# ContexteTech (pypi · contexte)

Search and load AI datasets, prompts and few-shot contexts from the ContexteTech catalogue.

- Trust score: 65/100 (medium)
- Change this week: +15
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-10-22

## Components

- remote · `contextetech.com`: 73/100, [markdown](https://verifymcp.io/servers/contexte-tech-contexte/contextetech.md), [page](https://verifymcp.io/servers/contexte-tech-contexte/contextetech)
- pypi · `contexte`: 65/100 (this document), [markdown](https://verifymcp.io/servers/contexte-tech-contexte/contexte.md), [page](https://verifymcp.io/servers/contexte-tech-contexte/contexte)

## Channel facts

- Registry: `pypi`
- Package: `contexte`
- Version: `0.5.1`
- 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 2026-10-22.

- **Supply Chain Security**: 100/100
  - No malware found by supply-chain analysis.
  - No known CVEs affecting this package version or its production dependencies.
  - Runs setuptools.build_meta at install time, a recognised build step with no custom scripting around it.
  - No production dependencies, so there is no dependency health to assess.
- **Provenance & Transparency**: 19/100
  - Repository check failed: no source repository is declared.
  - Provenance check failed: no build-provenance attestation is published.
  - Clear OSI-approved license (MIT).
  - Actively maintained (last published 6 days ago).
  - Security-disclosure policy not yet verified: we couldn't inspect the source repository.
- **Schema Quality & AI Usability**: 72/100
  - AI-judged instruction clarity (good).
  - Tool/resource definitions use about 585 tokens (~117/item across 5 items; 5 tools + 0 resources), lean.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 0/100
  - Stability check failed: the tool surface changed between 0.4.2 and 0.5.1: 3 tool removals, 0 breaking changes, 5 additions.
- **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 5 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 6 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 ContexteTech MCP server?

ContexteTech runs locally as a PyPI package, launched with uvx contexte. 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 contexte-tech-contexte -- uvx contexte
```

### Cursor

```json
{
  "mcpServers": {
    "contexte-tech-contexte": {
      "command": "uvx",
      "args": [
        "contexte"
      ]
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "contexte-tech-contexte": {
      "command": "uvx",
      "args": [
        "contexte"
      ]
    }
  }
}
```

### Codex

```bash
codex mcp add contexte-tech-contexte -- uvx contexte
```

### opencode

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

### OpenClaw

```bash
openclaw mcp add contexte-tech-contexte --command uvx --arg contexte
```

### Hermes

```yaml
mcp_servers:
  contexte-tech-contexte:
    command: "uvx"
    args: ["contexte"]
```

### Netclaw

```json
{
  "McpServers": {
    "contexte-tech-contexte": {
      "Transport": "stdio",
      "Command": "uvx",
      "Arguments": [
        "contexte"
      ]
    }
  }
}
```

### Vellum

```bash
assistant mcp add contexte-tech-contexte -t stdio -c uvx -a contexte
```

### Other

```json
{
  "mcpServers": {
    "contexte-tech-contexte": {
      "command": "uvx",
      "args": [
        "contexte"
      ]
    }
  }
}
```

## 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.

### 2026-10-19 (score 65, 0)

- [functional] Package version: 0.4.2 → 0.5.1

### 2026-10-16 (score 65, +15)

- [security improvement] Malware scan: unverified → pass

### 2026-10-15 (score 50, −15)

- [security regression] Stability: unverified → fail
- [security regression] Malware scan: pass → unverified
- [security regression] Tool safety: 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] Schema quality: 380 → 585
- [functional regression] Capabilities: pass → unverified
- [functional regression] Tool coverage: 100 → unverified
- [functional regression] Schema quality: pass → fail
- [functional] Package version: 0.4.2 → 0.5.1
- [functional] Package version: 0.4.2 → 0.5.0

### 2026-10-14 (score 65, +31)

- [security improvement] Injection markers: 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] MCP protocol: unverified → pass
- [functional improvement] Tool coverage: unverified → 100
- [functional] First check of Tool coverage: 100
- [functional] First check of Schema quality: good
- [functional] First check of Schema quality: pass
- [functional] First check of Destructive annotations: pass
- [functional] First check of Schema quality: fail

### 2026-10-13 (score 34)

First indexed and scored.

## MCP tools (5)

### `search_resources` (~161 tokens)

Search the ContexteTech catalogue

Search the ContexteTech catalogue of AI building blocks: fine-tuning and evaluation datasets (chat, DPO, agent traces), prompts, few-shot contexts, MCP servers, models and more, many grounded in official European sources, in 9 languages. Returns for each match: short code, title, type, language, licence, number of rows (datasets), description and page URL.

Input parameters:

- `language` (string): Optional content language: fr, en, es, de, it, nl, pt, sv, pl
- `query` (string, required): Search words, e.g. 'customs code' or 'GDPR'
- `type` (string): Optional type: dataset, prompt, context, tool, model, agent, eval, rag…

### `load_resource` (~98 tokens)

Load a resource

Load one ContexteTech resource by short code (e.g. 'jr6t0n') or 'author/name'. Dataset: description, licence and the first rows; prompt: template and variables; context: system prompt and examples.

Input parameters:

- `code` (string, required): Short code or author/name; 'code#v2' for a fixed version
- `rows` (integer): Dataset rows to return (default 10, max 50)

### `fill_prompt` (~56 tokens)

Fill a prompt

Fill a ContexteTech prompt template ({{variable}} placeholders) and return the ready-to-use prompt.

Input parameters:

- `code` (string, required): Short code or author/name of the prompt
- `variables` (object, required): Values for each {{variable}}

### `download_dataset` (~121 tokens)

Download a dataset to a file

Save a whole ContexteTech dataset to a local file, ready for fine-tuning or evaluation. Formats: jsonl (original), messages (OpenAI chat), sharegpt, alpaca, csv. Never overwrites an existing file.

Input parameters:

- `code` (string, required): Short code or author/name of the dataset; 'code#v2' for a fixed version
- `format` (string): File format (default: jsonl)
- `path` (string): File or folder to write to (default: current folder, file named after the dataset)

### `estimate_cost` (~66 tokens)

Estimate the cost

Estimated cost of a ContexteTech resource with common AI models (euros): input and output tokens, cost per call or per pass, batch discount, cheapest model; for a dataset, fine-tuning on a rented GPU.

Input parameters:

- `code` (string, required): Short code or author/name

## Diagnostics

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

## Score history

- 2026-10-22: 65
- 2026-10-21: 65
- 2026-10-20: 65
- 2026-10-19: 65
- 2026-10-18: 65
- 2026-10-17: 65
- 2026-10-16: 65
- 2026-10-15: 50
- 2026-10-14: 65
- 2026-10-13: 34

## Common questions

### What is the ContexteTech MCP server?

ContexteTech is an MCP server listed in the public MCP registry as io.github.contexte-tech/contexte. Search and load AI datasets, prompts and few-shot contexts from the ContexteTech catalogue. This page covers its PyPI package (contexte).

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

ContexteTech scores 65 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 22 October 2026. 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 ContexteTech MCP server expose?

ContexteTech exposes 5 tools: search_resources, load_resource, fill_prompt, download_dataset, estimate_cost. Their descriptions and schemas cost roughly 502 tokens of context every time the server is loaded.

### Is the ContexteTech MCP server still maintained?

ContexteTech 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 ContexteTech MCP server under?

ContexteTech 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/contexte/
- Socket report: https://socket.dev/pypi/package/contexte
- Website: https://contextetech.com/en/
- Changelog RSS feed: https://verifymcp.io/servers/contexte-tech-contexte/contexte.xml
- Changelog JSON feed: https://verifymcp.io/servers/contexte-tech-contexte/contexte.json
- HTML version of this page: https://verifymcp.io/servers/contexte-tech-contexte/contexte