# Mcpgrade

> Lighthouse for MCP servers — score any MCP server on agent usability, not just spec compliance

- **Type:** MCP server
- **Install:** `agentstack add mcp-tengbyte-mcpgrade`
- **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior
- **Seller:** [TengByte](https://agentstack.voostack.com/s/tengbyte)
- **Installs:** 0
- **Category:** [Integrations](https://agentstack.voostack.com/c/integrations)
- **Latest version:** 0.1.0
- **License:** MIT
- **Upstream author:** [TengByte](https://github.com/TengByte)
- **Source:** https://github.com/TengByte/mcpgrade

## Install

```sh
agentstack add mcp-tengbyte-mcpgrade
```

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

## About

# mcpgrade

> **Lighthouse for MCP servers.** Your server can be 100% spec-compliant and still fail agents — vague descriptions, token-bloated schemas, confusable tool names. mcpgrade scores what compliance checkers can't: whether an LLM can actually use your tools.

```bash
npx mcpgrade https://your-server.example.com/mcp   # streamable HTTP
npx mcpgrade --stdio "node ./my-server.js"          # local stdio server
npx mcpgrade --snapshot tools.json                  # saved tools/list output
```

Zero config. No API key. Report in seconds.

## What it checks

| Category | Weight | Examples |
|---|---|---|
| **Descriptions** | 30% | missing/too-short descriptions, undocumented params, placeholder text, duplicate descriptions |
| **Schema design** | 30% | missing types, no `required` array, `additionalProperties: true`, prose-instead-of-enum, deep nesting |
| **Naming** | 15% | confusable names (`get_user` vs `get_users`), generic verbs (`process`), mixed conventions |
| **Token cost** | 15% | catalog total budget, per-tool budget — agents pay your schema on *every* request |
| **Consistency** | 10% | catalog-wide uniformity; with `--probe`, live checks that error messages help the model self-correct |

Every finding comes with a concrete fix. Scores are density-normalized: 3 broken tools out of 3 is an F; 3 out of 30 is a dent.

## Example

```
mcpgrade — agent usability report
target: examples/bad-server.json · 4 tools

  F   37/100

  Descriptions   ░░░░░░░░░░░░░░░░░░░░   0
  Naming         ███████████░░░░░░░░░  55
  Schema design  ███░░░░░░░░░░░░░░░░░  13
  Token cost     ████████████████████ 100
  Consistency    ████████████████████ 100

  findings: 6 errors · 10 warnings · 2 info

  Descriptions
    ✖ D002 [get_user] Description of "get_user" is only 12 chars ("Gets a user.").
      ↳ Expand to at least one full sentence: what it does, when to use it, what it returns.
    ...
```

## CI

```bash
mcpgrade  --json                # machine-readable
mcpgrade  --fail-on error       # exit 1 on errors — gate your PRs
mcpgrade  --disable S008,N001   # tune rules
mcpgrade rules                          # list all rules
```

## Why

I integrate first-party and third-party MCP connectors into a production AI agent for a living. Most MCP servers fail agents in the same ten ways — none of which show up in a spec compliance check. So I wrote the linter I wished server authors had run before shipping.

## mcpgrade vs mcp-lint

Different tools, different questions. [mcp-lint](https://www.npmjs.com/package/mcp-lint) checks whether your tool schemas *parse correctly* across clients (Claude, Cursor, OpenAI strict mode, ...) — syntax-level compatibility. mcpgrade measures whether a model can actually *use* your tools — description quality, naming confusion, token economics, and live LLM tool-selection accuracy. A server can pass mcp-lint cleanly and still score an F here, and vice versa. They compose well: lint for compatibility, grade for usability. Full side-by-side with concrete outputs: [docs/comparison.md](docs/comparison.md).

## Roadmap

- [x] v0.1 — static lint engine, 24 rules, A–F scoring
- [x] v0.2 — `--eval`: LLM-powered live testing — synthetic task generation, blind tool selection, argument validation, refusal accuracy, confusion pairs. Calibrated on real servers ([methodology](docs/eval-calibration.md)); costs ~$0.05–0.2 per server on Haiku. Bring your own `ANTHROPIC_API_KEY`, or any OpenAI-compatible endpoint via `--eval-base-url` (DeepSeek, OpenRouter, ...); `--eval-mock` runs offline. Respects `HTTPS_PROXY`.
- [ ] v0.3 — GitHub Action, dynamic badges, public leaderboard of popular MCP servers

## License

MIT

## Source & license

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

- **Author:** [TengByte](https://github.com/TengByte)
- **Source:** [TengByte/mcpgrade](https://github.com/TengByte/mcpgrade)
- **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-tengbyte-mcpgrade
- Seller: https://agentstack.voostack.com/s/tengbyte
- 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%.