Can the AI agent track active project milestones and timeline risks?

Yes. The agent uses the explicit milestones and risks endpoints to provide real-time updates on deliverable health, letting you manage complex Portfolio lifecycles entirely through natural language commands without sifting through gantt charts.

Does it map team hours and billable expenses internally?

Absolutely. Using the resources, time entries, and expenses tools, the agent accurately links organizational workers, the exact time they logged natively, and their costs—directly mapping them onto specific project ledgers on the fly.

Can the agent query custom issues and complex gating approvals?

Yes. The integration pulls mapped states of blocking issues and traces routing limits for approvals over timesheets or expenses, granting you full observability into administrative constraints without opening the Celoxis interface.

Celoxis MCP Server for Google ADK 12 tools — connect in under 2 minutes

Name: Celoxis
Availability: InStock
Author: Vinkius

google.github.io/adk-docs/tools/mcp-tools

Built by Vinkius GDPR 12 Tools SDK

Google Agent Development Kit (ADK) is Google's framework for building production AI agents. Add Celoxis as an MCP tool provider through Vinkius and your ADK agents can call every tool with full schema introspection.

Get MCP Server for AI Agents

ASK AI ABOUT THIS MCP SERVER

Open in ChatGPT Open in Claude Open in Perplexity

Vinkius supports streamable HTTP and SSE.

python

from google.adk.agents import Agent
from google.adk.tools.mcp_tool import McpToolset
from google.adk.tools.mcp_tool.mcp_session_manager import (
    StreamableHTTPConnectionParams,
)

# Your Vinkius token. get it at cloud.vinkius.com
mcp_tools = McpToolset(
    connection_params=StreamableHTTPConnectionParams(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp",
    )
)

agent = Agent(
    model="gemini-2.5-pro",
    name="celoxis_agent",
    instruction=(
        "You help users interact with Celoxis "
        "using 12 available tools."
    ),
    tools=[mcp_tools],
)

Fully ManagedVinkius Servers

60%Token savings

High SecurityEnterprise-grade

IAMAccess control

EU AI ActCompliant

DLPData protection

V8 IsolateSandboxed

Ed25519Audit chain

<40msKill switch

Stream every event to Splunk, Datadog, or your own webhook in real-time

* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure

About Celoxis MCP Server

Connect your Celoxis enterprise platform to any AI agent and take full control of your Project Portfolio Management (PPM) workflow through natural conversation.

Google ADK natively supports Celoxis as an MCP tool provider. declare Vinkius Edge URL and the framework handles discovery, validation, and execution automatically. Combine 12 tools with Gemini's long-context reasoning for complex multi-tool workflows, with production-ready session management and evaluation built in.

What you can do

Project & Portfolio Mapping — List strategic portfolios and extract granular project structures including absolute timelines, completion statuses, and mapped budget blocks.
WBS & Tasks — Retrieve explicit Work Breakdown Structure nodes, identifying active assignments, task health, and explicit phase deliverables.
Resource Allocation — Evaluate working resources, parse user mappings, and expose global scheduling types and distinct system roles across your organization.
Timesheets & Accounting — Accurately pull time entries logged by members to measure billable matrices and ledger associations tied directly to tasks natively.
Issue & Risk Governance — Poll blocking issues preventing workflows and assess graded severity impacts modeled inside the Celoxis organizational risk matrix.
Approvals Pipeline — Interrogate pending validations routing over timesheets, assessing gating rules and internal clearance statuses immediately.

The Celoxis MCP Server exposes 12 tools through the Vinkius. Connect it to Google ADK in under two minutes — no API keys to rotate, no infrastructure to provision, no vendor lock-in. Your configuration, your data, your control.

How to Connect Celoxis to Google ADK via MCP

Follow these steps to integrate the Celoxis MCP Server with Google ADK.

Install Google ADK

Run pip install google-adk

Replace the token

Replace [YOUR_TOKEN_HERE] with your Vinkius token

Create the agent

Save the code above and integrate into your ADK workflow

Explore tools

The agent will discover 12 tools from Celoxis via MCP

Why Use Google ADK with the Celoxis MCP Server

Google ADK provides unique advantages when paired with Celoxis through the Model Context Protocol.

Google ADK natively supports MCP tool servers. declare a tool provider and the framework handles discovery, validation, and execution

Built on Gemini models, ADK provides long-context reasoning ideal for complex multi-tool workflows with Celoxis

Production-ready features like session management, evaluation, and deployment come built-in. not bolted on

Seamless integration with Google Cloud services means you can combine Celoxis tools with BigQuery, Vertex AI, and Cloud Functions

Celoxis + Google ADK Use Cases

Practical scenarios where Google ADK combined with the Celoxis MCP Server delivers measurable value.

Enterprise data agents: ADK agents query Celoxis and cross-reference results with internal databases for comprehensive analysis

Multi-modal workflows: combine Celoxis tool responses with Gemini's vision and language capabilities in a single agent

Automated compliance checks: schedule ADK agents to query Celoxis regularly and flag policy violations or configuration drift

Internal tool platforms: build self-service agent platforms where teams connect their own MCP servers including Celoxis

Celoxis MCP Tools for Google ADK (12)

These 12 tools become available when you connect Celoxis to Google ADK via MCP:

get_project

Get an explicit Celoxis project and its complete intrinsic properties structure by ID

list_approvals

List explicit tracking objects identifying pending/cleared approvals over timesheets and expenses constraints

list_clients

List explicit top-level CRM organizational clients linked internally to distinct portfolios

list_expenses

List raw billable/non-billable expenses physically mapped onto task items inside the ecosystem

list_issues

List custom app items representing blocked issues explicit to complex workflows mapping problems

list_milestones

List raw milestones natively mapping absolute phase delivery tracking inside the WBS

list_portfolios

List strategic global tracking Portfolios mapping top-level aggregates over child projects natively

list_projects

List all top-level project portfolio items in Celoxis. Returns physical IDs, names, status, and timeline data

list_resources

List all explicit Celoxis working resources parsing the core user mappings handling allocations

list_risks

List explicit organizational risks bounded natively via the Celoxis custom application matrix

list_tasks

List comprehensive Work Breakdown Structure (WBS) tasks representing concrete deliverables within active projects

list_time_entries

List actual time entries logged explicitly against Celoxis tasks or projects for accounting

Example Prompts for Celoxis in Google ADK

Ready-to-use prompts you can give your Google ADK agent to start working with Celoxis immediately.

"List all active projects in our company portfolio and check their timeline status."

"Check the detailed logged time entries for the Marketing project and verify pending approvals."

"Extract the explicit risk logs and blocked issues reported across our client portfolio."

Troubleshooting Celoxis MCP Server with Google ADK

Common issues when connecting Celoxis to Google ADK through the Vinkius, and how to resolve them.

McpToolset not found

Update: pip install --upgrade google-adk

Celoxis + Google ADK FAQ

Common questions about integrating Celoxis MCP Server with Google ADK.

How does Google ADK connect to MCP servers?

Import the MCP toolset class and pass the server URL. ADK discovers and registers all tools automatically, making them available to your agent's tool-use loop.

Can ADK agents use multiple MCP servers?

Yes. Declare multiple MCP tool providers in your agent configuration. ADK merges all tool schemas and the agent can call tools from any server in a single turn.

Which Gemini models work best with MCP tools?

Gemini 2.0 Flash and Pro models both support function calling required for MCP tools. Flash is recommended for latency-sensitive use cases, Pro for complex reasoning.