How to Use the GitScrum ClientFlow MCP in LlamaIndex

Q: Can I use LlamaIndex to search through GitScrum ClientFlow proposals?

Yes. The agent can use listproposals to retrieve active agreements, index the text blocks into your vector store, and let you run semantic queries against contract terms.

Q: Can I index historic timesheet entries from GitScrum ClientFlow into LlamaIndex?

Yes, you can pull your entire history using listtimeentries. The framework indexes these records so you can search for past tasks and analyze time spent on similar projects.

Turn your billing history and timesheets into a searchable knowledge base using LlamaIndex and GitScrum ClientFlow.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect GitScrum ClientFlow MCP to LlamaIndex

Create your Vinkius account to connect GitScrum ClientFlow to LlamaIndex 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 GitScrum ClientFlow with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Index timesheets and proposals using this MCP Server

This MCP Server allows LlamaIndex to query your active agency records and index them directly into vector storage. By pulling raw data via `list_time_entries` and `list_proposals`, you build a semantic search engine over your entire operational history. Instead of manually digging through old projects, you can ask your LlamaIndex query engine which tasks consumed the most hours last quarter. The agent queries the index, retrieves the exact logs, and answers your questions using grounded data instead of making things up.

Ground client budget answers in live financial data

This MCP Server exposes `project_budget` to your LlamaIndex query engine to prevent hallucinated financial answers. By exposing active financial limits to your query engine, the agent pulls real-time data before answering any questions about project health. The agent combines current budget data with historical invoice trends retrieved via `list_invoices`. This ensures every financial projection or status report is backed by actual numbers pulled directly from GitScrum ClientFlow.

Build a smart dashboard query assistant

This MCP Server lets your LlamaIndex agent call `clientflow_dashboard` to provide natural language summaries of your agency health. Your agent can get an instant overview of outstanding tasks and pending payments, translating complex structures into simple summaries. If a teammate asks for specific details on a client's status, the agent uses `get_client` to fetch the record and merges it with active proposals from `get_proposal`. You get instant, accurate answers without clicking through multiple tabs.

Setup guide

Set up GitScrum ClientFlow MCP in LlamaIndex

Prerequisites

Python 3.10+ installed
llama-index-tools-mcp package
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install llama-index-tools-mcp llama-index-llms-openai. The MCP tools package provides BasicMCPClient and McpToolSpec.
2

Connect with BasicMCPClient
Point BasicMCPClient to your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports SSE and Streamable HTTP transports.
3

Convert to LlamaIndex tools
Call mcp_tool_spec.to_tool_list_async() to convert all GitScrum ClientFlow MCP tools into native FunctionTool objects that any LlamaIndex agent can use.
4

Run with any LLM
Create a FunctionAgent with the tools and your preferred LLM. Swap OpenAI for Anthropic, Gemini, or any LlamaIndex-supported provider.

agent.py

from llama_index.tools.mcp import BasicMCPClient, McpToolSpec
from llama_index.core.agent.workflow import FunctionAgent
from llama_index.llms.openai import OpenAI

# Connect to the MCP
mcp_client = BasicMCPClient(
    "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)
mcp_tool_spec = McpToolSpec(client=mcp_client)

# Convert MCP tools to LlamaIndex tools
tools = await mcp_tool_spec.to_tool_list_async()

# Create and run the agent
agent = FunctionAgent(
    tools=tools,
    llm=OpenAI(model="gpt-4o"),
    system_prompt="You have access to GitScrum ClientFlow tools.",
)
response = await agent.run("List recent GitScrum ClientFlow data")

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 GitScrum. 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 GitScrum ClientFlow 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 GitScrum ClientFlow MCP in LlamaIndex

Yes. The agent can use `list_proposals` to retrieve active agreements, index the text blocks into your vector store, and let you run semantic queries against contract terms.

By fetching direct API data. When you ask about outstanding bills, the agent calls `list_invoices` or `get_invoice` to ground its response in actual records rather than relying on its training data.

Yes, you can pull your entire history using `list_time_entries`. The framework indexes these records so you can search for past tasks and analyze time spent on similar projects.

You initialize the client, convert the tool specifications to a list of executable functions, and pass them to your agent. The agent then decides when to call `get_client` or `project_budget` based on the user's query.

We never store your client profiles, budget limits, or invoice files. This MCP Server processes all requests in memory within an ephemeral sandbox, passing the data directly to your LlamaIndex pipeline over a secure connection.

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