Skip to main content
Glama
Sign In
mcp-pilotage

mcp-pilotage

by fmenguy
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Local

etat_git

Retrieve live, read-only Git status for all repositories or a specific project, including branch, latest commit, uncommitted files, remote tracking, and project activity.

Instructions

État git en direct, lu au moment de l'appel : branche courante, dernier commit avec sa date et son auteur, nombre de fichiers modifiés non commités, avance et retard sur le dépôt distant, et niveau d'activité du projet (actif si moins de 30 jours, ralenti jusqu'à 120 jours, dormant au delà). Sans paramètre « projet », renvoie le tableau de bord de TOUS les dépôts d'un coup, trié du plus récemment touché au plus ancien : c'est la façon la plus rapide de savoir sur quoi François travaille en ce moment et ce qu'il a laissé en chantier. Avec un « projet », se concentre dessus et peut remonter l'historique des derniers commits. Strictement en lecture : cet outil n'exécute aucune commande git qui modifie quoi que ce soit, ni add, ni commit, ni push, ni checkout, ni fetch.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "etat_git"
  }
}

Input Schema

NameRequiredDescriptionDefault
projetNoNom ou chemin absolu d'un projet pour n'examiner que celui-là. Si absent, tous les dépôts git sont examinés.
nb_commitsNoNombre de commits récents à détailler. Ignoré quand aucun « projet » n'est précisé, pour garder la réponse compacte.
seulement_modifiesNoNe garder que les dépôts qui ont des modifications non commitées. Pratique pour répondre à la question : qu'est-ce que j'ai laissé en cours ?

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.0.0

TDQS

A4.5/5.0
Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations at all, the description carries the full safety burden and does so explicitly: 'Strictement en lecture' plus an enumeration of the mutating git commands it never runs (add, commit, push, checkout, fetch). It also discloses non-obvious behavior an agent could not infer — the 30/120-day activity thresholds, the recency sort order, and that nb_commits is ignored in all-repos mode.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

One dense paragraph, front-loaded with the live-state nature of the read and the returned fields before the mode rules. The enumeration of forbidden git commands and the phrase 'la façon la plus rapide de savoir sur quoi François travaille' lean slightly promotional, but both carry real routing value rather than filler.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

No output schema and no annotations, yet the description effectively documents the returned fields and the activity-classification rules, and clarifies the read-only guarantee. What is left implicit is the concrete response shape (per-repo object structure, field naming, ordering guarantees when a single 'projet' is given) — minor for a read-only 3-optional-param tool.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the baseline would be 3, but the description adds cross-parameter coupling that the schema states only tersely: 'Avec un « projet », se concentre dessus et peut remonter l'historique des derniers commits.' It reinforces why the no-projet path is deliberately compact, which frames the trade-off between the two modes.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

Opens with a specific verb+resource ('État git en direct, lu au moment de l'appel') and then enumerates exactly what is reported: branche courante, dernier commit avec date et auteur, fichiers modifiés, avance/retard, niveau d'activité. This is clearly distinct from sibling tools like lister_projets or decrire_projet, which an agent can rule out from the description alone.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives explicit mode-based guidance: without 'projet' it returns a dashboard of ALL repos sorted by recency, described as 'la façon la plus rapide de savoir sur quoi François travaille'; with 'projet' it zooms in and can surface commit history. It also ties 'seulement_modifies' to a concrete question ('qu'est-ce que j'ai laissé en cours'). It stops short of naming a sibling tool as the alternative for cross-repo search, which would have earned a 5.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Deploy Server

Other Tools