries on incomplete indexes, saving you API credits and compute time.

Targeted Deep-Dive Code Search

The `search_codebase` tool enables your agents to run targeted grep-like operations across all files when debugging. Instead of asking the model to guess where an error originates, the agent runs a fast search to isolate the exact problem files. Once the files are found, the agent uses `get_file_info` to inspect the code structure and imports. This targeted approach keeps the context window clean, ensuring your agents only process the exact lines of code needed to solve the issue.

Setup guide

Set up Greptile MCP in CrewAI

Prerequisites

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

1

Install CrewAI
Run pip install crewai to install the framework. MCP support is built-in via the mcps parameter.
2

Add the MCP URL to your agent
Pass your Vinkius endpoint directly to the mcps list. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. CrewAI handles tool discovery and caching automatically.
3

Kick off your crew
Create a Crew with your agent and tasks. Call crew.kickoff() — the agent will automatically invoke Greptile tools as needed.

crew.py

from crewai import Agent, Task, Crew

agent = Agent(
    role="Greptile Analyst",
    goal="Access and analyze Greptile data via MCP.",
    backstory="Expert analyst with direct Greptile access.",
    mcps=[
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ],
)

task = Task(
    description="List recent Greptile transactions",
    agent=agent,
    expected_output="A summary of recent activity",
)

crew = Crew(agents=[agent], tasks=[task])
result = crew.kickoff()
print(result)

Get your connection token →

Prerequisites

Python 3.10+ installed
crewai + crewai-tools packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install crewai crewai-tools. The MCPServerAdapter handles lifecycle management and tool conversion.
2

Connect with MCPServerAdapter
Use MCPServerAdapter as a context manager with SseServerParameters pointing to your Vinkius endpoint. The adapter automatically manages connection lifecycle.
3

Assign tools and run
Pass the returned mcp_tools to your agent's tools parameter. The adapter converts MCP tools to native BaseTool objects compatible with all CrewAI agents.

crew.py

from crewai import Agent, Task, Crew
from crewai_tools import MCPServerAdapter
from mcp import SseServerParameters

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

with MCPServerAdapter(server_params) as mcp_tools:
    agent = Agent(
        role="Greptile Analyst",
        goal="Access and analyze Greptile data via MCP.",
        backstory="Expert analyst with direct Greptile access.",
        tools=mcp_tools,
    )

    task = Task(
        description="List recent Greptile transactions",
        agent=agent,
        expected_output="A summary of recent activity",
    )

    crew = Crew(agents=[agent], tasks=[task])
    result = crew.kickoff()
    print(result)

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 CrewAI

You pass the server's HTTP endpoint directly into the agent's mcps parameter during initialization. This automatically registers tools like query_codebase and search_codebase so the MCP agent can use them during execution.

Yes, CrewAI supports parallel execution, allowing different agents to call query_codebase or search_by_filepath simultaneously. The MCP Server handles these concurrent requests smoothly, returning isolated results to each agent.

Your coordinator agent can use get_repository_status to check if the index is ready. If it isn't, the agent can call index_repository and wait until the status returns active before delegating tasks to the rest of the crew.

You can task a cleanup agent with running list_repositories to find stale codebases. The agent then calls delete_repository on any project that hasn't been queried recently, keeping your index storage tidy.

The codebase files and directory structures are sent securely to the indexing service to build semantic maps. All communication happens over encrypted channels, and the underlying Vinkius infrastructure ensures your data is purged from memory once the task completes.

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