# Lead Green (pypi · leadgreen-mcp)

GPU energy per million output tokens by model, GPU and configuration, with grid carbon by country.

- Trust score: 63/100 (medium)
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-10-23

## Components

- pypi · `leadgreen-mcp`: 63/100 (this document), [markdown](https://verifymcp.io/servers/ai-leadgreen-green-token-index/leadgreen-mcp.md), [page](https://verifymcp.io/servers/ai-leadgreen-green-token-index/leadgreen-mcp)

## Channel facts

- Registry: `pypi`
- Package: `leadgreen-mcp`
- Version: `0.3.1`
- Transport: `stdio`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-10-23.

- **Supply Chain Security**: 50/100
  - Malware scan not yet available for this package.
  - No known CVEs affecting this package version or its production dependencies.
  - Runs hatchling.build at install time, a recognised build step with no custom scripting around it.
  - 1 of 31 dependencies flagged as unhealthy.
- **Provenance & Transparency**: 97/100
  - Source repository is publicly reachable at the declared URL.
  - Cryptographically verified build provenance (signed, bound to katonic-dev/leadgreen-ai).
  - Clear OSI-approved license (Apache-2.0).
  - Actively maintained (last published 2 days ago).
  - Disclosure check failed: no security disclosure policy was found in the source repository.
- **Schema Quality & AI Usability**: 75/100
  - 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).
  - AI-judged instruction clarity (good).
  - Context-footprint check failed: tool/resource definitions use about 1348 tokens (~149/item across 9 items; 8 tools + 1 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 0/100
  - Stability not yet verified: not enough scan history yet (needs a 30-day window).
- **Tool Coverage**: 67/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 0% of tool parameters carry a description.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - We read all 8 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 10 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a current MCP spec version (2026-07-28).

**Unverified: 1 category.** A category scored 0 because we could not verify it: a data source with nothing on this package, evidence we could not reach, or a check we could not run. We only credit what we can confirm.

## Install

### How do I install the Lead Green MCP server?

Lead Green runs locally as a PyPI package, launched with uvx leadgreen-mcp. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

### Claude

```bash
claude mcp add ai-leadgreen-green-token-index -- uvx leadgreen-mcp
```

### Cursor

```json
{
  "mcpServers": {
    "ai-leadgreen-green-token-index": {
      "command": "uvx",
      "args": [
        "leadgreen-mcp"
      ]
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "ai-leadgreen-green-token-index": {
      "command": "uvx",
      "args": [
        "leadgreen-mcp"
      ]
    }
  }
}
```

### Codex

```bash
codex mcp add ai-leadgreen-green-token-index -- uvx leadgreen-mcp
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "ai-leadgreen-green-token-index": {
      "type": "local",
      "command": [
        "uvx",
        "leadgreen-mcp"
      ],
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add ai-leadgreen-green-token-index --command uvx --arg leadgreen-mcp
```

### Hermes

```yaml
mcp_servers:
  ai-leadgreen-green-token-index:
    command: "uvx"
    args: ["leadgreen-mcp"]
```

### Netclaw

```json
{
  "McpServers": {
    "ai-leadgreen-green-token-index": {
      "Transport": "stdio",
      "Command": "uvx",
      "Arguments": [
        "leadgreen-mcp"
      ]
    }
  }
}
```

### Vellum

```bash
assistant mcp add ai-leadgreen-green-token-index -t stdio -c uvx -a leadgreen-mcp
```

### Other

```json
{
  "mcpServers": {
    "ai-leadgreen-green-token-index": {
      "command": "uvx",
      "args": [
        "leadgreen-mcp"
      ]
    }
  }
}
```

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-10-20 (score 63)

First indexed and scored.

## MCP tools (8)

### `list_models` (~51 tokens)

List every model on the Green Tokens index with the GPUs it was measured on.

Returns names, Hugging Face ids, parameter counts and the GPUs available, so
you can pick exact arguments for the other tools.

### `energy_per_million_tokens` (~226 tokens)

GPU energy per million output tokens for a model, from the index.

Args:
    model: model name, slug or Hugging Face id (for example "Qwen 3 32B",
        "qwen-3-32b" or "Qwen/Qwen3-32B").
    gpu: optional, "H100" or "B200". If omitted, every GPU the model was
        measured on is returned.
    itl_deadline_ms: optional latency ceiling in milliseconds. If given, each
        GPU's row is re-selected from every measured configuration: the
        lowest energy whose median inter-token latency is at or under it.
        If omitted, the index rows (the index's own ceiling) are returned.

Each row is the most energy-efficient configuration found for that model on
that GPU while keeping median inter-token latency under the ceiling, on a
text-conversation workload. The response reports the ceiling used.

Input parameters:

- `gpu`
- `itl_deadline_ms`
- `model` (string, required)

### `estimate` (~496 tokens)

Estimate GPU energy, and optionally carbon and energy at the meter, for serving a number of output tokens.

Args:
    model: model name, slug or Hugging Face id.
    output_tokens: how many output tokens will be generated (for example
        50_000_000 for fifty million).
    gpu: "H100" or "B200". If omitted, the most efficient measured GPU is used.
    country: optional country name or ISO 3166 code (or "World") to convert
        the energy to kg CO2e using that grid's annual average intensity.
    running_batch: optional. The average running batch the server will hold:
        how many requests it decodes at once (vLLM num_requests_running). If
        given, the estimate uses the measured configuration nearest to it, on
        the same GPU count as the best row unless num_gpus is set. A small
        running batch can raise energy per token several-fold.
    num_gpus: optional. Use configurations on this many GPUs (for example 2
        for 2 x H100).
    itl_deadline_ms: optional latency ceiling in milliseconds. The lowest-energy
        configuration with median inter-token latency at or under it is used.
        If omitted, the index's own ceiling applies.
    pue: optional power usage effectiveness of the facility, at least 1.0.
    system_power_ratio: optional ratio of whole-server power to GPU power, at
        least 1.0 (a DGX B200 at its 14.3 kW maximum over 8 x 1.0 kW of GPU
        power is about 1.79).
    requests_in_flight: the old name for running_batch, still accepted.

Returns energy in Wh and kWh, the configuration used, and, with a country,
kg CO2e. With pue or system_power_ratio it also returns energy at the meter,
which rests on those assumptions. The measured figures are GPU-only floors;
see the caveat.

Input parameters:

- `country`
- `gpu`
- `itl_deadline_ms`
- `model` (string, required)
- `num_gpus`
- `output_tokens` (number, required)
- `pue`
- `requests_in_flight`
- `running_batch`
- `system_power_ratio`

### `compare_gpus` (~128 tokens)

Compare a model's energy per million output tokens on H100 and B200.

Args:
    model: model name, slug or Hugging Face id.
    itl_deadline_ms: optional latency ceiling in milliseconds. If given, each
        GPU's row is the lowest-energy configuration with median inter-token
        latency at or under it. If omitted, the index rows are compared.

Returns the best row per GPU and the ratio between them. Models measured on
only one GPU return that single row.

Input parameters:

- `itl_deadline_ms`
- `model` (string, required)

### `concurrency_curve` (~117 tokens)

Energy per million output tokens at every measured running batch for a model on a GPU.

Args:
    model: model name, slug or Hugging Face id.
    gpu: "H100" or "B200".

The running batch (avg_running_batch, vLLM num_requests_running) is how many
requests the server decodes at once. Energy per token falls as it grows. Use
this to see where a lightly loaded deployment sits relative to the index.

Input parameters:

- `gpu` (string, required)
- `model` (string, required)

### `grid_intensity` (~102 tokens)

Annual average grid carbon intensity for a country, in g CO2e per kWh.

Args:
    country: country name (common names such as "UK", "US" or "Turkey"
        work), ISO 3166 alpha-3 code, alpha-2 code where the data carries
        it, or "World".

display_name is the short name the site shows; name is the data source's label.

Input parameters:

- `country` (string, required)

### `gpu_hardware` (~93 tokens)

Manufacturer power ceilings (max TDP), memory, and MIG slice profiles for data-centre GPUs.

Args:
    gpu: optional filter such as "H100", "H200", "A100" or "B200". Omit for all.

Whole-system ceilings (for example DGX B200) come with the matching GPU; they
help choose a system_power_ratio for estimate.

Input parameters:

- `gpu`

### `sources` (~26 tokens)

Every source behind the index, with version, retrieval date and licence, plus the API endpoints.

## Diagnostics

Captured diagnostic sections: Provenance, Install scripts, Dependencies. The full working is on the page: https://verifymcp.io/servers/ai-leadgreen-green-token-index/leadgreen-mcp#diagnostics

## Score history

- 2026-10-23: 63
- 2026-10-22: 63
- 2026-10-21: 63
- 2026-10-20: 63

## Common questions

### What is the Lead Green MCP server?

Lead Green is an MCP server listed in the public MCP registry as ai.leadgreen/green-token-index. GPU energy per million output tokens by model, GPU and configuration, with grid carbon by country. This page covers its PyPI package (leadgreen-mcp).

### Is the Lead Green MCP server safe to use?

Lead Green scores 63 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 23 October 2026. Its build provenance is signed and verified. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

### What tools does the Lead Green MCP server expose?

Lead Green exposes 8 tools: list_models, energy_per_million_tokens, estimate, compare_gpus, concurrency_curve, and 3 more. Their descriptions and schemas cost roughly 1,239 tokens of context every time the server is loaded.

### Is the Lead Green MCP server still maintained?

Lead Green is still listed as active in the MCP registry. We last reached this channel on 23 October 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

### What licence is the Lead Green MCP server under?

Lead Green declares the Apache-2.0 licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.

## Links

- PyPI project: https://pypi.org/project/leadgreen-mcp/
- Socket report: https://socket.dev/pypi/package/leadgreen-mcp
- Repository: https://github.com/katonic-dev/leadgreen-ai
- Website: https://leadgreen.ai/mcp/
- Changelog RSS feed: https://verifymcp.io/servers/ai-leadgreen-green-token-index/leadgreen-mcp.xml
- Changelog JSON feed: https://verifymcp.io/servers/ai-leadgreen-green-token-index/leadgreen-mcp.json
- HTML version of this page: https://verifymcp.io/servers/ai-leadgreen-green-token-index/leadgreen-mcp