Skip to content
Tallyfy

Using Tallyfy MCP server with Google Gemini

Google Gemini connects to Tallyfy’s MCP server through OAuth 2.1, letting you manage workflows with natural language. You can use the Gemini CLI for local connections or Google Cloud’s managed MCP infrastructure for enterprise setups.

Gemini MCP support status

  • Official support - MCP announced December 2025 for Gemini models
  • Managed MCP servers - Google Cloud provides managed servers for Maps, BigQuery, Compute Engine, Kubernetes Engine
  • Gemini CLI - FastMCP integration for local MCP server connections
  • Transport - Streamable HTTP
  • Apigee integration - Translate standard APIs to MCP servers

Prerequisites

  • Google Cloud account with Gemini API access
  • Tallyfy account with an active organization
  • Gemini CLI installed (for local MCP connections)

Setting up the connection

  1. Install Gemini CLI

    Terminal window
    npm install -g @google/gemini-cli
    gemini --version

  2. Configure MCP server connection

    Create a configuration file for the Tallyfy MCP server:

    {
      "mcpServers": {
        "tallyfy": {
          "url": "https://mcp.tallyfy.com",
          "transport": "streamable-http",
          "auth": {
            "type": "oauth2",
            "authorization_url": "https://go.tallyfy.com/mcp/oauth/authorize",
            "token_url": "https://go.tallyfy.com/mcp/oauth/token",
            "scopes": ["mcp.tasks.read", "mcp.tasks.write", "mcp.processes.read", "mcp.processes.write", "mcp.templates.read", "mcp.templates.write", "mcp.users.read"]
          }
        }
      }
    }

    Tallyfy uses dot-separated scopes with read/write suffixes (e.g., mcp.tasks.read). The full list of available scopes includes mcp.users.read, mcp.users.write, mcp.tasks.read, mcp.tasks.write, mcp.processes.read, mcp.processes.write, mcp.templates.read, mcp.templates.write, mcp.forms.read, mcp.forms.write, mcp.automation.read, and mcp.automation.write.

  3. Authenticate with Tallyfy

    Terminal window
    gemini mcp auth tallyfy

    This opens a browser window where you’ll authorize Gemini’s access to your Tallyfy workspace and select your organization.

  4. Verify the connection

    Terminal window
    gemini chat --mcp tallyfy
    > Show me all open tasks in Tallyfy

  5. Use in Google Cloud (optional)

    For enterprise deployments, configure Tallyfy as a managed MCP server in Google Cloud:

    # gemini-mcp-config.yaml
    apiVersion: aiplatform.googleapis.com/v1
    kind: McpServerConfig
    metadata:
      name: tallyfy-mcp
    spec:
      endpoint: https://mcp.tallyfy.com
      authentication:
        oauth2:
          clientId: ${TALLYFY_CLIENT_ID}
          authorizationEndpoint: https://go.tallyfy.com/mcp/oauth/authorize
          tokenEndpoint: https://go.tallyfy.com/mcp/oauth/token

Practical examples

Task management via natural language

Prompt:

Using Tallyfy, find all overdue tasks and create a summary grouped by assignee.

Gemini will call the search_for_tasks tool with an overdue filter, group results by assignee, and generate a formatted summary.

Process analytics

Prompt:

Analyze our "Customer Onboarding" processes from the last month and identify bottlenecks.

Gemini queries process history through MCP tools, calculates step completion times, and identifies which steps take longest.

Template review

Prompt:

Review our "Invoice Processing" template and suggest improvements.

Gemini retrieves the template structure using get_template, analyzes step dependencies and automation rules, then suggests optimizations.

Gemini-specific features

Google Cloud integration

Since Gemini lives inside Google’s platform, you can combine Tallyfy data with other Google services:

  • BigQuery - Analyze Tallyfy process data alongside your data warehouse
  • Cloud Run - Deploy custom MCP logic at scale
  • Pub/Sub - Set up event-driven workflow triggers

Multimodal input

Gemini can process images and documents alongside text, which helps with visual inspection workflows or document review processes.

Vertex AI agents

Build multi-agent systems that combine Tallyfy with other services through Google’s Agent Development Kit - useful for orchestrating across multiple tools with governance controls.

Limitations

Feature rollout

MCP support is new (December 2025). Some managed MCP servers are still rolling out, regional availability varies, and enterprise features may need additional configuration.

Text-based constraints

Like other AI chat interfaces, Gemini can’t display Tallyfy’s visual process tracker. Complex forms become text-based interactions, and you’ll need to ask explicitly for status updates.

Google Cloud dependencies

Managed MCP servers require a Google Cloud account. Some features need specific IAM permissions, and Cloud usage has its own billing.

Best use cases

Data-driven optimization

Combine BigQuery analytics with Tallyfy process data:

Correlate customer support ticket data from BigQuery with our support process completion times in Tallyfy.

Multi-service automation

Coordinate across Google Cloud and Tallyfy:

When a new document is uploaded to Cloud Storage, trigger the document review process in Tallyfy and notify the team via Gmail.

Process monitoring

Use Gemini’s analytical capabilities for workflow insights:

Monitor all active processes and alert me to any at risk of missing their SLA, with root cause analysis.

Security

  • Authentication - OAuth 2.1 with PKCE (S256 code challenge). Tokens are stored in Google’s infrastructure with automatic refresh token rotation.
  • Data handling - Processed according to Google’s AI policies, with enterprise controls via Vertex AI and audit logging in Cloud Logging.
  • Network - All traffic over HTTPS, with VPC Service Controls and private connectivity options for enterprise.

Integrations > MCP server

Tallyfy’s MCP Server lets you control workflows through plain English in any major AI platform like ChatGPT or Claude or Gemini or Copilot using the open Model Context Protocol standard to search tasks and launch processes and manage templates and set up automations without needing any API knowledge.

Mcp Server > Using Tallyfy MCP server with ChatGPT

ChatGPT Enterprise and Team users can connect to Tallyfy’s MCP server at mcp.tallyfy.com through OAuth 2.1 authentication to manage workflows and search tasks and analyze templates using natural language prompts while the text-based interface works well for complex queries and process documentation but falls short for visual workflow tracking and real-time collaboration and bulk operations that are better handled in Tallyfy’s native UI.

Integrations > BYO AI (Bring Your Own AI)

BYO AI lets you connect your existing AI subscriptions like ChatGPT or Claude directly into Tallyfy workflows through the MCP industry standard so your AI can read task context and complete steps and generate content and make decisions automatically inside running processes without any copy-pasting or app-switching.

Byo Ai > ChatGPT integration

ChatGPT users on Plus or higher plans can connect to Tallyfy’s MCP server at https://mcp.tallyfy.com using OAuth 2.1 with PKCE to search and manage tasks and processes and templates and automations through plain language — with over 30 available tools covering everything from task creation to template health audits — though the text-based interface cannot replace Tallyfy’s visual workflow tracking or handle file uploads and
Get in touch
About Tallyfy