This project implements an advanced sequential thinking process using a **Multi-Agent System (MAS)** built with the **Agno** framework and served via
This project implements an advanced sequential thinking process using a Multi-Agent System (MAS) built with the Agno framework and served via MCP. It
This is an MCP server - not a standalone application. It runs as a background service that extends your LLM client (like Claude Desktop) with sophisticated sequential thinking capabilities. The server provides a sequentialthinking tool that processes thoughts through multiple specialized AI agents, each examining the problem from a different cognitive angle.
DEEPSEEK_API_KEY (default, recommended) - Groq: GROQ_API_KEY - OpenRouter: OPENROUTER_API_KEY - GitHub Models: GITHUB_TOKEN - Anthropic: ANTHROPIC_API_KEY - Ollama: Local installation (no API key) - Optional: EXA_API_KEY for web research capabilities - uv package manager (recommended) or pipCompare MCP servers by category, or browse hosted MCP servers if you prefer an endpoint over a local process.
{
"mcpServers": {
"sequential-thinking": {
"command": "mcp-server-mas-sequential-thinking",
"env": {
"LLM_PROVIDER": "deepseek",
"DEEPSEEK_API_KEY": "YOUR_DEEPSEEK_API_KEY",
"EXA_API_KEY": "YOUR_EXA_API_KEY"
}
}
}
}From the project documentation. Replace placeholders and example paths before connecting.
DEEPSEEK_API_KEY (default, recommended) - Groq: GROQ_API_KEY - OpenRouter: OPENROUTER_API_KEY - GitHub Models: GITHUB_TOKEN - Anthropic: ANTHROPIC_API_KEY - Ollama: Local installation (no API key) - Optional: EXA_API_KEY for web research capabilities - uv package manager (recommended) or pip| Variable | Description | Required |
|---|---|---|
| LLM_PROVIDER | Declared in the maintainer’s client configuration. | Check documentation |
| DEEPSEEK_API_KEY | Declared in the maintainer’s client configuration. | Check documentation |
| EXA_API_KEY | Declared in the maintainer’s client configuration. | Optional |
Read, search and edit files inside allowed directories with the Model Context Protocol reference Filesystem server.
Retrieve version-aware library documentation and code examples with Context7 MCP, using resolve-library-id and query-docs.
:heavy_exclamation_mark: This project builds a local, read-only MCP server. For fully remote MCP access, check out the first managed MCP platform
AI-assisted development MCP providing long-term, on-device "AI memory" for IDEs. Powered by Kuzu GraphDB and exposed via MCP server
MCP Server and Plugin for Vectric Aspire/V-Carve
Code synthesis through belief revision, mutation testing, and verification