contexte
OfficialServer Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| search_resourcesA | 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. |
| load_resourceA | 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. |
| fill_promptB | Fill a ContexteTech prompt template ({{variable}} placeholders) and return the ready-to-use prompt. |
| download_datasetA | 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. |
| estimate_costA | 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. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 5 tools
Each tool targets a clearly distinct action: search_resources finds resources, load_resource inspects one, fill_prompt renders prompt templates, download_dataset persists full datasets, and estimate_cost computes pricing. Boundaries are sharp — even the superficially similar load_resource vs download_dataset differ (preview/first rows vs full file export), so an agent can select confidently.
All five names follow a strict snake_case verb_noun pattern (search_resources, load_resource, fill_prompt, download_dataset, estimate_cost). The only variation is plural vs singular nouns, which reflects the actual cardinality semantics rather than an inconsistency.
Five tools is well-scoped for a resource-catalogue server covering discovery, inspection, prompt rendering, dataset export and cost estimation. Every tool earns its place with no redundancy.
The surface covers the core catalogue lifecycle: discover, inspect, use (fill prompts), export datasets and estimate cost. Minor gaps exist — no explicit browse/list-by-type or metadata filtering beyond free search, and no way to fetch a model or MCP server artifact directly — but agents can work around these via search.