MMCPMarkets
HM

hanzoai/mcp

Developer tools
7 stars 10 forks Quality 84 Trend 35MIT
Repository Install

Model Context Protocol server with 260+ tools for AI agents

Overview

The official server for coding agents, autonomous workflows, and tool orchestration. It exposes 260+ capabilities collapsed into high-efficiency action-routed tools over or streamable (--transport http), plus native integration with the . Hanzo Dev (dev.chat) comes pre-wired with @hanzo/mcp by default. You can also attach custom server flags: Add to your mcpServers configuration (~/.cursor/mcp.json or project .mcp.json): For remote or multi-agent deployments, serve over HTTP with Server-Sent Events: POST JSON-RPC requests to http://127.0.0.1:3000/ with header Accept: application/json, text/event-stream. Running serve with default flags registers the complete action-routed tool catalog defined in src/tools/unified/index.ts: The unified hanzo tool gives agents access to all 2,400+ endpoints across the Hanzo Cloud platform: - resource: Names the subsystem (e.g., models, graph, iam, kms, billing, chain, network). - action: Names the operation.

README

@hanzo/mcp

The official Model Context Protocol (MCP) server for coding agents, autonomous workflows, and tool orchestration.

It exposes 260+ capabilities collapsed into high-efficiency action-routed tools over stdio or streamable HTTP/SSE (--transport http), plus native integration with the Kai Agent Governance & Decision Engine.

Quick Setup & Client Configuration

The package requires Node 18 or newer.

1. Claude Code

Register globally for all projects:

npx -y @hanzo/mcp install --claude-code
# or manually:
claude mcp add --scope user hanzo -- npx -y @hanzo/mcp serve

Verify with:

claude mcp list
# reports: hanzo: npx -y @hanzo/mcp serve - ✔ Connected

2. Hanzo Dev (hanzo dev)

Hanzo Dev (dev.chat) comes pre-wired with @hanzo/mcp by default. You can also attach custom server flags:

hanzo dev
# or within any repo session:
/mcp add hanzo -- npx -y @hanzo/mcp serve

3. Cursor, Windsurf, Zed, and VS Code

Add to your mcpServers configuration (~/.cursor/mcp.json or project .mcp.json):

{
  "mcpServers": {
    "hanzo": {
      "command": "npx",
      "args": ["-y", "@hanzo/mcp", "serve"],
      "env": {
        "HANZO_API_KEY": "sk-..."
      }
    }
  }
}

4. Over Streamable HTTP (SSE)

For remote or multi-agent deployments, serve over HTTP with Server-Sent Events:

npx -y @hanzo/mcp serve --transport http --port 3000

POST JSON-RPC requests to http://127.0.0.1:3000/ with header Accept: application/json, text/event-stream.

Tool Catalog

Running serve with default flags registers the complete action-routed tool catalog defined in src/tools/unified/index.ts:

Group Tools Description
core fs, exec, code, git, fetch, workspace, ui File read/write, shell execution, AST code edits, git operations, HTTP calls, UI components.
optional think, memory, hanzo, plan, tasks, mode, gimp CoT scratchpads, semantic memory, Hanzo Cloud resource dispatch, task coordination, canvas.
code intelligence code_search, code_context, code_ask, code_index Dense vector code search, symbol index lookup, context graph resolution.
tracker tracker_boards, tracker_issues, tracker_create, tracker_update Visible engineering work items and live session status tracking on hanzo.app.
coding coding (start, progress, changes, artifacts, tree, blob, steer, merge, stop) Autonomous coding runs: a repo and a task in, a pushed branch out; a pull request when the work is ready (Rust runtime).
kai (governance) kai_decide, kai_choice, kai_score, kai_noul, kai_tool_select, kai_next_action, kai_command_guard, kai_injection_screen, kai_extract, kai_log_triage, kai_recover, kai_agent_step Typed policy evaluation, behavioral consistency benchmarking, command guards, failure recovery.

The hanzo Cloud Dispatcher

The unified hanzo tool gives agents access to all 2,400+ endpoints across the Hanzo Cloud platform:

  • resource: Names the subsystem (e.g., models, graph, iam, kms, billing, chain, network).
  • action: Names the operation. Calling with no action lists available operations.
  • args: Arguments passed to the operation.
{
  "resource": "models",
  "action": "list",
  "args": {}
}

Kai Decision Primitives & Local Acceleration

Kai tools ask Hanzo’s decision model typed questions (POST /v1/decisions on https://api.hanzo.ai or a local instance via LOCAL_KAI_URL=http://127.0.0.1:8080) and return calibrated probabilities and audit rationales:

  • kai_choice: Multi-class categorical decision matching policy criteria.
  • kai_score: Ordinal scoring and confidence assessment.
  • kai_noul: Evaluates the probability that a behavioral statement holds true.
  • kai_command_guard: Pre-execution command check (ALLOW, ASK, or DENY).
  • kai_injection_screen: Prompt injection and jailbreak barrier.
  • kai_decide: Batch evaluation of up to 100 questions in a single call.

See the cookbook for 15+ runnable recipes.

Server Flags & Custom Surfaces

Customize the active tool surface using command-line flags:

Flag Effect
--core-only Exposes only the core tools (fs, exec, code, git, fetch, workspace, ui).
--disable-tools Comma-separated list of tools to disable (e.g. --disable-tools plan,tasks).
--enable-ui Registers individual ui_* web and component inspection tools.
--enable-desktop Enables OS GUI automation (hanzo_desktop, playwright_control).
--full-surface Enables all UI, AutoGUI, orchestration, registry, and GitHub toolsets together.

List all options:

npx -y @hanzo/mcp serve --help

Sibling Implementations

Development & Testing

pnpm install
pnpm build
pnpm smoke    # runs smoke integration over stdio: initialize, tools/call, resources

Company & Leadership

Hanzo AI is co-led by Co-CEOs Antje Worring and Zach Kelling.

License

MIT — see LICENSE.

View the full README on GitHub

Install

npx -y @hanzo/mcp serve
New to MCP? Start with the mcpskill.org guide →

Configuration

{ "mcpServers": { "hanzo": { "command": "npx", "args": ["-y", "@hanzo/mcp", "serve"], "env": { "HANZO_API_KEY": "sk-..." } } } }