How to Use the GitScrum Knowledge MCP in LlamaIndex

Q: Can LlamaIndex search across both wiki pages and notes in GitScrum Knowledge?

Yes. LlamaIndex uses globalsearch to query both resource types simultaneously, or it can run targeted semantic searches over notes retrieved via listnotes.

Q: How do I handle document updates in GitScrum Knowledge using LlamaIndex?

Your agent can call updatenote or updatewikipage to modify documents based on query results. LlamaIndex then updates the corresponding vector embeddings to keep the index synchronized.

Q: Can I filter which tools LlamaIndex has access to?

Yes. You can pass an allowedtools list to your tool specification to restrict the agent. For example, you can limit it to read-only tools like listnotes and getwikipage.

Index your GitScrum Knowledge base directly into LlamaIndex vector stores using this MCP Server.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect GitScrum Knowledge MCP to LlamaIndex

Create your Vinkius account to connect GitScrum Knowledge 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 Knowledge with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Semantic Indexing of Notes

`list_notes` pulls all workspace notes so LlamaIndex can parse and chunk them into vector embeddings. This turns your raw notes into a semantic index that your agent queries for context-rich answers. When notes evolve, `note_revisions` lets the indexer track changes and update only modified chunks. This avoids rebuilding the entire vector store from scratch, keeping your index fresh and reducing API overhead.

MCP Server Wiki Parsing for RAG

`get_wiki_page` retrieves full markdown content from your documentation pages to populate LlamaIndex query engines. The framework reads the nested hierarchy from `list_wiki_pages` to preserve parent-child relationships in the index. If the agent needs to update the source material, it calls `update_wiki_page` directly. The query engine then re-indexes that specific page, ensuring your RAG system always references current information.

Real-Time Chat Context Enrichment

`channel_messages` fetches real-time conversation threads to feed active user context into your LlamaIndex pipelines. The agent reads recent discussion history to understand the user's intent before executing a search. If the agent needs to post its findings, it calls `send_message` to write directly back to the channel. This creates a loop where the agent reads discussions, indexes them, and posts summaries back to the team.

Setup guide

Set up GitScrum Knowledge 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 Knowledge 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 Knowledge tools.",
)
response = await agent.run("List recent GitScrum Knowledge 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 Knowledge 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 Knowledge MCP in LlamaIndex

Install llama-index-tools-mcp and initialize the BasicMCPClient with the server URL. Wrap the client in McpToolSpec to expose tools like list_notes and get_wiki_page to your query engine.

Yes. LlamaIndex uses global_search to query both resource types simultaneously, or it can run targeted semantic searches over notes retrieved via list_notes.

Your agent can call update_note or update_wiki_page to modify documents based on query results. LlamaIndex then updates the corresponding vector embeddings to keep the index synchronized.

Yes. You can pass an allowed_tools list to your tool specification to restrict the agent. For example, you can limit it to read-only tools like list_notes and get_wiki_page.

Yes. All communication with the server is encrypted, and your wikis, notes, and channel messages are processed in memory without being stored. The zero-trust sandbox isolates each execution, preventing cross-tenant data leaks.

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