# glin (pypi · glin-ml)

Exactly explainable classifiers for agents: train, tune, predict, explain on CSV or Excel.

- Trust score: 65/100 (medium)
- Change this week: +31
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-10-22

## Components

- pypi · `glin-ml`: 65/100 (this document), [markdown](https://verifymcp.io/servers/akashchatterjee-glin/glin-ml.md), [page](https://verifymcp.io/servers/akashchatterjee-glin/glin-ml)

## Channel facts

- Registry: `pypi`
- Package: `glin-ml`
- Version: `0.1.5`
- 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 2026-10-22.

- **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 42 dependencies flagged as unhealthy.
- **Provenance & Transparency**: 97/100
  - Source repository is publicly reachable at the declared URL.
  - Cryptographically verified build provenance (signed, bound to AkashChatterjee/glin).
  - Clear OSI-approved license (MIT).
  - Actively maintained (last published 3 days ago).
  - Disclosure check failed: no security disclosure policy was found in the source repository.
- **Schema Quality & AI Usability**: 70/100
  - 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 1858 tokens (~265/item across 7 items; 7 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 17/100
  - Stability observed for 5 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 71/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 0% of tool parameters carry a description.
  - Structured output schemas are declared (100% of tools); any adoption earns full credit.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - All 1 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation.
  - An AI judge read all 7 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).

## Install

### How do I install the glin MCP server?

glin runs locally as a PyPI package, launched with uvx glin-ml. 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 akashchatterjee-glin -- uvx glin-ml
```

### Cursor

```json
{
  "mcpServers": {
    "akashchatterjee-glin": {
      "command": "uvx",
      "args": [
        "glin-ml"
      ]
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "akashchatterjee-glin": {
      "command": "uvx",
      "args": [
        "glin-ml"
      ]
    }
  }
}
```

### Codex

```bash
codex mcp add akashchatterjee-glin -- uvx glin-ml
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "akashchatterjee-glin": {
      "type": "local",
      "command": [
        "uvx",
        "glin-ml"
      ],
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add akashchatterjee-glin --command uvx --arg glin-ml
```

### Hermes

```yaml
mcp_servers:
  akashchatterjee-glin:
    command: "uvx"
    args: ["glin-ml"]
```

### Netclaw

```json
{
  "McpServers": {
    "akashchatterjee-glin": {
      "Transport": "stdio",
      "Command": "uvx",
      "Arguments": [
        "glin-ml"
      ]
    }
  }
}
```

### Vellum

```bash
assistant mcp add akashchatterjee-glin -t stdio -c uvx -a glin-ml
```

### Other

```json
{
  "mcpServers": {
    "akashchatterjee-glin": {
      "command": "uvx",
      "args": [
        "glin-ml"
      ]
    }
  }
}
```

## 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.

### 2026-10-21 (score 65, +1)

No change was recorded against any check on this day. Stability & Change Management went from 10 to 13. That category is still filling its 30-day observation window: 3 days of observed history at the previous scan, 4 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-19 (score 64, −14)

- [security regression] Malware scan: pass → unverified

### 2026-10-18 (score 78, 0)

- [security regression] Tool safety: pass → unverified
- [security regression] Malware scan: pass → unverified
- [security] Stability: Stability not yet verified: we do not have a sandbox capture of the MCP schema this version of the package serves yet.
- [functional regression] Capabilities: pass → unverified
- [functional regression] Tool coverage: 100 → unverified
- [functional regression] Schema quality: 100 → unverified
- [functional improvement] Schema quality: 299 → 265
- [functional improvement] Stability: unverified → 0.03
- [functional] Destructive annotations: pass → 100
- [functional] Package version: 0.1.4 → 0.1.5

### 2026-10-17 (score 78, +44)

- [security improvement] Injection markers: unverified → pass
- [security improvement] Malware scan: unverified → pass
- [security] First check of Judged manipulation: pass
- [security] Stability: Stability not yet verified: not enough scan history yet (needs a 30-day window).
- [functional improvement] Tool coverage: unverified → 100
- [functional improvement] MCP protocol: unverified → pass
- [functional improvement] Schema quality: unverified → 100
- [functional] First check of Tool coverage: 0
- [functional] First check of Schema quality: fail
- [functional] First check of Destructive annotations: pass
- [functional] First check of Schema quality: fail
- [functional] First check of Schema quality: good
- [functional] First check of Tool coverage: 100

### 2026-10-14 (score 34, −15)

- [security regression] Malware scan: pass → unverified
- [security] Stability: Stability not yet verified: this package could not be installed in a clean environment, so we have no schema to compare.
- [security] Tool safety: Tool safety not yet verified: this package could not be installed in a clean environment, so we have no tool text to scan.
- [functional] Schema quality: Schema quality not yet verified: this package could not be installed in a clean environment, so we have no schema to assess.
- [functional] Capabilities: Protocol version not yet verified: this package could not be installed in a clean environment, so we never saw its MCP handshake.
- [functional] Tool coverage: Tool coverage not yet verified: this package could not be installed in a clean environment, so we have no tool definitions to assess.

### 2026-10-13 (score 49, +26)

- [security improvement] Malware scan: unverified → pass
- [security improvement] Known CVEs: unverified → pass
- [functional improvement] Dependency health: unverified → 0.99

### 2026-10-12 (score 23)

First indexed and scored.

## MCP tools (7)

### `list_models` (~19 tokens)

List all trained glin models available on this machine.

Output parameters:

- `result` (array)

### `inspect_model` (~30 tokens)

Return feature names, types, and target classes for a trained model.

Input parameters:

- `model_name` (string, required)

### `predict` (~249 tokens)

Predicted class and probabilities, plus the full glassbox audit:
\`base_logit` (the intercept), every contributing feature's exact score
(sorted by magnitude), and an additivity check verifying the scores sum
to the model's own predicted probabilities (`reconstructed_probability`
vs `model_probability`, both keyed by class name). For binary targets
scores and `base_logit` are log-odds of `score_class` (`target_classes[1]`;
positive pushes toward it, negative toward the other class); multiclass reports
per-class scores and a per-class `base_logit`. `warnings` names inputs the model never
saw (unseen categories, numerics or dates outside the training range,
unparseable numbers or dates); treat the prediction as less reliable when present.
\`missing_features` lists absent inputs, which are valid but worth
mentioning. Pass a date column as its raw value (e.g. "2024-03-06");
glin derives the `<col>__<part>` terms shown in `contributions` itself.

Input parameters:

- `features` (object, required)
- `model_name` (string, required)
- `top_n` (integer)

### `explain_model` (~146 tokens)

Global view of what a trained model learned, exact rather than
sampled from example predictions: every feature ranked by its mean
absolute contribution to the log-odds (`features`, with main-effect
vs interaction split), the top terms including pairwise interactions
(`terms`, each with its share of the total), and, for binary targets,
a `shape` per main effect showing which categories or value ranges
push the prediction up or down. Use this to answer "what drives this
model" instead of running `predict` on a handful of rows.

Input parameters:

- `include_shapes` (boolean)
- `model_name` (string, required)
- `top_n` (integer)

### `list_hyperparameters` (~67 tokens)

Every EBM training hyperparameter `train_model` accepts in its
\`hyperparameters` argument: name, type, default, allowed range, and
what raising/lowering it does. Fetch the `tune_model_hyperparameters`
prompt for a search strategy built on these.

Output parameters:

- `result` (array)

### `train_model` (~1285 tokens)

Train an EBM classifier from a CSV or Excel file and save it as model_name. This
is also how to retrain an existing model: pass overwrite=True to
replace it with a freshly trained model (e.g. on updated data) --
otherwise a pre-existing model_name is rejected so it isn't silently
clobbered.

Pass exactly one of:
\- csv_path: a .csv, .xlsx or .xls file inside a directory this
  server allows (it does the reading itself). Always prefer this --
  it works for large files (up to the server's size limit, 200 MB
  by default) without the calling agent ever
  having to read or reproduce the file's contents itself. Excel
  files need the optional `glin-ml[excel]` install.
\- csv_content: the complete raw CSV text (header row + data rows).
  Only use this when there's no file on disk to point at, e.g.
  data pasted into the chat or assembled in memory. Do not use this for large files --
  having an agent inline tens of thousands of rows as a tool-call
  argument is slow, burns enormous context, and risks truncation.
  Prefer writing the data to a file the server can see (csv_path)
  whenever that's possible instead.

Excel only (csv_path ending in .xlsx/.xls): `sheet` picks the sheet
by name or 1-based position (required when the workbook has several
sheets). The header row is auto-detected, skipping title/banner rows
and trailing footnote rows (mostly empty rows whose text starts with
Source, Note, *, or is a long sentence; `warnings` names the dropped
rows); if that is ambiguous the error says so. For
multi-row or merged headers set `header_rows` to the 1-based sheet
row numbers as shown in Excel: 4, "3-4" or [3, 4]; they are
flattened into unique column names and data starts below them. The
result reports the `sheet` and `header_rows` actually used.

Either way, this tool does no cleanup of its own beyond what
EBMTabularPreprocessor already does automatically (coercing dirty
numeric formatting such as currency symbols, thousands separators and
trailing % -- percentages sta…

Input parameters:

- `csv_content`
- `csv_path`
- `header_rows`
- `holdout_fraction` (number)
- `holdout_group_column`
- `hyperparameters`
- `model_name` (string, required)
- `overwrite` (boolean)
- `sheet`
- `suppression_codes`
- `target_column` (string, required)

### `delete_model` (~62 tokens)

Permanently delete a trained model and its saved files. This cannot
be undone; confirm with the user before you call it. To replace a
model with a new one, call `train_model` with overwrite=True instead.

Input parameters:

- `model_name` (string, required)

## Diagnostics

Captured diagnostic sections: Provenance, Install scripts, Dependencies. The full working is on the page: https://verifymcp.io/servers/akashchatterjee-glin/glin-ml#diagnostics

## Score history

- 2026-10-22: 65
- 2026-10-21: 65
- 2026-10-20: 64
- 2026-10-19: 64
- 2026-10-18: 78
- 2026-10-17: 78
- 2026-10-16: 34
- 2026-10-15: 34
- 2026-10-14: 34
- 2026-10-13: 49
- 2026-10-12: 23

## Common questions

### What is the glin MCP server?

glin is an MCP server listed in the public MCP registry as io.github.AkashChatterjee/glin. Exactly explainable classifiers for agents: train, tune, predict, explain on CSV or Excel. This page covers its PyPI package (glin-ml).

### Is the glin MCP server safe to use?

glin scores 65 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 22 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 glin MCP server expose?

glin exposes 7 tools: list_models, inspect_model, predict, explain_model, list_hyperparameters, and 2 more. Their descriptions and schemas cost roughly 1,858 tokens of context every time the server is loaded.

### Is the glin MCP server still maintained?

glin is still listed as active in the MCP registry. We last reached this channel on 22 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 glin MCP server under?

glin declares the MIT 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/glin-ml/
- Socket report: https://socket.dev/pypi/package/glin-ml
- Repository: https://github.com/AkashChatterjee/glin
- Changelog RSS feed: https://verifymcp.io/servers/akashchatterjee-glin/glin-ml.xml
- Changelog JSON feed: https://verifymcp.io/servers/akashchatterjee-glin/glin-ml.json
- HTML version of this page: https://verifymcp.io/servers/akashchatterjee-glin/glin-ml