mcp

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 HTTP/SSE (hanzo mcp -t sse), plus native integration with the Kai Agent Governance & Decision Engine.

---

Install

One install, any OS (Windows included):

npm i -g hanzo                      # or, on macOS/Linux: curl -fsSL https://hanzo.sh | sh
hanzo auth login                    # sign in

npm i -g hanzo installs a small launcher. Each native Rust binary is downloaded on first use and its SHA-256 checked:

Command	What it runs
hanzo mcp	this MCP server (native Rust hanzo-mcp) over stdio; hanzo mcp -t sse serves HTTP/SSE
hanzo dev	the Hanzo Dev agent, with this server attached
hanzo engine serve <model>	local inference (Hanzo Engine)
hanzo	a coding session

The native server takes no serve subcommand (hanzo mcp serve is tolerated).

Client Configuration

Nothing needs to be installed first: npx -y hanzo mcp fetches the launcher and the server.

1. Claude Code

claude mcp add --scope user hanzo -- npx -y hanzo mcp
claude mcp list

2. Codex

codex mcp add hanzo -- npx -y hanzo mcp

3. Hanzo Dev (hanzo dev)

Hanzo Dev (dev.chat) attaches this server by default:

hanzo dev

4. 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"]
    }
  }
}

Once you have run hanzo auth login, the server uses that sign-in; set HANZO_API_KEY in an env block only to override it.

5. Over HTTP (SSE)

For remote or multi-agent deployments:

hanzo mcp -t sse --port 3333

6. Choosing tools

Every tool schema the server lists is sent to the model on each turn. Serve only the ones you use:

claude mcp add --scope user hanzo -- npx -y hanzo mcp --tools fs,code,exec

Run hanzo mcp --help for every option (--project-dir, --transport, --port, --tools).

---

Tool Catalog

Tool names and action schemas are the same in every runtime; LLM.md has the per-tool parity table:

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 native server carries kai_decide; the rest are in the TypeScript server (below).

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: Only kai_decide is in the native server; the others below are served by the TypeScript server.

• 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.

---

TypeScript server (@hanzo/mcp)

The TypeScript runtime is still published as @hanzo/mcp (Node 18+) for anyone who wants it specifically, e.g. for the kai_* governance tools the cookbook uses: npx -y @hanzo/mcp serve. Its own flags (--core-only, --disable-tools <names>, --enable-ui, --enable-desktop, --full-surface) are listed by npx -y @hanzo/mcp serve --help.

---

Sibling Implementations

• Python: hanzo-mcp on PyPI, built from hanzoai/python-sdk.
• Rust: the native server is rust/ in this repo (hanzo mcp); a native MCP client crate lives under hanzo-rs/sdk.
• Go: High-throughput MCP provider under hanzo-go/sdk.

---

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.

• Antje Worring: Co-CEO (LinkedIn · GitHub: zooqueen) — corporate leadership, operations, ecosystem partnerships, and strategic execution.
• Zach Kelling: Co-CEO & Founding CTO (LinkedIn · GitHub: zeekay) — foundational architecture, engineering, systems, and open-source models.
• Corporate Address: 1 Ferry Building, San Francisco, CA 94105
• Inquiries: dev@hanzo.ai · support@hanzo.ai

---

License

MIT — see LICENSE.