CLEO is a portable brain and memory system designed for AI software development, providing project memory, verifiable sources, and agent - secure orchestration across repositories, model providers, and coding tools.
3 points
6.7K

What is the CLEO MCP Server?

The CLEO MCP Server is a server based on the Model Context Protocol (MCP) standard. It exposes CLEO's intelligent task management, project memory, and collaboration functions to any AI development tool that supports MCP. Through this server, your AI assistant (such as Claude Code, Cursor, etc.) can directly query task status, create new tasks, update progress, and access the project's complete memory system.

How to use the CLEO MCP Server?

Using the CLEO MCP Server is very simple: First, make sure CLEO is installed. Then, add the MCP server to your AI tool through automatic configuration or manual configuration. After configuration, your AI assistant will have two core tools: query and mutate. Through these tools, you can access all the functions of CLEO.

Applicable scenarios

The CLEO MCP Server is particularly suitable for the following scenarios: 1. When using an AI assistant for software development, you need to manage complex task dependencies. 2. In team collaboration projects, you need to maintain the consistency of task status. 3. In long - term projects, you need to maintain project memory and knowledge bases. 4. In multi - tool workflows, you need to share task context between different AI tools.

Main features

Dual - tool interface
Provides two core tools, query and mutate, covering all read and write operations. Query is used to safely read data, and mutate is used to create and modify data to ensure the security of operations.
10 functional domains
Organized into 10 logical domains: tasks, session, memory, check, pipeline, orchestrate, tools, admin, nexus, sticky. Each domain contains a related set of operations.
256 standardized operations
Provides 145 query operations and 111 modification operations, covering all functions of CLEO. Each operation has clearly defined parameters and return values to ensure that the AI assistant can accurately understand and use them.
Automatic tool detection and configuration
Supports automatic detection and configuration of 12 AI development tools, including Claude Code, Cursor, Windsurf, Antigravity, etc. One - click configuration without manually editing the configuration file.
Structured JSON response
All responses follow the LAFS (LLM - Agent - First Specification) protocol and return structured JSON data. Supports MVI (Minimum - Viable - Complete) progressive disclosure to optimize token usage efficiency.
Cross - project network support
Supports cross - project queries and collaboration through the nexus domain. You can access the registered CLEO project network, share patterns, and discover related projects.
Advantages
Standardized interface: Based on the MCP protocol, compatible with all tools that support MCP.
No need to learn new commands: The AI assistant uses the familiar query/mutate mode.
Automatic configuration: Supports automatic detection and configuration of 12 tools.
Complete function coverage: 256 operations cover all functions of CLEO.
Security isolation: Query operations are read - only, and mutate operations require explicit calls.
Structured response: The JSON format is convenient for the AI assistant to parse and process.
Limitations
Dependent on MCP compatibility: The AI tool needs to support the MCP protocol.
Configuration complexity: Some tools require manual configuration of the MCP server.
Learning curve: You need to understand the organizational structure of 10 domains and 256 operations.
Performance consideration: Network communication may be slightly slower than the local CLI.

How to use

Install CLEO
First, make sure CLEO is installed. You can install it via NPM or use the installation script.
Automatically configure the MCP server
Run the automatic configuration command. CLEO will detect the installed AI tools and automatically configure the MCP server.
Verify the configuration
Check the list of supported AI tools to confirm successful configuration.
Manual configuration (optional)
If automatic configuration fails or you need custom configuration, you can manually edit the MCP configuration file of the tool.
Start using
Restart the AI tool. Now your assistant can use the query and mutate tools to interact with CLEO.

Usage examples

Daily task management
The AI assistant helps you manage daily development tasks, query to - do items, and update task status.
Project planning meeting
In the planning meeting, the AI assistant helps create new epic tasks and decompose sub - tasks.
Code review assistance
During code review, the AI assistant queries the historical records and decision - making basis of related tasks.
Cross - project collaboration
When working on multiple related projects, the AI assistant helps discover cross - project dependencies and patterns.

Frequently Asked Questions

What is the difference between the MCP Server and the CLEO CLI?
Which AI tools support the CLEO MCP Server?
Is the MCP Server secure? Will it be misoperated by the AI assistant?
How to view all operations supported by the MCP Server?
What is the performance of the MCP Server? Will it affect the response speed of the AI assistant?
What if the automatic configuration fails?

Related resources

MCP Server specification document
The complete technical specification of the MCP server, including detailed descriptions of all domains and operations
MCP usage guide
A beginner - oriented tutorial on using the MCP server, including step - by - step examples
CLEO GitHub repository
The source code and issue tracking of the CLEO project
Model Context Protocol official website
The official documentation and specifications of the MCP protocol
LAFS protocol specification
The specification of the LLM - Agent - First Specification protocol

Installation

Copy the following command to your Client for configuration
{
  "mcpServers": {
    "cleo": {
      "command": "npx",
      "args": ["-y", "@cleocode/cleo", "--mcp-server"]
    }
  }
}

{
  "mcpServers": {
    "cleo": {
      "command": "cleo",
      "args": ["mcp"]
    }
  }
}
Note: Your key is sensitive information, do not share it with anyone.

Alternatives

B
Better Icons
An MCP server and CLI tool that provides search and retrieval of over 200,000 icons, supports more than 150 icon libraries, and helps AI assistants and developers quickly obtain and use icons.
TypeScript
5.6K
4.5 points
A
Assistant Ui
assistant - ui is an open - source TypeScript/React library for quickly building production - grade AI chat interfaces, providing composable UI components, streaming responses, accessibility, etc., and supporting multiple AI backends and models.
TypeScript
6.2K
5 points
A
Apify MCP Server
The Apify MCP Server is a tool based on the Model Context Protocol (MCP) that allows AI assistants to extract data from websites such as social media, search engines, and e-commerce through thousands of ready-to-use crawlers, scrapers, and automation tools (Apify Actors). It supports OAuth and Skyfire proxy payment and can be integrated into MCP clients such as Claude and VS Code through HTTPS endpoints or local stdio.
TypeScript
6.4K
5 points
R
Rsdoctor
Rsdoctor is a build analysis tool specifically designed for the Rspack ecosystem, fully compatible with webpack. It provides visual build analysis, multi - dimensional performance diagnosis, and intelligent optimization suggestions to help developers improve build efficiency and engineering quality.
TypeScript
9.3K
5 points
N
Next Devtools MCP
The Next.js development tools MCP server provides Next.js development tools and utilities for AI programming assistants such as Claude and Cursor, including runtime diagnostics, development automation, and document access functions.
TypeScript
10.7K
5 points
T
Testkube
Testkube is a test orchestration and execution framework for cloud-native applications, providing a unified platform to define, run, and analyze tests. It supports existing testing tools and Kubernetes infrastructure.
Go
6.5K
5 points
M
MCP Windbg
An MCP server that integrates AI models with WinDbg/CDB for analyzing Windows crash dump files and remote debugging, supporting natural language interaction to execute debugging commands.
Python
10.5K
5 points
R
Runno
Runno is a collection of JavaScript toolkits for securely running code in multiple programming languages in environments such as browsers and Node.js. It achieves sandboxed execution through WebAssembly and WASI, supports languages such as Python, Ruby, JavaScript, SQLite, C/C++, and provides integration methods such as web components and MCP servers.
TypeScript
9.3K
5 points
G
Gitlab MCP Server
Certified
The GitLab MCP server is a project based on the Model Context Protocol that provides a comprehensive toolset for interacting with GitLab accounts, including code review, merge request management, CI/CD configuration, and other functions.
TypeScript
24.2K
4.3 points
M
Markdownify MCP
Markdownify is a multi-functional file conversion service that supports converting multiple formats such as PDFs, images, audio, and web page content into Markdown format.
TypeScript
33.9K
5 points
N
Notion Api MCP
Certified
A Python-based MCP Server that provides advanced to-do list management and content organization functions through the Notion API, enabling seamless integration between AI models and Notion.
Python
20.2K
4.5 points
D
Duckduckgo MCP Server
Certified
The DuckDuckGo Search MCP Server provides web search and content scraping services for LLMs such as Claude.
Python
72.2K
4.3 points
U
Unity
Certified
UnityMCP is a Unity editor plugin that implements the Model Context Protocol (MCP), providing seamless integration between Unity and AI assistants, including real - time state monitoring, remote command execution, and log functions.
C#
31.0K
5 points
F
Figma Context MCP
Framelink Figma MCP Server is a server that provides access to Figma design data for AI programming tools (such as Cursor). By simplifying the Figma API response, it helps AI more accurately achieve one - click conversion from design to code.
TypeScript
64.0K
4.5 points
G
Gmail MCP Server
A Gmail automatic authentication MCP server designed for Claude Desktop, supporting Gmail management through natural language interaction, including complete functions such as sending emails, label management, and batch operations.
TypeScript
21.0K
4.5 points
C
Context7
Context7 MCP is a service that provides real-time, version-specific documentation and code examples for AI programming assistants. It is directly integrated into prompts through the Model Context Protocol to solve the problem of LLMs using outdated information.
TypeScript
97.8K
4.7 points
AIBase
Zhiqi Future, Your AI Solution Think Tank
© 2026AIBase