Agents Council
A

Agents Council

Agents Council is an AI agent collaboration tool based on the MCP protocol, which allows different AI agent sessions (such as Claude Code, Codex, Gemini, etc.) to communicate and collaborate across sessions without additional infrastructure. It realizes communication between agents through a central MCP server, supports session retention, human - participation monitoring, summoning of Claude agents, etc., to help developers solve complex tasks.
2.5 points
6.7K

What is Agents Council?

Agents Council is a tool based on the Model Context Protocol (MCP), specifically designed to connect and coordinate the collaboration among different AI agents. It allows your existing AI sessions (such as Claude Code, Codex, Gemini, Cursor, etc.) to communicate with each other, share insights, and jointly solve complex problems. Imagine that you can let Claude be responsible for code review, Gemini provide creative suggestions, and Codex assist in debugging. They communicate in real - time through the Agents Council platform, ultimately providing you with a more comprehensive and high - quality solution.

How to use Agents Council?

Using Agents Council is very simple: 1. Start a council session in one of your AI tools (such as Claude Code) and describe the problem you need to solve. 2. Join this council from another AI tool (such as Codex or Gemini). 3. Let different AI agents discuss and collaborate. 4. After the council provides enough insights, you can take over the session and continue working. The entire process does not require you to leave your current working environment, and all states are saved locally.

Applicable scenarios

Agents Council is particularly suitable for the following scenarios: - When complex problems require multi - angle analysis. - When code review requires the opinions of multiple experts. - When creative projects need suggestions from different styles of AI. - When technical decisions need to weigh different options. - When learning new concepts requires explanations from different perspectives.

Main features

Cross - platform AI collaboration
Connect multiple AI agents such as Claude, Codex, Gemini, Cursor, etc., and let them collaborate on the same topic.
Summon Claude function
Summon a new Claude instance to participate in the discussion at any time in the council, and automatically reuse the authentication information of the local Claude Code.
Session retention
Set specific context when starting an AI agent. After they collaborate, you can seamlessly take over the session and continue working.
Local chat interface
Provide a local web interface that allows you to monitor the council discussion in real - time and participate as a human if necessary.
Fully localized
All state data is stored on the local disk (~/.agents - council/state.json) to ensure privacy and security.
Flexible output format
Support Markdown or JSON format output, which is suitable for both human reading and automated processing.
Advantages
No complex infrastructure required: Directly connect existing AI sessions without setting up a server or network configuration.
Maintain workflow: No need to leave the current working environment and can continue working immediately after collaboration.
Privacy protection: All data is stored locally and does not rely on cloud services.
Flexible integration: Support multiple popular AI development tools.
Easy to use: Can be enabled through simple MCP configuration.
Limitations
Experimental stage: Currently in the experimental state, and the functions may change.
Dependent on local installation: Requires a Node.js or Bun environment.
Some functions are limited: Currently mainly supports the summoning function of Claude, and the summoning functions of other AIs are under development.
Requires manual configuration: Each AI tool needs to be configured with an MCP server separately.

How to use

Environment preparation
Ensure that your system has installed the Node.js (≥18.0.0) or Bun runtime environment.
Install Agents Council
If you need to use the web interface or global commands, you can install it globally. If you only need the MCP function, you can skip this step.
Configure the MCP server
Select the corresponding configuration command according to the AI tool you use. The following is an example of configuring Claude Code.
Start a council session
In your AI tool, use the start_council tool to start a new council discussion.
Join the council
In other AI tools, use the join_council tool to join an existing council.
Participate in the discussion
Use the send_response tool to submit feedback, or use get_current_session_data to get the latest discussion content.

Usage examples

Code review collaboration
When you need to review complex code from multiple perspectives, you can let different AI agents participate together. Claude can check the code quality, Codex can evaluate the performance, and Gemini can provide best - practice suggestions.
Architectural design decision
When designing a system architecture, different options need to be weighed. Through council discussion, a more comprehensive perspective can be obtained, avoiding the bias or limitations of a single AI.
Learning complex concepts
When learning new technologies or complex concepts, different AIs can explain them in different ways to help you understand from multiple perspectives.

Frequently Asked Questions

Is Agents Council free?
Do I need to pay separately for each AI tool?
How to ensure my data privacy?
Which AI tools are supported?
What conditions are required for the summoning Claude function?
Can multiple councils run simultaneously?
How to get help when encountering problems?

Related resources

GitHub repository
Source code, issue tracking, and contribution guidelines
MCP protocol documentation
Official specification of the Model Context Protocol
Claude Code documentation
MCP configuration guide for Claude Code
LLM Council project
The project that inspired Agents Council

Installation

Copy the following command to your Client for configuration
{
  "mcpServers": {
    "council": {
      "command": "npx",
      "args": [
        "agents-council@latest",
        "mcp"
      ]
    }
  }
}
Note: Your key is sensitive information, do not share it with anyone.

Alternatives

V
Vestige
Vestige is an AI memory engine based on cognitive science. By implementing 29 neuroscience modules such as prediction error gating, FSRS - 6 spaced repetition, and memory dreaming, it provides long - term memory capabilities for AI. It includes a 3D visualization dashboard and 21 MCP tools, runs completely locally, and does not require the cloud.
Rust
9.2K
4.5 points
M
Moltbrain
MoltBrain is a long-term memory layer plugin designed for OpenClaw, MoltBook, and Claude Code, capable of automatically learning and recalling project context, providing intelligent search, observation recording, analysis statistics, and persistent storage functions.
TypeScript
8.7K
4.5 points
B
Bm.md
A feature-rich Markdown typesetting tool that supports multiple style themes and platform adaptation, providing real-time editing preview, image export, and API integration capabilities
TypeScript
15.6K
5 points
S
Security Detections MCP
Security Detections MCP is a server based on the Model Context Protocol that allows LLMs to query a unified security detection rule database covering Sigma, Splunk ESCU, Elastic, and KQL formats. The latest version 3.0 is upgraded to an autonomous detection engineering platform that can automatically extract TTPs from threat intelligence, analyze coverage gaps, generate SIEM-native format detection rules, run tests, and verify. The project includes over 71 tools, 11 pre-built workflow prompts, and a knowledge graph system, supporting multiple SIEM platforms.
TypeScript
7.7K
4 points
P
Paperbanana
Python
8.8K
5 points
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
10.4K
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
8.6K
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
9.4K
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
79.3K
4.3 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
24.4K
4.5 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
37.7K
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
27.8K
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#
38.0K
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
71.1K
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
23.6K
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
105.5K
4.7 points
AIBase
Zhiqi Future, Your AI Solution Think Tank
© 2026AIBase