How to Use the Jibble MCP in LlamaIndex

Q: How do I register Jibble MCP tools in LlamaIndex?

Initialize the BasicMCPClient with your Jibble URL using llama-index-tools-mcp. Wrap it in McpToolSpec and call totoollistasync() to get tools like listtimeentries for your FunctionAgent.

Q: Can LlamaIndex search through Jibble locations?

Yes, you can index the output of listlocations directly into your vector store. This lets your agent perform semantic searches over your physical job sites and match them against employee entries.

Q: Does LlamaIndex support filtering Jibble MCP tools?

Yes, use the allowedtools filter when setting up your McpToolSpec. If you only want your agent to access listprojects and listtimeentries while blocking personal info, you can explicitly define that.

Q: How is my Jibble payroll data protected?

Your sensitive payroll data—including employee IDs from listpeople and durations from listtimeentries—is processed in an ephemeral V8 Isolate sandbox. Your credentials are never exposed to the LLM or third parties.

Connect LlamaIndex to Jibble via MCP to index live time entries directly into your vector stores.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Jibble MCP to LlamaIndex

Create your Vinkius account to connect Jibble 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 Jibble with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Index Jibble data for semantic search

Turn raw time sheets into a queryable knowledge base. LlamaIndex takes the output of `list_time_entries` and indexes it into your vector store, allowing your agent to answer complex questions about team availability and project allocations without raw database queries. Don't look up individual logs manually—just ask your agent who worked on development tasks this week. The system queries the index, cross-references with `list_activities`, and returns grounded answers.

Grounded RAG with Jibble MCP Server tools

Avoid hallucinations when analyzing team performance. By connecting this MCP Server to LlamaIndex, your agent retrieves actual data from `get_person` and `list_groups` to ground its responses in real-time organizational structures. This ensures that when you ask about a specific department's output, the agent pulls the current roster from `list_people` instead of guessing or relying on outdated training data.

Build structured project summaries

Automate your weekly client billing reports. Your LlamaIndex agent can fetch live project lists using `list_projects` and pair them with active time entries from `get_time_entry` to build structured summaries. The agent indexes these summaries, making it easy to search past project histories or verify which clients were billed for specific activities retrieved from `list_clients`.

Setup guide

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

Initialize the `BasicMCPClient` with your Jibble URL using `llama-index-tools-mcp`. Wrap it in `McpToolSpec` and call `to_tool_list_async()` to get tools like `list_time_entries` for your `FunctionAgent`.

Yes, you can index the output of `list_locations` directly into your vector store. This lets your agent perform semantic searches over your physical job sites and match them against employee entries.

Yes, use the `allowed_tools` filter when setting up your `McpToolSpec`. If you only want your agent to access `list_projects` and `list_time_entries` while blocking personal info, you can explicitly define that.

Build a query engine that checks local contract PDFs and uses Jibble MCP tools like `list_clients` to verify if active tracking matches your written contract terms.

Your sensitive payroll data—including employee IDs from `list_people` and durations from `list_time_entries`—is processed in an ephemeral V8 Isolate sandbox. Your credentials are never exposed to the LLM or third parties.

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