Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
IMPRESSO_EMAILNoYour impresso account email.
IMPRESSO_PASSWORDNoYour impresso account password.
IMPRESSO_API_TOKENNoA temporary API token from impresso (expires in hours).
IMPRESSO_CACHE_DIRNoDirectory for cache and token. Overrides --cache-dir.
IMPRESSO_MIN_REQUEST_INTERVALNoMinimum time between requests in seconds. Default 1.

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

CapabilityDetails
tools
{
  "listChanged": true
}
logging
{}
prompts
{
  "listChanged": false
}
resources
{
  "subscribe": false,
  "listChanged": false
}
extensions
{
  "io.modelcontextprotocol/ui": {}
}
experimental
{}

Tools

Functions exposed to the LLM to take actions

NameDescription
search_impressoA

Search the Swiss and Luxembourgish historical press full text.

impresso covers 1738-2018 in German, French, Luxembourgish and Italian, with the Neue Zürcher Zeitung and the Luxembourg papers as its heaviest runs. Results are individual articles rather than issues or pages, and each carries its keyword-in-context fragments inline, with matches in {braces}, so no further call is needed to judge a hit.

THERE IS NO OPERATOR SYNTAX INSIDE A TERM. The server escapes the characters an operator would need, so a OR b searches for that literal text. A multi-word query is matched as a phrase. Use advanced_search_impresso for alternatives, exclusions and filters.

get_impresso_textA

Download one article's transcript, returning the path to the cached file.

Use only when the search fragments are not enough and the whole article has to be read or grepped. This is the metered call: transcripts are drawn against the account's monthly quota, while searches are not. An article whose rights status this account cannot read is refused with an explanation rather than returned empty.

Prompts

Interactive templates invoked by user choice

NameDescription

No prompts

Resources

Contextual data attached and managed by the client

NameDescription

No resources

TDQS

A4.4/5.0

Scored across 2 tools

Disambiguation5/5

The two tools have clearly distinct purposes: one searches for articles with inline fragments, the other retrieves full text for a specific article. There is no overlap in functionality, so an agent can easily decide which to call.

Naming Consistency5/5

Both tool names follow the same pattern: a verb followed by 'impresso' (search_impresso, get_impresso_text). The naming is consistent and predictable, with no mixed conventions.

Tool Count3/5

With only two tools, the server feels thin for the scope of a historical press archive. While search and retrieval cover a basic workflow, the reference to an 'advanced_search_impresso' tool that isn't present suggests the set is incomplete.

Completeness2/5

The server explicitly mentions an advanced search tool that is not implemented, and there are no filtering or browsing options (by date, language, newspaper, etc.). This limits the search to simple phrase queries, which is a significant gap for the intended research use case.

Maintenance

ActivityStale
ResponsivenessNo issues