Nifty MCP for AI. Manage projects, tasks, and milestones from chat.
Gemini Works with every AI agent you already use
…and any MCP-compatible client
Connect to your AI in seconds.
Nifty MCP Server connects your AI agent directly to a unified project management workspace. This server lets you manage tasks, track milestones, view portfolios, and orchestrate entire workflows using natural conversation.
Instead of jumping between Jira, Trello, and Slack, your agent handles the data retrieval and modification across your whole organization's projects.
What your AI can do
Mark task as complete
Changes the status of a task to 'Done' or completed.
Create project milestone
Establishes a major project milestone or phase on a board.
Create new task
Adds a new, specific task to an existing Nifty board.
The agent pulls a list of all active projects and can fetch detailed metadata for specific environments.
You instruct the agent to generate new tasks or set up key project milestones within a designated board.
The agent modifies existing tasks, changing their metadata or marking them as finished.
You ask the agent to find specific tasks across multiple projects using keywords or filters.
The agent lists and provides metadata for entire groups of interconnected projects.
Ask an AI about this
Waiting for input…
Nifty MCP Server: 12 Tools for Project Workflow Management
Use these tools to create, list, update, and search every key element of your project lifecycle—from individual tasks to entire organizational portfolios.
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 Nifty on VinkiusMark Task As Complete
Changes the status of a task to 'Done' or completed.
Create Project Milestone
Establishes a major project milestone or phase on a board.
Create New Task
Adds a new, specific task to an existing Nifty board.
Get Api Status
Checks the current connection status and operational health of your Nifty account.
Get Project Details
Retrieves detailed information, including board structure and members, for a...
Get Task Info
Fetches all metadata and current details for a single, specified task ID.
List Project Milestones
Displays all major phases or milestones set for a specific project board.
List Organization Portfolios
Retrieves a list of all top-level portfolios containing multiple projects.
List Active Projects
Lists every project board currently managed under your Nifty account.
List Workflow Tasks
Lists standard, sequential tasks within an active workflow pipeline.
Search All Tasks
Finds tasks across all projects using general search terms and filters.
Update Task Metadata
Modifies key details (like assignee or description) for an existing task.
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 Nifty integration is available immediately — no restart needed.
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
Make Your AI Do More
Start with Nifty, 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 Nifty. 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
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 12 powerful capabilities that interface natively with Claude, ChatGPT, Cursor, and other compatible AI platforms. No middleware. No custom integration required.
Context switching kills velocity.
Today, updating project status is a multi-step ritual: You open Nifty, navigate to Project A's board. Then you switch tabs to check the roadmap in Google Docs. Next, you copy the task ID and paste it into Slack to notify your manager, who then has to open Jira to verify everything.
With this MCP server, your agent handles that entire chain of actions inside a chat window. You simply ask: 'Confirm Project A's status and update Task X.' The agent runs `get_task_info`, verifies the data against `list_project_milestones`, and gives you one clean answer.
Nifty MCP Server: Manage projects, tasks, and milestones from chat.
The painful manual process of tracking project health involves logging into the portfolio view (`list_organization_portfolios`), checking status against individual milestone boards (`list_project_milestones`), and then manually cross-referencing task completion records. It takes minutes, but it's error-prone.
Now, you ask your agent a single question: 'What is the current health of the Mobile App Launch portfolio?' The system executes multiple tool calls behind the scenes to gather all necessary data points and summarizes them in plain English. You just get the answer.
What your AI can actually do with this
Nifty MCP Server connects your AI agent directly to a unified project management workspace. It lets your agent read and write core project metadata—tasks, milestones, portfolios—all through natural conversation.
Your agent acts like an embedded Project Coordinator that handles the complexity of Nifty’s structure so you don't have to switch between tabs or copy-paste IDs. You tell your agent what you need, and it pulls or pushes the data across your entire organization’s projects.
Getting a full view of your work:
You can ask your agent to pull a list of every active project board managed under your Nifty account. For any specific environment, it fetches detailed metadata, giving you access to the board's structure and member lists. To see the big picture across multiple groups, it retrieves a complete list of all top-level portfolios, providing status data for entire collections of interconnected projects.
If you need to track sequential steps, your agent can display every standard task within an active workflow pipeline.
Finding specific items:
Instead of navigating manually, you just ask the agent to search across all tasks. It uses general search terms and filters to pinpoint the right item no matter which project it lives in. If you know a task ID, your agent fetches all metadata—everything from who owns it to its current status—for that single task.
You can also pull detailed information for any given board, giving you full visibility into its setup.
Changing things and creating plans:
You instruct the agent to create new tasks; it adds a specific assignment directly onto an existing Nifty board. If you need to modify an item that's already there, your agent updates key details for any task, like changing the assignee or rewriting the description. It also lets you establish major project milestones or phases on a designated board through the create_project_milestone tool.
You can tell it when a task is finished, and it changes the status to 'Done' immediately.
Monitoring and Health Checks:
Your agent constantly monitors your account health; you use the get_api_status tool to check the current connection status and operational readiness of your Nifty account. If you need a full breakdown of what’s happening, it lists all major phases or milestones set for an entire project board.
This server lets your AI agent manage everything from listing organization portfolios to marking a single task as complete. You just talk to your agent, and it handles the data retrieval and modification across every part of your workflow.
019dd12d-1a54-70dc-976d-9d8d20a939a5 
Here's how it actually works
The bottom line is: you talk to your agent like a project coordinator talking to their team, not an API endpoint calling functions.
Subscribe to the Nifty server and provide your Nifty Access Token in the client settings.
Reference a specific need (e.g., 'List all active projects' or 'Create task X').
The agent translates that request into tool calls, executes them against your Nifty account, and returns the structured data directly to you.
Who is this actually for?
Project Managers and Product Leads who hate context switching. This is for the ops engineer tired of clicking through five different dashboards just to get one status update. It works when your job requires coordinating across multiple, disconnected project silos.
Uses list_active_projects and list_project_milestones to quickly map out team roadmaps without leaving their chat window.
Creates new work items using create_new_task or modifies task metadata via update_task_metadata as decisions are made on the fly.
Checks organizational health by calling list_organization_portfolios and verifying project status across multiple departments.
What Changes When You Connect
You track project status without context switching. Instead of manually opening 5 tabs to check on 'Website Redesign' progress, just ask your agent using list_project_milestones for an instant overview.
Task creation is immediate. Don't stop work to update a ticket; simply tell the agent to add it with create_new_task. It handles the board assignment and logging instantly.
Portfolios are visible at a glance. Instead of drilling down into every department, use list_organization_portfolios to get high-level status metadata for the whole company.
You maintain perfect historical fidelity. When a task changes, you don't just update it; you modify its details using update_task_metadata, preserving the audit trail automatically.
Project discovery is fast. If you forget which project holds that key feature, running list_active_projects gives you the full list to check against.
See it in action
The End-of-Sprint Checkpoint
A Project Manager needs to know if three different teams hit their phase gates. Instead of logging into three separate dashboards, they ask the agent: 'What are the milestones for all Q4 initiatives?' The agent uses list_organization_portfolios and then list_project_milestones, giving an instant status report that drives the sprint review.
Handling Scope Creep
A Product Lead hears a new feature request mid-sprint. They tell their agent: 'Create a task for implementing X in the Mobile App Launch project.' The agent runs create_new_task, ensuring the ticket is logged and assigned immediately, preventing work from falling into the void.
The Status Update Nightmare
An Operations Team Member needs to audit 50 tasks across 3 boards. Instead of running a complex search query manually, they tell their agent: 'Find all open tasks tagged 'Legal Review' across the organization.' The agent executes search_all_tasks and compiles the list instantly.
Finalizing a Feature
The team finishes development on the Website Redesign board. A developer simply tells the agent: 'Mark task SEO Audit as complete.' The agent executes mark_task_as_complete, moving the ticket to the done column and freeing up the resource.
The honest tradeoffs
Treating Nifty like a simple database lookup.
Asking the agent, 'What is the status of Project X?' The AI might just run get_project_details and give you 50 pages of raw JSON data that's hard to read.
Instead, ask for a specific summary: 'List milestones and tell me which one is overdue.' This forces the agent to use list_project_milestones, providing only the high-level answer you need.
Over-relying on general search.
Using search_all_tasks with vague terms like 'stuff' and getting a massive, unfilterable list of 500 results that requires manual filtering anyway.
If you know the scope, use specific functions. First, run list_organization_portfolios to narrow down the area, then target your search using get_task_info on known task IDs.
Assuming all projects are visible.
Asking for a report on 'The Next Big Thing Project' and getting an error because you never listed that project board first.
Always start by running list_active_projects. This confirms the system recognizes the project name before attempting any reads or writes.
When It Fits, When It Doesn't
Use this server if your workflow requires constant, conversational interaction with structured project data. You need an agent that can act as a multi-tool dispatcher—calling list_active_projects to find the right board, then running create_new_task on it, and finally updating its metadata using update_task_metadata.
Don't use this if you just need basic file storage or simple messaging. For those, a dedicated chat tool is better. If your goal is simply to 'see what happened,' try running get_project_details first; it gives the broadest context before committing to a specific task action.
Questions you might have
How do I check if my Nifty connection is working with get_api_status? +
Run get_api_status first. This tool immediately confirms your access token works and that the server can communicate with your account, preventing failed workflow attempts later.
Can I find a task if I don't know the project name? Use search_all_tasks. +
Yes. search_all_tasks lets you use keywords to hunt for tasks across multiple projects, which is useful when you only remember part of the description or assignee.
What’s the difference between list_active_projects and get_project_details? +
Use list_active_projects to see all available project boards. Only after identifying a specific board do you run get_project_details for the deep dive into that single board's structure.
How does update_task_metadata work? Do I need an ID? +
Yes, you must provide the task ID. This tool modifies specific fields like assignee or due date, so providing a unique identifier ensures you hit the right ticket.
When should I use `list_project_milestones` versus calling `create_project_milestone`? +
You use list_project_milestones to read the current phases for a project. Calling create_project_milestone adds an entirely new, structured phase to the existing timeline. It’s how you programmatically build out your project roadmap.
To use `mark_task_as_complete`, do I need more than just the Task ID? +
Yes, you must provide context beyond the Task ID for it to work reliably. The agent needs to know which specific project or milestone this task belongs to so it can update the records accurately.
If I need an overview of all department boards, should I use `list_organization_portfolios`? +
That's the right tool. Using list_organization_portfolios scopes your view up from individual projects to entire organizational units. It helps you manage high-level departmental status without navigating multiple project dashboards.
What specific data points does `get_task_info` return that a general list doesn't? +
list_workflow_tasks gives you summaries—quick views of tasks. However, get_task_info fetches the full metadata payload for a single task. This includes detailed notes, assigned owners, and historical status changes.
Can my AI automatically find the details for a specific task by its ID? +
Yes! Use the get_task tool with the Task ID. Your agent will respond with complete metadata for the record, including assignee details, current status, and due dates in seconds.
How do I find my Nifty Access Token? +
Log in to your Nifty account (Business Plan or above required), navigate to App Center > Integrate with API, and you will find your unique secret token there.
Can I use the AI to mark a milestone as complete? +
The current MCP implementation allows you to monitor milestones and manage tasks. To update a milestone status, we recommend using the Nifty dashboard while we expand tool capabilities.
We've already built the connector for Nifty. Just plug in your AI agents and start using Vinkius.
No hosting. No infrastructure. No complex setup.
All 12 tools are live and waiting.
You're up and running in seconds.
Gemini Vinkius gives your AI agents access to the full catalog of app connectors, all fully managed, secure, and enterprise-ready. One subscription, every tool you need.
Built, hosted, and secured by Vinkius. You just connect and go.