Log inSubmit server
Tachibot MCP logo

Tachibot MCP

Orchestrates multiple AI model providers through 67 MCP tools, profiles, prompt techniques, and YAML workflows.

InstallRepositoryWebsite
Full README Compare alternatives Embed widget Claim this listing

Install Tachibot MCP

Pick your client, then add it in one click or paste the config.

STDIONode.js
~/Library/Application Support/Claude/claude_desktop_config.json
claude_desktop_config.json
{
  "mcpServers": {
    "tachibot-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "-p",
        "tachibot-mcp",
        "tachibot"
      ]
    }
  }
}

Settings → Developer → Edit Config, merge this into mcpServers, then fully quit and reopen Claude Desktop.

We couldn’t confirm it starts correctly

We ran the install command but it didn't respond within our test window — this can mean a slow first-time install rather than a real problem.

npx -y -p tachibot-mcp tachibot

No response to initialize.

This is an experimental automated check and can have false negatives — missing environment variables, a slow cold install, etc. It doesn’t necessarily mean something’s wrong. Last checked 10d ago.

Overview

The tachibot-mcp MCP server exposes multi-model AI orchestration through the Model Context Protocol. It provides 67 tools for reasoning, search, coding review, planning, writing, prompt techniques, and other model-assisted tasks across 12 providers. YAML workflows and token-optimized profiles help structure repeated or provider-diverse operations. Reach for it when an MCP client needs access to several AI providers through one tool interface.

Use cases

  • Route reasoning tasks across multiple AI providers
  • Run structured YAML-based model workflows
  • Review code changes and implementation plans
  • Search with provider-specific AI tools
  • Generate researched long-form writing

Key features

  • 67 MCP tools
  • 12 AI providers
  • YAML workflow support
  • Token-optimized profiles
  • 85 prompt techniques
  • Code review and planning tools

Security & health

What it can reach and how reliably it runs — from our own checks, not the maintainer’s claims.

ActiveLast checked 2d ago

Recent health check succeeded.

4/4 checks healthy over the last 20d

Supply-chain signal

No high-severity advisories surfaced by our automated scan.

Critical 0High 0Medium 0Low 0

Scanned 5d ago via OSV.dev · tachibot-mcp (npm)

Adoption & maintenance

Factual signals from GitHub, npm, and our automated checks — not a rating.

GitHub stars13Stargazers on the source repository.
npm downloads3kPackage downloads in the last 30 days.
Last commit6d agoMost recent push to the default branch.
Install checkInconclusiveDidn't respond in our test window — often a slow first install.
Directory activity2 viewsConfig copies, upvotes, and views on AllMCPs.

How Tachibot MCP works

What the tachibot-mcp MCP server does

tachibot-mcp MCP server gives MCP-compatible clients a single interface for orchestrating models from multiple AI providers. The tool catalog covers model calls, web-oriented search, reasoning, code review, plan critique, writing, and prompt-engineering techniques.

The server is intended for workflows that benefit from choosing different models or prompting strategies for different tasks. For example, separate tools route reasoning, explanation, brainstorming, search, and code review requests to different provider or model paths. Named profiles provide predefined configurations with different token or capability tradeoffs, while YAML workflows support structured multi-step operations.

How it works

An MCP client discovers tachibot-mcp MCP server tools and invokes the tool that matches the task. The server handles the provider-specific orchestration behind that interface.

The project also includes a prompt-technique library. Listed techniques cover retrieval, prompt-injection defense, few-shot prompting, trace management, tabular work, and creative writing. A recommendation path can select techniques based on the wording or intent of a request, and a preview tool can show the selected technique before use. The catalog has expanded to 85 techniques according to the release notes.

Setup and configuration

tachibot-mcp MCP server is distributed as the tachibot-mcp npm package and requires Node.js 22 or newer. The README identifies it as compatible with Claude Code, Claude Desktop, Cursor, and MCP clients generally.

The release notes describe profiles including full, balanced, research_power, and heavy_coding; they also indicate that the project has six real profiles, while older documentation may contain stale profile information. Provider access can vary by organization and model availability. For example, the OpenAI path can fall back to other models when an organization cannot access the default model.

Tools and capabilities

  • Invoke model-specific reasoning, explanation, brainstorming, and code-review operations.
  • Search with provider-specific tools, including Grok search and OpenAI search paths.
  • Review code changes and critique implementation plans.
  • Generate researched long-form writing with blog_writer.
  • Apply retrieval, few-shot, tabular, writing, and prompt-injection-defense techniques.
  • Build structured operations with YAML workflows and select among token-oriented profiles.

Limitations and notes

The tool count and model routing change between releases, so descriptions tied to a specific version may become outdated. Version 2.34.0 lists 67 tools, while earlier release notes mention 66; use the installed package version as the source of truth. Some models are limited to particular organizations or may be retired by their provider, and the server can fall back to another model in supported cases.

Read the full README View source on GitHub

Reviews

No reviews yet — be the first to share how it worked for you.

Frequently Asked Questions about Tachibot MCP

tachibot-mcp is an MCP server that connects MCP clients to 12 AI providers through 67 tools for model reasoning, search, code review, plan critique, writing, and prompt techniques. It also supports YAML workflows and configurable profiles for orchestrating different model and token-use strategies.

Install tachibot-mcp from its npm package using the project’s documented setup instructions.

Yes, tachibot-mcp is documented as working with Cursor. The README also names Claude Code, Claude Desktop, and MCP clients generally as supported client environments.

They cover model orchestration, search, reasoning, writing, code review, plan critique, and prompt techniques; earlier releases listed fewer tools.

tachibot-mcp supports 12 providers.

Related MCP servers

All in Finance & Fintech All alternatives
Add a badge to your READMEShow it’s listed — live SVG, Markdown or HTML.

AllMCPs Directory Badge

Full Badge Customizer

Showcase your server listing on GitHub or your project documentation. Embed this dynamic SVG badge to highlight official listing status and live engagement.

Badge Style:
Live Dynamic SVG PreviewTachibot MCP AllMCPs Directory Badge
Markdown (GitHub README)
[![AllMCPs](https://allmcps.com/api/badge/tachibot-mcp?style=directory)](https://allmcps.com/mcp/tachibot-mcp)
HTML Embed
<a href="https://allmcps.com/mcp/tachibot-mcp"><img src="https://allmcps.com/api/badge/tachibot-mcp?style=directory" alt="Tachibot MCP on AllMCPs" /></a>