ContexteTech

io.github.contexte-techPublished by GitHub account contexte-techv0.5.2Updated Oct 24, 2026

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

The publisher's own server: Tech.eu Funding Explorer

VerifiedStreamable HTTPWeb executableKnowledge & MemoryData & AnalyticsAI & ML

Overview

AI-generated overview

ContexteTech lets an assistant search and load AI datasets, prompts and few-shot contexts from its catalogue, fill prompt templates, and estimate model running.

What you can do
Search the catalogue of AI datasets, prompts, few-shot contexts, MCP servers and models, in nine languages, many grounded in official European sources (search_resources, search). Read one resource by short code, author/name or fixed version, returning title, type, licence, language, source, version and page URL (load_resource, fetch). Fill a prompt template with your own variable values and get the ready-to-send text (fill_prompt). Estimate in euros what a resource costs to run with common AI models, from weekly list prices (estimate_cost).
When to use it
Useful when you need AI training or evaluation material such as chat, DPO or agent-trace datasets, prompts or few-shot contexts, and want to find, read and apply them. Also handy for comparing what a prompt, context or dataset would cost across models before committing.
Requirements
Runs as a remote endpoint or as a local process from the PyPI package contexte, started with uvx over stdio. No authentication, environment variables or headers are declared. Network access to the ContexteTech service is needed.
Before you install
Cost estimates are based on weekly list prices and are indicative only, not a quote. Resources carry their own licences, which the assistant reports; check them before reuse. No credentials are requested, but searches and resource loads go to the ContexteTech service.

Installation

In SourceWeft

  1. Open ContexteTech in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Web executable via Streamable HTTP. Remote servers run from the web runtime once configured in a workspace.

Use with an agent

Paste this prompt into Claude Code, Codex, Cursor or another agent — or into SourceWeft chat. The agent reads this server's install guide, shows you its publisher, endpoint and sign-in, and adds it to your client once you agree. Keys never go into a command.

Read https://sourceweft.com/mcp/io.github.contexte-tech%2Fcontexte/install.md and connect the MCP server it describes to my client. Before changing any config, show me its publisher, endpoint and sign-in method and wait for my OK. Never put an API key in a command or in a file I would commit; ask me where it should come from.

Read the install guide the agent follows

Other MCP clients

Add this to your client's mcpServers config.

{
  "mcpServers": {
    "contextetech": {
      "type": "http",
      "url": "https://contextetech.com/mcp"
    }
  }
}

Tools

6

search_resources

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. Use it first when the user needs AI training or evaluation data, a prompt, a context or an AI component, then call load_resource with a returned code. Write the topic in a few words, in English or the content language; common topics are matched across French, English, German and Spanish (e.g. 'marine weather' finds 'météo marine'), and a type word such as 'dataset' or 'prompt' puts that type first. Resources matching every topic come first; weaker matches carry match: partial. Returns up to 15 matches, each with short code, title, type, language, licence, author, rows (datasets), description and page URL; when nothing matches, returns a short message suggesting how to rephrase.

Parameterstypequeryrequiredlanguage

load_resource

Load a resource

Read one ContexteTech resource, usually right after search_resources or when the user gives a code or page URL. Accepts the short code (end of the page URL, e.g. 'jr6t0n'), 'author/name', or 'code#v2' for a fixed version. Always returns title, type, licence, language, source, version and page URL; plus, for a dataset, the total number of rows, the first rows (default 10, max 50); for a prompt, the template and its {{variables}} (then call fill_prompt); for a context, the system prompt, knowledge and examples. The result ends with a Source line (resource, author, original data source, publisher, licence): citing it with its links is required. Fails with an error if the code does not exist or the resource is private.

Parameterscoderequiredrows

fill_prompt

Fill a prompt

Fill a ContexteTech prompt template and return the ready-to-send text, nothing else. Use it when the user wants a prompt applied to their own case; call load_resource first if you need the template or the exact variable names. 'variables' maps each {{name}} of the template to its text value; extra keys are ignored. Fails with an error if the code is unknown, if the resource is not a prompt, or if a template variable is missing (the error lists the missing names).

Parameterscoderequiredvariablesrequired

estimate_cost

Estimate the cost

Estimate in euros what a ContexteTech resource costs to run with common AI models, from the week's list prices. Use it when the user asks about cost, budget or the cheapest model. For a prompt or context: input and output tokens, cost per call for each model and batch discount; for a dataset: cost of one pass over all rows and a fine-tuning estimate on rented GPUs (hours and offers); for a model: memory (VRAM) needed and GPU offers that fit. Returns available: false with a note when no estimate exists for that type.

Parameterscoderequired

fetch

Fetch (connector format)

Fetch the full content of a ContexteTech resource by the id returned by search.

Parametersidrequired

Version history

2
  1. v0.5.2LatestOct 15, 2026
  2. v0.4.2Oct 13, 2026

Score

75% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 daysRequired25 pts
  • Auth declaredRequired10 pts
  • Tools listedRequired15 pts
  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts

    Declare a GitHub repository with a README, or serve resource_documentation in the OAuth protected-resource metadata.

  • License10 pts

    Declare a license in the repository or the registry entry.

Other Tech integrations

Tech.eu Funding Explorer

eu.tech.fundingOfficial publisher

Lets an assistant search European tech funding rounds, companies, investors and exits, with EUR-normalized, source-linked figures.

Streamable HTTPWeb executable
Finance8 toolsOct 24, 2026

ScorpTech x402 API

com.it.scorptechOfficial publisher

ScorpTech x402 API's hosted MCP server, published by scorptech.it.com; no sign-in required; Streamable HTTP; 200 tools.

Streamable HTTPWeb executable
200+ toolsOct 25, 2026

Website Tech Stack Detector

Published by GitHub account prometheus-maker

Apify-hosted MCP server that identifies the technologies behind websites — CMS, frameworks, analytics, CDN, hosting — from a list of URLs.

Streamable HTTPWeb executableAuth
Web Search & ScrapingCredential requiredNov 7, 2026

Website Tech Stack Lookup

Published by GitHub account catalyst-labs-dev

Domains in, tech stack out: 7,600+ technologies, versions, DNS/email providers. $0.003/site.

Streamable HTTPWeb executableAuth
Credential requiredNov 3, 2026

Data Lantern Website Technology Detector

Published by GitHub account xiezhengyang1990-beep

Remote Apify-hosted MCP server that lets an assistant run batch website technology detection with supporting evidence.

Streamable HTTPWeb executableAuth
Web Search & ScrapingCredential requiredOct 31, 2026