Model Context Protocols (MCPs)
Extend Agiflow's AI capabilities with powerful Model Context Protocols that integrate seamlessly with your development workflow.
Why Agiflow MCP Matters
What's a defined AI agent? Prompt + Tools + Loops. With Agiflow's agent profile management and our building MCP blocks, you not only can build products better, but also repurpose Claude Code, Gemini CLI, Codex for marketing, sales, and any other purpose you like.
Our Project Management MCP
Agiflow's Project Management MCP system provides a unique, scoped approach to AI tool access. Unlike standard MCPs, Agiflow creates dedicated MCP servers per project and per task, ensuring precise context and preventing AI hallucination.
This scoped architecture means each AI agent automatically knows exactly which project and task it's working with, providing the right context without confusion or cross-contamination between different workstreams.
Scoped MCP Servers
Project MCP has access to create tasks, update project settings, etc. Task MCP only has access to update tasks, create comments, etc. Each scope prevents unauthorized actions.
MCP Proxy (Coming Soon)
Enable external MCP connections (SSE or HTTP) with authentication. Projects can selectively choose enabled MCP servers, with tasks inheriting and overriding project configs.
Building Blocks of Agiflow MCPs Offering
Agiflow provides core MCP building blocks that form the foundation of your AI-powered development workflow. Each MCP is designed to work seamlessly with the scoped architecture, providing precise context and capabilities.
Project MCP
Provides Claude with deep project context including file structure, dependencies, configuration, and codebase understanding for intelligent development assistance.
Task MCP
Enables Claude to create, manage, and track development tasks, issues, and workflows. Integrates with project management tools and provides intelligent task prioritization.
Open Source Development MCPs
We've open-sourced powerful development MCPs through the AI Code Toolkit. These MCPs help maintain consistency and enforce architectural patterns as your codebase scales.
Scaffold MCP
Open SourceGenerate standardized code from templates for consistent project bootstrapping and feature addition. Supports Next.js 15, TypeScript libraries, and MCP packages with customizable boilerplates.
Architect MCP
Open SourceEnforce architectural patterns and coding standards through design pattern guidance and automated code review. Validates code against project-specific rules with severity-rated feedback.
How Scoped MCPs Work
Unique MCP Server Per Project and Task
Each project gets its own dedicated MCP server with project-level permissions (create tasks, update project settings). Each task within a project gets its own scoped MCP server with task-level permissions (update task, create comments).
Automatic Context Awareness
The AI agent automatically knows the exact project and task scope without hallucination. No configuration needed - the scoped MCP server provides the right context and prevents cross-contamination between workstreams.
Inheritance and Override
Task MCPs inherit project MCP configurations and can selectively override settings. This eliminates bloated MCP configs while ensuring every team member gets the right tools for their specific task.
MCP Proxy Integration
External MCP connections (SSE or HTTP) with authentication can be enabled through MCP proxy. Projects selectively choose which external MCPs to enable, providing a single unified MCP interface.
Benefits of Scoped MCPs
No AI Hallucination
Scoped MCP servers ensure AI agents automatically know their exact project and task context without confusion. No more hallucinated project IDs or mixed-up task references.
Precise Permission Control
Project MCPs can create tasks and update settings, while Task MCPs are limited to task updates and comments. This prevents unauthorized actions and maintains security boundaries.
No Bloated MCP Configs
Task MCPs inherit project configurations and override as needed. Every team member gets the right tools for their specific task without managing complex, bloated MCP configurations.
Unified External MCP Access
MCP proxy enables external MCP connections with authentication. Projects selectively choose enabled MCPs, providing a single unified interface instead of multiple separate connections.
Getting Started with MCPs
Prerequisites
- Agiflow CLI installed and configured
- Active Agiflow project connection
- Claude Code running in your project
Quick Start
MCPs are automatically loaded when you start Claude in your project. To verify they're working:
Configuration Setup: Please click on the Project MCP or Task MCP sections above to copy and paste the appropriate configuration for your specific use case.
Next Steps
Explore Project MCP
Learn how Project MCP provides Claude with deep understanding of your codebase and project structure.
Explore Task MCP
Discover how Task MCP enables intelligent task management and workflow automation.
Explore Scaffold MCP
Generate standardized code from templates for consistent project bootstrapping and feature addition.
Explore Architect MCP
Enforce architectural patterns and validate code against project rules with automated guidance.