Skip to main content
Glama

Data Loireatlantique

by io.github.pipeworx-io
OverviewDiscussionsAdmin

Server Details

Loire-Atlantique Open Data (data.loire-atlantique.fr) — OpenDataSoft MCP.

The last two health checks of this connector failed. If this server requires authentication, missing or expired test credentials may be the cause. A test profile lets Glama authenticate for health checks and discover tools; it is separate from your personal connections.

If you are the author, claim ownership, then add or update a test profile under Admin → Test Profile.

Status
Unhealthy
Uptime
0.2% over 24 days
Last Tested
Transport
Streamable HTTP
URL
Repository
pipeworx-io/mcp-data-loireatlantique
GitHub Stars
0
Server Listing
mcp-data-loireatlantique

TDQS

A3.9/5.0

Scored across 39 tools

Disambiguation3/5

Most tools have distinct purposes, but several clusters are genuinely confusable: ask_pipeworx vs ask_pipeworx_beta vs ask_pipeworx_grounded are near-identical routers, and the six polymarket_* tools plus bet_research, kalshi_weather_edge and release_calendar_markets all operate on overlapping prediction-market data. Similarly entity_profile, recent_changes, compare_entities, company_facts, resolve_entity and validate_claim blur into one another, though the very verbose descriptions do a lot to separate them.

Naming Consistency4/5

Names are uniformly lowercase snake_case, with predictable family prefixes (ask_pipeworx*, polymarket_*, resolution_*) and clean verb_noun forms (search_datasets, dataset_info, generate_llms_txt). The only minor deviation is the mix of bare verbs/nouns (query, remember, recall, forget, subscribe) alongside compound names, but the convention itself never breaks.

Tool Count2/5

39 tools is heavy, and, more importantly, only three (search_datasets, dataset_info, query) actually serve the named Loire-Atlantique Open Data domain — the rest are a broad Pipeworx gateway/prediction-market sprawl. That is a severe mismatch between the server's stated scope and its surface, well past the 25-tool caution line.

Completeness3/5

For the departmental open-data domain the surface is thin but coherent: discover (search_datasets), inspect schema (dataset_info) and query with ODSQL — reasonable read-only coverage since open data needs no create/update/delete, though theme/category browsing and export are absent. The remaining Pipeworx meta-tools are broad yet leave real gaps (no direct non-meta data tools, several soft-fail legs like USPTO and court calendars), so coverage is uneven overall.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

  1. 1 tool update
    • Changedrelease_calendar_markets2 fields changed
      • addedOutput schema / properties / empty_reason
        Added value: +{
+  "description": "Present ONLY on a zero-release window: \"no_releases_in_window\". The window was queried and nothing is scheduled — this is an answer, not a failure.",
+  "type": "string"
+}
      • addedOutput schema / properties / hint
        Added value: +{
+  "description": "Present ONLY on a zero-release window: what to change (usually a wider `hours`).",
+  "type": "string"
+}
  2. 39 tool updates
    • First observedai_visibility_check
    • First observedask_pipeworx
    • First observedask_pipeworx_beta
    • First observedask_pipeworx_grounded
    • First observedbet_research
    • First observedcompany_facts
    • First observedcompare_entities
    • First observeddataset_info
    • First observeddeep_research
    • First observeddiscover_tools
    • First observedentity_profile
    • First observedforget
    • First observedgenerate_llms_txt
    • First observedkalshi_weather_edge
    • First observedlist_subscriptions
    • First observedpipeworx_feedback
    • First observedpipeworx_trending
    • First observedpolymarket_arbitrage
    • First observedpolymarket_edge_tracker
    • First observedpolymarket_edges
    • First observedpolymarket_fill_risk
    • First observedpolymarket_kalshi_spread
    • First observedquery
    • First observedrecall
    • First observedrecent_alerts
    • First observedrecent_changes
    • First observedrelease_calendar_markets
    • First observedremember
    • First observedresolution_audit
    • First observedresolution_diff
    • First observedresolve_entity
    • First observedscan_competitor_ai_presence
    • First observedscan_dependency
    • First observedsearch_datasets
    • First observedsearch_within
    • First observedsubscribe
    • First observedsuggest_questions
    • First observedunsubscribe
    • First observedvalidate_claim

Related MCP Connectors

Related MCP Servers

  • data-economie-fr

    pipeworx-io
    A
    license
    Not graded
    quality
    B
    maintenance
    France Economy & Finance Open Data MCP server providing tools to search datasets, retrieve metadata, and query records from data.economie.gouv.fr.
    21 npm
    MIT

  • mcp-gouv-fr

    gghez
    A
    license
    A
    quality
    D
    maintenance
    MCP server for exploring French public open data via APIs like data.gouv.fr, geo.api.gouv.fr, INSEE Sirene, and Radio France.
    11
    MIT

  • mcp-datagouv-fr

    pipeworx-io
    A
    license
    Not graded
    quality
    B
    maintenance
    MCP server for the French open-data catalogue data.gouv.fr, enabling dataset search and retrieval, organization lookup, and reuse discovery via natural language queries.
    234 npm
    MIT
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources