Skip to content
Tallyfy

MCP server

Tallyfy MCP server (preview)

Feature in development

The Tallyfy MCP Server is in active development and subject to change. Capabilities described here reflect the current state and may evolve before official release.

Tallyfy’s MCP (Model Context Protocol) Server lets you control workflows with plain English through any AI platform that supports MCP. You describe what you want, and the AI handles the rest - no API knowledge required. For a simpler approach that uses your existing AI subscriptions without technical setup, see our BYO AI (Bring Your Own AI) integration.

What is MCP?

MCP is a universal translator between AI assistants and your business tools. It’s an open standard - governed by the Agentic AI Foundation under the Linux Foundation - that creates secure connections between AI models and external systems while you stay in control of permissions. All major AI providers (OpenAI, Anthropic, Google, Microsoft) support it.

How it works

The MCP Server connects AI assistants (Claude, ChatGPT, Gemini, Copilot, and others) directly to your Tallyfy organization. Connect with OAuth 2.1 authentication or an API token, and you can:

  • Ask questions about your processes and tasks in plain English
  • Create, complete, and manage tasks through conversation
  • Launch and manage processes directly
  • Analyze templates and get improvement suggestions
  • Search across your organization’s workflows
  • Manage users and guests

Example interactions:

  • “Show me all overdue tasks for John”
  • “Launch the Employee Onboarding process for Jane Doe”
  • “What templates do we have for customer onboarding?”
  • “Analyze the health of our ‘Employee Onboarding’ template”

Current tools (preview)

Here’s what the MCP Server can do right now:

Search and discovery

  • search_for_tasks - Find tasks using natural language queries
  • search_for_processes - Locate processes by description or criteria
  • search_for_templates - Find templates that match your needs

Examples:

  • “Find all tasks related to budget approval”
  • “Search for processes containing ‘customer onboarding’”
  • “Show me templates for HR workflows”

User and access management

Organization members:

  • get_organization_users - List all members with optional group details
  • get_organization_users_list - Get a simplified user list
  • invite_user_to_organization - Add new members

Guests and groups:

  • get_organization_guests - View all guests with access to your workflows
  • get_organization_guests_list - Get a simplified guest list
  • get_groups - List groups in your organization

Task management

Viewing tasks:

  • get_my_tasks - Retrieve your assigned tasks
  • get_user_tasks - View tasks assigned to specific team members
  • get_tasks_for_process - List all tasks within a process

Task actions:

  • create_task_from_text - Create tasks from natural language with automatic due date extraction
  • complete_task - Mark a task as done
  • reopen_task - Reopen a completed task
  • update_task - Modify task details like title, deadline, or assignees

Comments:

  • get_task_comments - View comments on a task
  • add_task_comment - Add a comment to a task

Process management

  • get_organization_runs - View all running processes with filtering options
  • launch_process - Start a new process from a template
  • get_process - Get details of a specific process
  • update_process - Modify a running process
  • archive_process - Archive a completed process

Template design and optimization

Template tools:

  • get_template - Retrieve detailed template information
  • get_all_templates - List every template in your organization
  • get_template_steps - View all steps in a template
  • assess_template_health - Analyze template effectiveness
  • get_step_dependencies - See how steps relate to each other
  • suggest_step_deadline - Get deadline recommendations
  • update_template - Modify template properties
  • clone_template - Duplicate a template with a new name

Form field management:

  • add_form_field_to_step - Add form fields to template steps
  • update_form_field - Modify form field properties
  • move_form_field - Move form fields between steps
  • delete_form_field - Remove form fields
  • suggest_form_fields_for_step - Get AI suggestions for useful form fields

Dropdown fields:

  • get_dropdown_options - View dropdown field options
  • update_dropdown_options - Modify dropdown choices

Template structure:

  • add_assignees_to_step - Assign members or guests to steps
  • edit_description_on_step - Update step descriptions
  • add_step_to_template - Insert new steps

Kickoff fields:

  • suggest_kickoff_fields - Get recommendations for process launch form fields
  • get_kickoff_fields - View existing kickoff form fields

Automation and workflow logic

Automation rules:

  • create_automation_rule - Set up new automations for templates
  • update_automation_rule - Modify existing automation logic
  • delete_automation_rule - Remove automation rules
  • analyze_template_automations - Review current automation setup

Optimization:

  • consolidate_automation_rules - Simplify automation setups
  • suggest_automation_consolidation - Get recommendations for improvements
  • get_step_visibility_conditions - Check when steps appear or hide

Organization tools

  • get_tags - List tags in your organization
  • get_folders - List folders for organizing templates and processes

Security and authentication

The MCP Server uses OAuth 2.1 with PKCE for secure authentication. The well-known endpoint at /.well-known/oauth-authorization-server (per RFC 8414) lets AI clients discover authorization endpoints automatically. OAuth scopes use dot notation - for example, mcp.tasks.read, mcp.processes.write, mcp.templates.read.

Key security features:

  • Only authorized users can access your organization’s data
  • Every action respects your existing permissions
  • Audit trails track who did what
  • Dynamic Client Registration (RFC 7591) with redirect URI validation
  • Refresh token rotation with reuse detection

Available MCP integrations

Pick your AI platform:

  • Claude Desktop (Anthropic) - Remote MCP support for Pro, Max, Team, and Enterprise plans, Desktop Extensions, remote OAuth
  • ChatGPT (OpenAI) - Full MCP support via Apps (Pro/Plus/Team/Enterprise/Education plans)
  • Google Gemini - Managed MCP servers, Gemini CLI with FastMCP integration
  • Microsoft Copilot Studio - Enterprise MCP with Power Platform integration, Agent 365
  • Slack - Official MCP support with Real-time Search API (Enterprise+ plans)

Future capabilities

Coming soon:

  • Advanced reports with charts and insights
  • Connections to other middleware platforms
  • Real-time team collaboration features

Technical architecture

The MCP server is built from:

  • Core SDK - Python client that calls Tallyfy’s API
  • MCP Server - The protocol implementation (FastMCP-based)
  • Tool Framework - Structured tool definitions that tell AI clients what actions are available
  • OAuth 2.1 Layer - PKCE-based authentication with JWT access tokens

Limitations of text-based AI interfaces

MCP is powerful, but text-based AI chat has real limitations when you’re working with Tallyfy’s visual workflow features:

Visual interface constraints

  • No process tracker: Can’t display Tallyfy’s bird’s-eye view of running processes with progress indicators
  • No template builder: Can’t show the drag-and-drop interface or visualize step dependencies
  • No aggregated views: Can’t present filterable views of processes and tasks at a glance
  • No live updates: Can’t show real-time progress as team members complete tasks

Form field challenges

  • Dropdowns: Text-based AI must list all options as plain text, making selection tedious
  • Multi-select inputs: Form inputs lose their visual interface when reduced to text
  • Date/time pickers: Calendar and time tools become manual text entry
  • File uploads: Can’t handle file uploads through conversation

Assignment and collaboration barriers

  • Assignee selection: Can’t show Tallyfy’s visual suggestions for members, guests, job titles, and groups
  • Bulk operations: Managing multiple assignments through individual text commands is slow
  • Collaboration: Real-time features like simultaneous template editing become sequential

Template creation limitations

  • Step visualization: Can’t display all steps at once or show their relationships visually
  • Reordering: No drag-and-drop - must use text commands
  • Automation setup: Complex automation rules are harder to configure through conversation
  • Preview: Can’t visually preview how a template will work before deploying it

Where MCP works best

Text-based MCP shines in specific scenarios:

Search and discovery

Ask specific questions, get targeted answers:

  • “Find all templates related to employee onboarding that include background check steps”
  • “Show me all customer onboarding processes that took longer than 5 days”
  • “Which tasks are overdue and assigned to the sales team?”
  • “Find templates that use the ‘Budget Approval’ form field”

Template generation from documents

Got a messy document? AI turns it into structured templates:

  • Form field creation: Upload forms and let AI generate form fields with validation rules
  • Flowchart conversion: Turn process diagrams into templates with proper step sequences
  • Automation generation: Convert plain-language business rules into automation rules
  • Bulk field creation: Generate multiple related form fields from document analysis

What-if scenario testing

  • “If I set up an automation to route tasks by deal value, how would it handle these 5 example deals?”
  • “What would happen if we removed the approval step for purchases under $1,000?”
  • “How would task distribution change if we reassigned John’s templates to Sarah?”
  • “Based on historical data, estimate completion time if we add a review step”

Process updates from changed documents

Compliance docs changed? AI spots differences and updates everything:

  • “Here’s our updated SOX compliance procedure. Update our audit template to match”
  • AI identifies exactly what changed and updates only affected parts
  • Compare old and new documents to generate precise template modifications
  • Apply consistent changes across multiple templates from policy updates

Pattern recognition and optimization

  • “Look at one-off tasks added to hiring processes last month - which should become permanent template steps?”
  • “Which steps consistently cause delays?”
  • “Find similar templates that could be merged into one”
  • “Identify patterns in high-performing processes and suggest improvements”

Reporting with citations

  • “Which step in our sales process has the longest average completion time?”
  • “Show all instances where required approvals were skipped, with links to the processes”
  • “How has customer onboarding time changed over the last 6 months?”
  • “Which departments most frequently add ad-hoc tasks?”

Mcp Server > Using Tallyfy MCP server with ChatGPT

ChatGPT Enterprise Team and Education users can connect to Tallyfy’s MCP server using OAuth 2.1 with PKCE to manage workflows through natural language with full read/write capabilities via Developer Mode though the text-based interface has limitations for visual workflows form interactions and real-time collaboration making it best suited for complex searches analysis automation planning and template optimization.

Mcp Server > Using Tallyfy MCP server with Claude (text chat)

Claude Desktop provides native MCP integration that lets you connect Tallyfy’s workflow tools through a local server script so you can search tasks and manage processes using natural language chat while combining multiple MCP servers for cross-platform automation like onboarding employees across Tallyfy and Slack and GitHub simultaneously.

Byo Ai > ChatGPT integration

ChatGPT can connect to Tallyfy’s MCP server at mcp.tallyfy.com using OAuth 2.1 with PKCE to let users search and manage tasks and processes and templates through plain language commands with full read/write access and granular scope controls though the text-based interface works best for complex searches and analysis while visual workflow tracking and real-time collaboration still require Tallyfy’s native interface.

Byo Ai > Claude integration

Claude connects to Tallyfy’s MCP server at https://mcp.tallyfy.com using OAuth 2.1 with PKCE so you can manage tasks and processes and templates and automations through natural language in both Claude.ai web and Claude Desktop without writing any API calls.
Get in touch
About Tallyfy