# ~alter mcp-ollama (npm · @truealter/mcp-ollama)

Wraps local Ollama models so bulk generation runs on your own hardware, not a paid API.

- Trust score: 88/100 (high trust)
- Change this week: +3
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-09-20

## Components

- npm · `@truealter/mcp-ollama`: 88/100 (this document), [markdown](https://verifymcp.io/servers/true-alter-mcp-ollama/truealter-mcp-ollama.md), [page](https://verifymcp.io/servers/true-alter-mcp-ollama/truealter-mcp-ollama)

## Channel facts

- Registry: `npm`
- Package: `@truealter/mcp-ollama`
- Version: `0.2.1`
- 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 2026-09-20.

- **Supply Chain Security**: 98/100
  - No malware found by supply-chain analysis.
  - No known CVEs affecting this package version or its production dependencies.
  - No install/post-install scripts declared.
  - 31 of 95 dependencies flagged as unhealthy.
- **Provenance & Transparency**: 100/100
  - Source repository is publicly reachable at the declared URL.
  - Cryptographically verified build provenance (signed, bound to true-alter/mcp-ollama).
  - Clear OSI-approved license (Apache-2.0).
  - Actively maintained (last published 16 days ago).
  - Publishes a security disclosure policy (SECURITY.md).
- **Schema Quality & AI Usability**: 72/100
  - AI-judged instruction clarity (excellent).
  - Context-footprint check failed: tool/resource definitions use about 1711 tokens (~171/item across 10 items; 10 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 57/100
  - Stability observed for 17 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 100/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 100% 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 10 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 supported MCP spec version (2025-11-25); the latest is 2026-07-28.

## Install

### How do I install the ~alter mcp-ollama server?

\~alter mcp-ollama runs locally as an npm package, launched with npx -y @truealter/mcp-ollama. 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 true-alter-mcp-ollama -- npx -y @truealter/mcp-ollama
```

### Cursor

```json
{
  "mcpServers": {
    "true-alter-mcp-ollama": {
      "command": "npx",
      "args": [
        "-y",
        "@truealter/mcp-ollama"
      ]
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "true-alter-mcp-ollama": {
      "command": "npx",
      "args": [
        "-y",
        "@truealter/mcp-ollama"
      ]
    }
  }
}
```

### Codex

```bash
codex mcp add true-alter-mcp-ollama -- npx -y @truealter/mcp-ollama
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "true-alter-mcp-ollama": {
      "type": "local",
      "command": [
        "npx",
        "-y",
        "@truealter/mcp-ollama"
      ],
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add true-alter-mcp-ollama --command npx --arg -y --arg @truealter/mcp-ollama
```

### Hermes

```yaml
mcp_servers:
  true-alter-mcp-ollama:
    command: "npx"
    args: ["-y", "@truealter/mcp-ollama"]
```

### Netclaw

```json
{
  "McpServers": {
    "true-alter-mcp-ollama": {
      "Transport": "stdio",
      "Command": "npx",
      "Arguments": [
        "-y",
        "@truealter/mcp-ollama"
      ]
    }
  }
}
```

### Vellum

```bash
assistant mcp add true-alter-mcp-ollama -t stdio -c npx -a -y @truealter/mcp-ollama
```

### Other

```json
{
  "mcpServers": {
    "true-alter-mcp-ollama": {
      "command": "npx",
      "args": [
        "-y",
        "@truealter/mcp-ollama"
      ]
    }
  }
}
```

## 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.

### 2026-09-19 (score 88, +1)

No change was recorded against any check on this day. Stability & Change Management went from 50 to 53. That category is still filling its 30-day observation window: 15 days of observed history at the previous scan, 16 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-17 (score 87, +1)

No change was recorded against any check on this day. Stability & Change Management went from 43 to 47. That category is still filling its 30-day observation window: 13 days of observed history at the previous scan, 14 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-14 (score 86, +1)

No change was recorded against any check on this day. Stability & Change Management went from 33 to 37. That category is still filling its 30-day observation window: 10 days of observed history at the previous scan, 11 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-12 (score 85, +1)

No change was recorded against any check on this day. Stability & Change Management went from 27 to 30. That category is still filling its 30-day observation window: 8 days of observed history at the previous scan, 9 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-10 (score 84, +4)

- [functional improvement] Stability: unverified → 0.23

### 2026-09-03 (score 80)

First indexed and scored.

## MCP tools (10)

### `local_generate` (~193 tokens)

General-purpose local LLM generation. Delegates work to a local Ollama model
to save tokens. Use this when the task is bulk text processing that doesn't
require Opus-level reasoning: summarising documents, explaining code for docs,
generating boilerplate, reformatting content, translating, etc.

The local model (default: hermes3:8b) runs on the user's hardware - zero
API cost, ~40 tok/s on a decent GPU.

Input parameters:

- `max_tokens` (number): Max tokens to generate (default: 2048)
- `model` (string): Ollama model to use (default: hermes3:8b)
- `prompt` (string, required): The prompt / task for the local model
- `system` (string): System prompt to set context/role (optional)
- `temperature` (number): Sampling temperature 0-2 (default: 0.3)

### `local_summarize` (~175 tokens)

Summarise long text locally. Use this instead of having Opus process large
blocks of text when you only need a summary. Feed in file contents, docs,
logs, or any bulk text and get a concise summary back.

Particularly valuable for: large file contents, documentation, log output,
meeting notes, long git diffs, error traces.

Input parameters:

- `content` (string, required): The text to summarise
- `focus` (string): What to focus on in the summary (e.g., 'security issues', 'API changes', 'key decisions')
- `format` (string): Output format (default: bullets)
- `max_tokens` (number): Max tokens to generate (default: 1024)
- `model` (string): Ollama model to use (default: hermes3:8b)

### `local_analyze` (~164 tokens)

Extract structured information from text locally. Use this for classification,
entity extraction, tagging, pattern recognition, or any task that transforms
unstructured text into structured output.

Good for: categorising issues, extracting names/dates/amounts, tagging content,
parsing semi-structured data, sentiment analysis.

Input parameters:

- `content` (string, required): The text to analyse
- `model` (string): Ollama model to use (default: hermes3:8b)
- `output_format` (string): Desired output structure (e.g., 'JSON array', 'markdown table', 'key: value pairs')
- `task` (string, required): What to extract or analyse (e.g., 'extract all API endpoints mentioned', 'classify the sentiment', 'list all named entities')

### `local_draft` (~156 tokens)

Draft text locally - commit messages, PR descriptions, docstrings, changelog
entries, documentation sections, or any formulaic text that follows a template
or convention. Saves Opus tokens on boilerplate generation.

Input parameters:

- `context` (string, required): The context/input the draft should be based on (e.g., diff output, function code, change description)
- `model` (string): Ollama model to use (default: hermes3:8b)
- `style` (string): Style guide or conventions to follow (e.g., 'imperative mood, max 72 chars subject line')
- `task` (string, required): What to draft (e.g., 'commit message for these changes', 'docstring for this function')

### `local_code` (~274 tokens)

Code-aware local generation. Claude reads source code with Read/Grep (free),
then delegates the TEXT GENERATION to local - docstrings, test stubs,
explanations, type annotations, inline comments, or review feedback.

This is the primary tool for reducing API token usage on code tasks.
Claude orchestrates (decides what code to read, what task to perform),
but the actual generation happens locally at zero API cost.

Accepts up to ~12K tokens of code context (16K model context minus overhead).
For larger contexts, break into focused chunks (one function, one class).

Input parameters:

- `code` (string, required): Source code to work with - a function, class, module, or diff
- `context` (string): Additional context: file path, project conventions, what the function is used for, etc.
- `language` (string, required): Programming language (e.g., 'python', 'typescript')
- `model` (string): Ollama model to use (default: hermes3:8b)
- `task` (string, required): What to generate: docstring (generate docstring), test (generate test stub), explain (explain the code), review (style/pattern review - NOT security), types (add type annotations), comments (add inli…

### `local_diff` (~165 tokens)

Analyse a git diff locally. Use this for generating commit messages,
PR descriptions, changelog entries, or understanding what changed in a diff.
Claude runs `git diff` (free), passes the output here for text generation.

Particularly valuable for large diffs that would consume many API tokens
if processed by Opus/Sonnet directly.

Input parameters:

- `diff` (string, required): The git diff output
- `model` (string): Ollama model to use (default: hermes3:8b)
- `style` (string): Style conventions (e.g., 'imperative mood, 72 char subject')
- `task` (string, required): What to generate: commit-message, pr-description, changelog (categorised entries), summary (what changed), impact (what might break)

### `local_transform` (~168 tokens)

Perform mechanical code transformations locally. These are pattern-based
transforms that don't require architectural understanding - the kind of
work that burns API tokens for no good reason.

Use this for: converting between formats, renaming patterns, migrating
syntax, generating boilerplate from examples, etc.

Input parameters:

- `input` (string, required): The input code or text to transform
- `language` (string): Target programming language
- `model` (string): Ollama model to use (default: hermes3:8b)
- `transform` (string, required): What transformation to apply (e.g., 'convert class component to functional React component', 'convert these SQL queries to SQLAlchemy ORM', 'rename all instances of oldName to newName and update refe…

### `local_models` (~33 tokens)

List all models available in the local Ollama instance. Use this to check
what models are loaded and available for delegation.

### `local_pull` (~126 tokens)

Pull/download a model into Ollama from the registry, or import a local GGUF
file. Use this to make additional models available for delegation.

For GGUF files, create an Ollama Modelfile first, then use 'ollama create'.
This tool handles registry pulls (e.g., 'qwen2.5:14b', 'deepseek-r1:8b').

Input parameters:

- `model` (string, required): Model to pull (e.g., 'qwen2.5:14b', 'mistral-nemo', 'deepseek-r1:8b')

### `local_vision` (~257 tokens)

Have a local vision model SEE a rendered image (screenshot of a UI) and report
what is literally on screen - for zero API cost. local_analyze is TEXT-ONLY;
this is the multimodal path.

It REPORTS (is the main content populated or blank/error, what regions exist,
any illegible/clipped text, what the eye lands on first). It does NOT rank
severity, judge on-brand, or greenlight a change - a local vision model reads
pixels well but ranks badly, so keep the judgment on the calling model.

Modes: 'see' (full structural report), 'emptystate' (populated-vs-degraded data
check), 'legibility' (readability faults). Feed near-full-resolution PNGs;
downscaling below ~1280px wide makes the model hallucinate data presence.

Input parameters:

- `context` (string): One line: what this surface is meant to be
- `images` (array, required): Absolute path(s) to rendered PNG/JPG screenshot file(s) to look at
- `mode` (string): Reporting rubric (default: see)
- `model` (string): Vision model to use (default: qwen2.5vl:7b)

## Diagnostics

Captured diagnostic sections: Provenance, Dependencies. The full working is on the page: https://verifymcp.io/servers/true-alter-mcp-ollama/truealter-mcp-ollama#diagnostics

## Score history

- 2026-09-20: 88
- 2026-09-19: 88
- 2026-09-18: 87
- 2026-09-17: 87
- 2026-09-16: 86
- 2026-09-15: 86
- 2026-09-14: 86
- 2026-09-13: 85
- 2026-09-12: 85
- 2026-09-11: 84
- 2026-09-10: 84
- 2026-09-09: 80
- 2026-09-08: 80
- 2026-09-07: 80
- 2026-09-06: 80
- 2026-09-05: 80
- 2026-09-04: 80
- 2026-09-03: 80

## Common questions

### What is the ~alter mcp-ollama server?

\~alter mcp-ollama is listed in the public MCP registry as io.github.true-alter/mcp-ollama. Wraps local Ollama models so bulk generation runs on your own hardware, not a paid API. This page covers its npm package (@truealter/mcp-ollama).

### Is the ~alter mcp-ollama server safe to use?

\~alter mcp-ollama scores 88 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 20 September 2026. It declares no install or post-install scripts. 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 ~alter mcp-ollama server expose?

\~alter mcp-ollama exposes 10 tools: local_generate, local_summarize, local_analyze, local_draft, local_code, and 5 more. Their descriptions and schemas cost roughly 1,711 tokens of context every time the server is loaded.

### Is the ~alter mcp-ollama server still maintained?

\~alter mcp-ollama is still listed as active in the MCP registry. We last reached this channel on 20 September 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 ~alter mcp-ollama server under?

\~alter mcp-ollama 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

- npm package: https://www.npmjs.com/package/@truealter/mcp-ollama
- Socket report: https://socket.dev/npm/package/@truealter/mcp-ollama
- Repository: https://github.com/true-alter/mcp-ollama
- Changelog RSS feed: https://verifymcp.io/servers/true-alter-mcp-ollama/truealter-mcp-ollama.xml
- Changelog JSON feed: https://verifymcp.io/servers/true-alter-mcp-ollama/truealter-mcp-ollama.json
- HTML version of this page: https://verifymcp.io/servers/true-alter-mcp-ollama/truealter-mcp-ollama