LiquidPlanner Classic MCP for AI. Manage projects and resource dependencies in conversation.

Q: How do I check if a team member is overloaded using listmembers?

The agent analyzes resource allocation when you request listmembers. It provides percentages and flags specific members who are over capacity (e.g., 95% utilization), so you know exactly where the bottleneck is.

Q: Can I create a new project using createproject?

Yes, running createproject establishes a brand-new container in your default workspace. This lets you immediately start defining tasks and setting up initial milestones for the new initiative.

Q: What is the difference between listtasks and gettask?

listtasks gives you an index—a directory of every task in the workspace. gettask, however, requires a specific Task ID to retrieve all associated details, including full dependency lists and owner information.

Q: How do I update a project's deadline?

You use the updatetask tool. You must provide the task's unique ID, then instruct your agent to change the specific field—like updating the estimated completion date or reassigning the owner.

Q: Do I need getworkspace before working on projects?

It’s smart to use getworkspace first. This confirms which workspace your agent is currently operating in, preventing accidental data writes or reads in the wrong project environment.

Q: If I need an overview of all tasks across the entire workspace, should I use listprojects first?

No. Just running listtasks pulls a master inventory of every active task in the default workspace, regardless of which project it belongs to.

Claude

ChatGPT

Cursor

Gemini

Windsurf

VS Code

JetBrains

Vercel

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

Connect to your AI in seconds.

LiquidPlanner Classic connects project scheduling to your AI agent. It lets you build complex project plans and manage resources by understanding task dependencies and team capacity.

You can create projects, track tasks, check resource loads against deadlines, and monitor predictive schedules—all through natural conversation.

What your AI can do

Create project

Creates a new project record in the default LiquidPlanner workspace so you can start tracking work immediately.

Create task

Adds a new task to an existing project or folder, requiring a parent ID for proper nesting and context.

Get project

Retrieves full details about one specific project using its unique ID, giving you scope, milestones, and status.

+ 7 more capabilities included

Generate New Projects

Calls the create_project tool to establish a new project record in the default LiquidPlanner workspace.

Create and Update Tasks

Uses create_task or update_task to add tasks, set priorities, and modify existing task details within a parent project.

Retrieve Project Details

Runs the get_project tool to fetch all specific data points for a single project ID.

Check Resource Availability

The agent can run list_members and resource allocation checks, identifying overloaded employees or underutilized teams.

List Project Structures

Uses list_projects to provide a full directory of all projects currently defined in the workspace.

Find Specific Tasks

Retrieves task details using get_task, ensuring you have precise information on scope and deadlines.

Ask an AI about this

Included with Plan

Waiting for input…

AI Agent

LiquidPlanner Classic: 10 Tools for Project Management

Use these ten tools to create, read, list, and modify every aspect of your project scope—from creating a new workspace down to updating the smallest task detail.

Make your AI actually useful.

Add this MCP to Claude, Cursor, or Windsurf and your AI stops guessing. It gets real tools to look things up, take action, and handle the stuff you keep doing by hand.

Start using LiquidPlanner Classic on Vinkius

Create Project

Creates a new project record in the default LiquidPlanner workspace so you can start tracking work immediately.

Create Task

Adds a new task to an existing project or folder, requiring a parent ID for proper...

Get Project

Retrieves full details about one specific project using its unique ID, giving you...

Get Task

Fetches all information for a single task, including assignments, estimates, and...

Get Workspace

Gets details about the entire workspace or specifies a different one if you're...

List Members

Lists every team member in the default workspace, providing current resource allocation data for planning.

List Projects

Retrieves a comprehensive list of all available projects within the configured workspace.

List Tasks

Lists every task in the default workspace, allowing you to see what's active without...

List Workspaces

Shows all connected workspaces within LiquidPlanner Classic so your agent knows...

Update Task

Changes details on an existing task, such as adjusting the deadline, reassigning...

Security and governance baked right in.

Pick your AI client below to get set up. Just create a Vinkius account, subscribe, and you're instantly up and running. We handle the entire backend infrastructure, delivering out-of-the-box support for HTTPS Streamable, SSE, and OAuth2—zero messy routing required.

Claude AI

Open Claude Settings

Go to claude.ai, click your profile icon, then navigate to Customize → Connectors.

Add Custom Connector

Click the "+" button and select Add custom connector. Paste your Vinkius endpoint URL:

https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp

Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. For OAuth-protected servers, expand Advanced settings to add credentials.

Start a conversation

Open a new chat. The LiquidPlanner Classic integration is available immediately — no restart needed.

Antigravity

Configure Agent Environment

Open your Antigravity agent's workspace configuration or mcp-servers.json file.

Bind the Endpoint

Add the Vinkius endpoint URL to your agent's MCP connections list:

"mcp_servers": {
  "liquidplanner-classic": {
    "serverUrl": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
  }
}

Provide your secure token in place of [YOUR_TOKEN_HERE] to ensure your agent requests are authenticated.

Execute

Start your Antigravity session. The agent will autonomously discover and utilize the LiquidPlanner Classic tools with full Vinkius guardrails applied.

VS Code Copilot

⚡

One-Click Install (Recommended)

In your Vinkius Dashboard, simply click the Add to VS Code button for this server. We'll automatically configure your local workspace.

Or configure manually

Open MCP Settings

Open VS Code, press Ctrl/Cmd + Shift + P, and search for GitHub Copilot: MCP Servers.

Add Server Config

Add the Vinkius endpoint configuration to your mcp-servers.json file:

"liquidplanner-classic": {
  "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
}

Ensure you replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.

LangChain

Install Dependencies

Install the LangChain MCP adapters for your environment:

pip install langchain-mcp-adapters

Connect the Server

Use the SSEClient in LangChain to connect to the Vinkius managed endpoint:

from langchain_mcp_adapters.client import SSEClient

# Connect to Vinkius
client = SSEClient(url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp")
tools = client.get_tools()

CrewAI

Define the Tool

Load the Vinkius MCP tools into your CrewAI agents:

from crewai import Agent
from mcp_crewai import MCPTool

# Connect securely to Vinkius
vinkius_tools = MCPTool(url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp")

# Assign to Agent
researcher = Agent(
    role='Data Researcher',
    tools=vinkius_tools.get_all()
)

Execute Task

Run your CrewAI process. The agent will autonomously route tasks to the Vinkius managed server.

Choose How to Get Started

Build a custom MCP for your own tools, or connect a ready-made integration from our catalog.

Build Your Own

Turn any API into an MCP. Import a spec, define Agent Skills, or deploy with MCPFusion.

Import from OpenAPI, Swagger, or YAML specs
Create Agent Skills with progressive disclosure
Deploy to edge with MCPFusion framework
Built in DLP, auth, and compliance on every call
Real time usage dashboard and cost metering
Publish to catalog or keep private

Start building

Make Your AI Do More

Start with LiquidPlanner Classic, then connect any of our 5,000+ other servers whenever your AI needs more. One click, no limits.

Use this MCP plus 5,000+ others, all in one place
Add new capabilities to your AI anytime you want
Every connection is secured and compliant automatically
Track usage and costs across all your servers
Works with Claude, ChatGPT, Cursor, and more
New servers added to the catalog every week

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by LiquidPlanner Classic. 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.

VINKIUS INFRASTRUCTURE

Cloud Hosted

Managed infra

V8 Isolated

Sandboxed per request

Zero-Trust Proxy

No stored credentials

DLP Enforced

Policy on every call

GDPR Compliant

EU data residency

Token Compression

~60% cost reduction

Your data is protected. See how we built it.

Works with Claude, ChatGPT, Cursor, and more

The Model Context Protocol standardizes how applications expose capabilities to LLMs. Instead of operating in isolation, your AI gains direct access to external platforms, live data, and real-world actions through secure, standardized connections.

This connection provides 10 powerful capabilities that interface natively with Claude, ChatGPT, Cursor, and other compatible AI platforms. No middleware. No custom integration required.

Planning projects used to mean juggling spreadsheets until 2 AM.

Today, planning a project means jumping between the Gantt chart, resource dashboards, and separate dependency trackers. You pull reports for team members' time entries, copy-paste those numbers into a spreadsheet, then manually mark potential bottlenecks in red ink. It’s slow, it’s error-prone, and frankly, you rarely get an accurate picture of true capacity.

With LiquidPlanner Classic MCP Server, that manual process vanishes. You ask your agent: 'Show me the resource allocation for Q3.' The server runs `list_members` and checks all defined tasks against current capacities. You don't just see a number; you get an actionable report showing exactly who is overloaded and why.

LiquidPlanner Classic MCP Server: Get the full project picture.

Before, checking a major deliverable meant opening the main Project ID page, scrolling through milestones, finding the related tasks, and then running another report to see who owned them. It was a multi-step manual process that always resulted in incomplete data sets or missing context.

Now, you tell your agent: 'What's the status of the Mobile App project?' The server executes `get_project` which pulls all dependencies, milestones, and associated task owners into one single response. You get the entire picture instantly.

Support 24/7 support@vinkius.com ↗

Security Vinkius Trust Center ↗

SLA Service Level Agreement ↗

Report Listing Send Report ↗

What your AI can actually do with this

Listen up. This connection lets your AI agent talk directly to LiquidPlanner Classic. It’s how you get sophisticated project planning done using plain conversation, without needing to jump through a dozen menus. You're building out complex plans and managing who does what by understanding dependencies and team bandwidth. Here’s the deal: when your agent runs these tools, it tells you exactly what’s going on in LiquidPlanner.

To start, if you don't know where to look, your agent can run list_workspaces to show every single workspace connected to your account. If you need details about a specific environment, it uses get_workspace to fetch that info for you. From there, it pulls up all the projects using list_projects, giving you a directory of everything defined in your main workspace.

Building out work starts with creating structure. You can call create_project and instantly establish a new project record in the default LiquidPlanner space so you’re tracking work right away. Once that's set up, you use create_task to add individual tasks to an existing project or folder; remember it needs a parent ID to know where to nest it properly.

When you need more tasks later, your agent uses update_task to change anything about an existing task—you can adjust the deadline, reassign owners, or modify estimates on the fly.

If you're trying to figure out what a task entails, your agent fetches all the details for one specific piece of work using get_task. That gives you everything: who’s assigned it, how much time is estimated, and what other tasks depend on its completion. If you need the full scope of an entire job—the milestones, the status updates, the big picture—it runs get_project using a unique project ID.

You can also run list_tasks, which simply spits out every active task in the default workspace so you don't have to know specific project IDs just to see what’s happening.

When it comes to people, your agent has access to team data. It runs list_members to get a list of every person in the default workspace and pulls up their current resource allocation data for planning purposes. If you're looking at the whole picture, running list_workspaces shows all connected LiquidPlanner environments so your agent knows exactly where to look when retrieving data.

So, what does this mean for your day-to-day? You can tell it to build out a brand new project and populate it with tasks in minutes. You don't have to manually check who's overloaded or who's got bandwidth—the agent runs resource allocation checks against the list of members, letting you spot underutilized teams or employees swamped by deadlines.

It keeps track of everything from the initial task creation all the way up to checking if a project has hit its major milestones. You get accurate status updates and full details on any piece of work right through your chat interface.

Built · Hosted · Managed by Vinkius LiquidPlanner Classic MCP Server - Project & Task Scheduling

Server ID 019dd119-73a6-70b8-b1eb-9f69c03bcd7f

Vinkius Inspector

Compliance Grade A+

Score 100/100

Report View Report ↗

Here's how it actually works

The bottom line is: your agent acts as a universal interface. It takes natural conversation and converts it into specific project management actions.

Subscribe to the server, then enter your LiquidPlanner email, password, and Workspace ID.

Your AI client sends a request (e.g., 'What is the predicted deadline for Project X?').

The agent translates this into tool calls (get_project + list_tasks), pulls the data, and gives you an answer in plain English.

Who is this actually for?

Project Managers who dread manually checking Gantt charts; Technical Leads whose sprint planning falls apart due to resource conflicts; Program Directors needing a single source of truth for deadline forecasting. If you spend time coordinating schedules via email or jumping between multiple dashboards, this is for you.

Project Manager

Uses create_project and update_task to build out the full scope of work. They rely on resource checks (e.g., listing members) to ensure no team member is overbooked before setting a milestone.

Program Director

Runs broad queries like 'Show me all projects and their deadline forecasts' using the agent, needing an immediate overview of resource allocation across multiple departments.

Scrum Master / Team Lead

Uses list_tasks and get_task to keep individual team members accountable. They check who needs what by listing all workspace members and their current utilization.

What Changes When You Connect

See exactly who's overloaded. Instead of guessing, run list_members to check real-time resource allocation against project needs. It tells you which team members are at 95% capacity, flagging potential bottlenecks before they happen.

Never miss a deadline forecast again. Use the agent to query get_project and immediately get predictive schedules (best case, most likely, worst case) for any project in seconds, without opening the UI.

Maintain clean scope documentation. When you need to adjust something, use update_task. You don't have to manually navigate deep into a task's details just to change an estimate or owner; tell your agent to do it.

Get a full project picture instantly. If you only know the name but not the IDs, run list_projects first. Then, use get_project with the ID to pull all milestones and deliverables into one clean response.

Track work scope across teams. The agent lets you list tasks (list_tasks) or projects (list_projects), giving you a bird's-eye view of what everyone is working on without manually filtering dashboards.

See it in action

01 01

Project Kickoff: Determining Scope

A new initiative needs to start. Instead of creating it in the UI, you tell your agent: 'Start a project for X and list all required team members.' The agent first runs create_project, then uses list_members to check resource availability before confirming the scope.

02 02

Resource Crunch: Rebalancing Workload

The QA team is swamped. You ask your agent to 'Show me who has capacity next week.' The agent runs list_members, spots Sarah at 95%, and recommends moving a low-priority task from her current workload, requiring the use of update_task.

03 03

Post-mortem: Understanding Delays

The 'Platform v2' project slipped. You ask your agent to analyze the project schedule using get_project. It provides a deep dive, pointing directly to the critical path and identifying exactly which task dependencies caused the delay.

04 04

Discovery: Mapping All Work

You need an inventory of everything. You ask your agent to 'Show me all active projects and their major tasks.' The agent runs list_projects then loops through them, calling list_tasks for each project ID to give you a complete task breakdown.

The honest tradeoffs

Trying to guess resource availability

Anti-pattern

You look at the calendar and assume John is free next week because he has no meetings listed. You start assigning him three major tasks.

The Fix

Don't rely on calendars alone. Use list_members with your agent. It pulls capacity data directly from LiquidPlanner, telling you if John's schedule shows 90% utilization or if he actually has bandwidth.

Editing a task without knowing the ID

Anti-pattern

You find 'Implement caching layer' in an email and try to manually change its deadline. You get stuck because you can’t locate the exact Task ID.

The Fix

First, use list_tasks or run a search query through your agent to get the task's unique ID. Then, call update_task(TaskID=...) and give it the new deadline directly.

Creating everything at once

Anti-pattern

You write out 50 tasks in a spreadsheet and try to upload them all as one big batch job into LiquidPlanner.

The Fix

Use create_project first to set the container. Then, process your tasks iteratively by calling create_task(ParentID=...) for each group of related items. This maintains dependency integrity.

When It Fits, When It Doesn't

Use this server if your planning workflow is fundamentally governed by dependencies and capacity constraints—meaning task B can't start until task A finishes, and you need to know who does task A. It’s perfect for PMOs managing complex product rollouts.

Don't use it if your primary pain point is just simple data storage or basic team directory lookup; a simpler database connector will suffice. Also, don't rely on it for pure financial accounting—it tracks time and effort, but it isn't an ERP system. If all you need is to read static project names, list_projects works, but if you need schedules, you must use the full suite of tools like get_project, get_task, and list_members together.

Questions you might have

How do I check if a team member is overloaded using list_members? +

The agent analyzes resource allocation when you request list_members. It provides percentages and flags specific members who are over capacity (e.g., 95% utilization), so you know exactly where the bottleneck is.

Can I create a new project using create_project? +

Yes, running create_project establishes a brand-new container in your default workspace. This lets you immediately start defining tasks and setting up initial milestones for the new initiative.

What is the difference between list_tasks and get_task? +

list_tasks gives you an index—a directory of every task in the workspace. get_task, however, requires a specific Task ID to retrieve all associated details, including full dependency lists and owner information.

How do I update a project's deadline? +

You use the update_task tool. You must provide the task's unique ID, then instruct your agent to change the specific field—like updating the estimated completion date or reassigning the owner.

Do I need get_workspace before working on projects? +

It’s smart to use get_workspace first. This confirms which workspace your agent is currently operating in, preventing accidental data writes or reads in the wrong project environment.

When I use the `create_task` tool, what happens if I want to nest it under a specific project or folder? +

You must provide the parent ID. This ID links the new task directly to an existing container (like a project or folder), ensuring it inherits correct dependencies and organizational structure.

If I use `get_task` and the ID is incorrect, how does the system handle the error? +

The API sends back a clear error code indicating that no task was found. Your AI client can catch this specific response and prompt you to verify the task ID or list existing tasks using list_tasks.

If I need an overview of all tasks across the entire workspace, should I use `list_projects` first? +

No. Just running list_tasks pulls a master inventory of every active task in the default workspace, regardless of which project it belongs to.

Can I manage tasks with predictive scheduling? +

Yes. Create tasks with best/worst case estimates. LiquidPlanner calculates predictive schedules and deadline probabilities automatically.

Does LiquidPlanner Classic require three credentials? +

Yes. Requires Email, Password, and Workspace ID. Uses HTTP Basic Auth (email:password) against app.liquidplanner.com/api/workspaces/{id}.

Can I track time entries? +

Yes. Access logged time entries per task and team member with effort hours and date ranges.

Connect to your AI in seconds.

Create project

Create task

Get project

LiquidPlanner Classic: 10 Tools for Project Management

Make your AI actually useful.

Create Project

Create Task

Get Project

Get Task

Get Workspace

List Members

List Projects

List Tasks

List Workspaces

Update Task

Security and governance baked right in.

Claude AI

Open Claude Settings

Add Custom Connector

Start a conversation

Claude Code

Open your terminal

Add the MCP Server

Start coding

Cursor

One-Click Install (Recommended)

Open Cursor Settings

Add New Server

Use in Composer

Antigravity

Configure Agent Environment

Bind the Endpoint

Execute

VS Code Copilot

One-Click Install (Recommended)

Open MCP Settings

Add Server Config

Windsurf

One-Click Install (Recommended)

Open Windsurf Settings

Add Server Endpoint

LangChain

Install Dependencies

Connect the Server

CrewAI

Define the Tool

Execute Task

Choose How to Get Started

Build Your Own

Make Your AI Do More

Works with Claude, ChatGPT, Cursor, and more

Planning projects used to mean juggling spreadsheets until 2 AM.

LiquidPlanner Classic MCP Server: Get the full project picture.

What your AI can actually do with this

Here's how it actually works

Who is this actually for?

What Changes When You Connect

See it in action

Project Kickoff: Determining Scope

Resource Crunch: Rebalancing Workload

Post-mortem: Understanding Delays

Discovery: Mapping All Work

The honest tradeoffs

Trying to guess resource availability

Editing a task without knowing the ID

Creating everything at once

When It Fits, When It Doesn't

Questions you might have