# Claude Model Router

> Routes each task to the cheapest Claude model that still clears the quality bar — a Claude Code skill + MCP server that optimizes total cost to an acceptable answer, not sticker price.

- **Type:** MCP server
- **Install:** `agentstack add mcp-manishk753-claude-model-router`
- **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior
- **Seller:** [manishk753](https://agentstack.voostack.com/s/manishk753)
- **Installs:** 0
- **Category:** [AI & ML](https://agentstack.voostack.com/c/ai-and-ml)
- **Latest version:** 0.1.0
- **License:** MIT
- **Upstream author:** [manishk753](https://github.com/manishk753)
- **Source:** https://github.com/manishk753/claude-model-router

## Install

```sh
agentstack add mcp-manishk753-claude-model-router
```

Requires the [AgentStack CLI](https://agentstack.voostack.com/docs/cli). Works with Claude Code, Cursor, and any MCP-compatible agent.

## About

# Model Router

Route every task to the **cheapest Claude model that still gets it right** — and cut cost by ~60% vs always using the top model.

**The catch it solves:** the cheapest model is not the cheapest *answer*. Underpower a hard task and it fails, you retry on a bigger model, and you've paid twice. This router picks the right tier the first time — and escalates automatically if it's wrong.

- ✅ 100% routing accuracy on a held-out test set
- ✅ ~60% cheaper than always-top
- ✅ Pure Python, stdlib-only — nothing to `pip install`

---

## Requirements

- Python 3.9+
- *(optional)* the `claude` CLI — lets the installer auto-register the MCP server

## Install

```bash
git clone https://github.com/manishk753/claude-model-router.git
cd claude-model-router
./install.sh
```

Installs the Claude Code skill, registers the MCP server (if `claude` is on your PATH), and runs a smoke test. Re-running is safe. **Restart Claude Code afterward** so the tools load.

Want just one piece?

| Command | Installs |
|---|---|
| `./install.sh` | Skill + MCP server (all projects) |
| `./install.sh --skill` | Skill only |
| `./install.sh --mcp-user` | MCP server only (all projects) |
| `./install.sh --mcp` | MCP server only (this project) |
| `./install.sh --help` | Show help |

## Use it

Run the examples below from the repo directory.

### 1. Command line

```bash
python3 -m router "Debug this race condition in our async job queue"
```

Returns JSON: `model`, `tier`, `complexity`, `confidence`, `rationale`, `escalate_to`.

Force the top tier for high-stakes work:

```bash
python3 -m router "Delete inactive users in production" --context '{"critical": true}'
```

### 2. Claude Code (skill)

Type `/model-router `. Claude routes, then uses the returned tier's model — `cheap → haiku`, `mid → sonnet`, `high → opus`, `top → fable`.

### 3. MCP server

Exposes one tool: `route_task(task, critical?, context_tokens?)`. The installer registers it for you. To do it by hand from the repo directory:

```bash
claude mcp add --scope user model-router -- python3 "$(pwd)/router/mcp_server.py"
```

Claude Desktop — add to `claude_desktop_config.json` (use the absolute path to `router/mcp_server.py`):

```json
{"mcpServers": {"model-router": {
  "command": "python3",
  "args": ["/absolute/path/to/claude-model-router/router/mcp_server.py"]
}}}
```

### 4. Python API

```bash
pip install anthropic   # only this path needs it
```

```python
from router.dispatcher import dispatch
response, decision, attempts = dispatch("Debug this race condition: ...")
```

`dispatch()` routes, calls the chosen model, and auto-escalates one tier on failure.

## Try the eval

```bash
python3 eval/run_eval.py     # scores every strategy, prints a table
python3 eval/run_test.py     # held-out set + writes eval/test_report.html
```

## Configure

All model IDs, prices, tier cutoffs, and weights live in [config.json](config.json) — no code changes needed.

> ⚠️ Model IDs and prices change over time. Verify them against the live API.

**Tune:** run `python3 eval/run_eval.py`, read the misroute list, then adjust `tier_cutoffs` first, `weights` second, keyword banks last.

## How it works

Free deterministic heuristics handle clear cases. A tiny Haiku classifier breaks ties only on ambiguous tasks. A capped escalation path catches the rest. Full decision contract and rules: [SKILL.md](SKILL.md).

## Source & license

This open-source MCP server is cataloged on AgentStack and links to its original source — we do not rehost the code.

- **Author:** [manishk753](https://github.com/manishk753)
- **Source:** [manishk753/claude-model-router](https://github.com/manishk753/claude-model-router)
- **License:** MIT

Install and usage instructions live in the source repository linked above.

## Pricing

- **Free** — Free

## Security capabilities

Automated source analysis of v0.1.0 — what this tool can access:

- **Network access:** no
- **Filesystem access:** no
- **Shell / process execution:** no
- **Environment & secrets:** no
- **Dynamic code execution:** no

*"Yes" means the capability is present in the source — more access means more to trust, not that it is unsafe.*


## Versions

- **0.1.0** — security scan: passed — Imported from the upstream source.

## Links

- Listing page: https://agentstack.voostack.com/l/mcp-manishk753-claude-model-router
- Seller: https://agentstack.voostack.com/s/manishk753
- Browse the marketplace: https://agentstack.voostack.com/browse

---
Listed on AgentStack — the marketplace for AI agent skills and MCP servers. Every listing is security-reviewed. Creators keep 70%.