How to Use the Glob Pattern Tester MCP in LlamaIndex

Q: Can Glob Pattern Tester filter documents during LlamaIndex ingestion?

Yes, you can run candidate paths through the testglob tool before loading them into your index. This ensures only paths matching your target patterns get vectorized.

Index and query validated file paths in LlamaIndex using standard git and npm matching rules.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Glob Pattern Tester MCP to LlamaIndex

Create your Vinkius account to connect Glob Pattern Tester 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 Glob Pattern Tester with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Filter files before indexing in LlamaIndex

The `test_glob` tool evaluates file paths against your custom exclusion rules before LlamaIndex starts parsing documents. Your indexing pipeline calls this tool to ensure files like markdown configs or test logs never enter your vector database. This step keeps your index clean and focused solely on high-value data. By applying standard gitignore patterns, you prevent redundant chunks from consuming vector storage and polluting your search results.

Connect the Glob Pattern Tester MCP Server

The `test_glob` tool exposes standard npm path matching directly to your LlamaIndex data agents. You initialize the connection using the MCP tool spec adapter and pass the generated tool list to your index coordinator. This architecture allows your RAG application to dynamically test path eligibility during query execution. The agent verifies which source files match the user's requested scope before retrieving semantic chunks.

Ground document retrieval in valid path patterns

The `test_glob` tool gives your LlamaIndex search agent a reliable way to verify path patterns during conversational retrieval. When a user asks to search only within a specific directory, the agent tests candidate document paths against the requested pattern. This matching happens instantly using the standard minimatch library. Your agent relies on the boolean match results to filter down the candidate document set before performing vector similarity lookups.

Setup guide

Set up Glob Pattern Tester 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 Glob Pattern Tester 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 Glob Pattern Tester tools.",
)
response = await agent.run("List recent Glob Pattern Tester 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 minimatch. 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 Glob Pattern Tester 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 Glob Pattern Tester MCP in LlamaIndex

Yes, you can run candidate paths through the `test_glob` tool before loading them into your index. This ensures only paths matching your target patterns get vectorized.

Install the MCP tool spec library, initialize the client with your server URL, and convert the tool list for your LlamaIndex agent. The agent then gains immediate access to the `test_glob` tool.

Yes, the server normalizes backslashes to forward slashes before executing the match. Your LlamaIndex agent can pass raw paths from any operating system directly to the `test_glob` tool.

Yes, the agent can generate glob patterns based on user queries and test them against indexed metadata. This allows precise, file-level filtering on top of semantic search.

Yes, the MCP server only receives the specific file paths and pattern strings you pass to it. No directory trees are scanned, and no path metadata is stored or transmitted outside the ephemeral session.

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