How to Use the Celoxis MCP in LlamaIndex

Q: How do I connect the Celoxis MCP Server to LlamaIndex?

Run pip install llama-index-tools-mcp. Create a BasicMCPClient with your Vinkius URL, wrap it in an McpToolSpec, and call totoollistasync() to feed the endpoints to your FunctionAgent.

Q: Do I need to manually map the tool schemas?

No. The McpToolSpec automatically translates the complex JSON schemas for tools like listclients into formats your embedding models understand natively.

Q: Can I restrict which Celoxis tools my LlamaIndex agent uses?

Use the allowedtools filter during initialization. If you only want the agent indexing risks, restrict it to listrisks and block the financial endpoints entirely.

Q: How does Vinkius protect Celoxis client portfolios during indexing?

Every call to listportfolios or listclients runs through a zero-trust architecture. The managed endpoint authenticates the request, fetches the CRM organizational data, and immediately destroys the execution context to prevent data leakage.

Index your Celoxis project portfolios into searchable vector stores using LlamaIndex.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Celoxis MCP to LlamaIndex

Create your Vinkius account to connect Celoxis 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 Celoxis with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Turn Celoxis project data into a RAG knowledge base

LlamaIndex changes how you interact with project management software. Instead of just querying an API, you run `list_projects` and `get_project` to pull the complete intrinsic properties of your active work. The framework then chunks and embeds this structured data into your vector store. Now your users can ask semantic questions about project statuses. The system searches the index, finds the exact physical IDs and timeline data pulled from the MCP Server, and generates answers grounded in actual operational reality.

Embed timesheets and expenses for semantic search

You can build RAG applications that understand your project financials. By calling `list_expenses` and `list_time_entries`, your LlamaIndex setup pulls raw billable and non-billable metrics. It maps these figures to the working resources fetched via `list_resources`. The result is a unified, queryable index of who did what and how much it cost. When someone asks about budget overruns, the FunctionAgent retrieves the exact accounting data from the vector store rather than hallucinating a response.

Query governance constraints via LlamaIndex MCP

Complex workflows require strict oversight. You use `list_approvals` to pull pending governance objects and `list_risks` to grab organizational threats. The framework ingests these constraints alongside your standard documents. When an executive asks about project health, the system cross-references those risks with concrete deliverables from `list_tasks`. You get a complete view of blocked workflows and pending approvals, all driven by live data.

Setup guide

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

Run `pip install llama-index-tools-mcp`. Create a `BasicMCPClient` with your Vinkius URL, wrap it in an `McpToolSpec`, and call `to_tool_list_async()` to feed the endpoints to your FunctionAgent.

Yes. You can configure your agent to pull the Work Breakdown Structure via `list_tasks` and `list_milestones`. The framework parses these concrete deliverables and indexes them for semantic retrieval.

No. The `McpToolSpec` automatically translates the complex JSON schemas for tools like `list_clients` into formats your embedding models understand natively.

Use the `allowed_tools` filter during initialization. If you only want the agent indexing risks, restrict it to `list_risks` and block the financial endpoints entirely.

Every call to `list_portfolios` or `list_clients` runs through a zero-trust architecture. The managed endpoint authenticates the request, fetches the CRM organizational data, and immediately destroys the execution context to prevent data leakage.

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