Orchestrate multiple AI models (Perplexity, Grok, OpenAI, Gemini, OpenRouter) with 31 tools and YAML workflows. For developers building multi-model AI agents, research pipelines, and code analysis systems.
io.github.byPawel/tachibot-mcp
Local install
STDIO
3 required env vars
How models use it and what it is built for.
Orchestrate multiple AI models (Perplexity, Grok, OpenAI, Gemini, OpenRouter) with 31 tools and YAML workflows. For developers building multi-model AI agents, research pipelines, and code analysis systems.
Local install — runs as a subprocess.
Configuration this server reads at startup.
Perplexity API key for web search, research, and reasoning (https://www.perplexity.ai/settings/api)
Grok/xAI API key for code analysis, debugging, and architecture (https://console.x.ai/)
OpenAI API key for GPT-5 analysis and comparison (https://platform.openai.com/api-keys)
Google Gemini API key for brainstorming and code/text analysis (https://aistudio.google.com/apikey)
OpenRouter API key for Qwen3 Coder and other models
Tool profile selection: minimal, research_power, code_focus, balanced, or full (default: balanced)
Where to find authoritative docs and source for Bypawel Tachibot.
Paste any of these into Agent Studio after connecting Bypawel Tachibot.
Common questions about connecting and running Bypawel Tachibot.
What models does tachibot-mcp support?
It supports Perplexity (web search and research), Grok/xAI (code analysis and debugging), OpenAI (GPT-5 analysis), Google Gemini (brainstorming and text analysis), and OpenRouter models like Qwen3 Coder. You configure which ones to use via API keys.
Do I need all five API keys to use tachibot-mcp?
No. Perplexity, Grok, and OpenAI keys are required; Google Gemini and OpenRouter are optional. Start with the three required keys and add others as needed for your workflow.
What are token-optimized profiles and how do I choose one?
Profiles (minimal, research_power, code_focus, balanced, full) control which of the 31 tools are active, reducing token usage and costs. Set TACHIBOT_PROFILE to match your use case; balanced is the default.
Can I define custom workflows in YAML?
Yes, tachibot-mcp supports YAML workflows for orchestrating multi-step AI tasks. Refer to the project documentation for workflow schema and examples.
How do I install and run tachibot-mcp?
Install with `npx tachibot-mcp@2.0.5`, set your required API keys (PERPLEXITY_API_KEY, GROK_API_KEY, OPENAI_API_KEY), optionally set TACHIBOT_PROFILE, and connect via stdio transport to your MCP client.
MCP Playground runs 10,000+ hosted MCP servers — GitHub, Linear, Notion, Stripe, Sentry and more — across Claude, GPT, Gemini, DeepSeek and 60+ AI models. Compare model answers side-by-side, save agent presets, share runs. Zero install.
Open Agent StudioJudges Panel
45 judges that evaluate AI-generated code for security, cost, and quality with built-in AST.
Addozhang Nexus
Query Sonatype Nexus Repository (OSS/Pro) for Maven, Python, and Docker artifacts
Cyanheads MCP Ts Template
TypeScript template for building MCP servers with declarative tooling, observability, and auth.
Chernistry Bernstein
Declarative agent orchestration for engineering teams