Skip to main content
Glama
Sign In
mcp-pilotage

mcp-pilotage

by fmenguy
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Local

chercher_partout

Search text or regex across files in all projects at once, returning matches grouped by project with file and line number. Restrict by project names and file globs to narrow results.

Instructions

Cherche un texte ou une expression régulière dans le CONTENU des fichiers de tous les projets à la fois, et renvoie les correspondances groupées par projet avec le fichier et le numéro de ligne. C'est l'outil qui répond aux questions du type : où est-ce que j'ai déjà écrit ce personnage, dans quel projet se trouve cette clé d'API, quels dépôts utilisent cette dépendance, où ai-je documenté cette décision. Utilise ripgrep quand il est installé sur la machine, sinon un parcours interne équivalent. Les dossiers lourds (node_modules, dist, build, .astro, venv, pycache, .git) sont toujours exclus. Restreins la recherche avec « projets » et « filtre_fichiers » dès que tu peux : c'est plus rapide et le résultat est plus lisible.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "motif": "<motif>"
    },
    "name": "chercher_partout"
  }
}

Input Schema

NameRequiredDescriptionDefault
motifYesTexte à chercher. Interprété littéralement par défaut, ou comme une expression régulière si « regex » vaut true.
regexNoInterpréter « motif » comme une expression régulière plutôt que comme du texte littéral.
projetsNoNoms ou chemins des projets à fouiller. Si absent, tous les projets de l'inventaire sont fouillés.
max_resultatsNoNombre total de correspondances renvoyées au maximum.
sensible_casseNoRespecter la casse. Par défaut la recherche l'ignore.
filtre_fichiersNoMotif glob sur le chemin des fichiers, par exemple « *.md », « **/*.ts » ou « src/**/*.py ». Réduit fortement le temps de réponse.
max_par_fichierNoNombre maximal de correspondances conservées par fichier, pour éviter qu'un seul fichier ne monopolise le résultat.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.0.0

TDQS

A4.2/5.0
Behavior4/5

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

With no annotations supplied, the description carries the behavioral burden well: it discloses the search engine (ripgrep when installed, otherwise an equivalent internal traversal), the permanently excluded heavy directories (node_modules, dist, build, .astro, venv, __pycache__, .git), and the grouped output format. It does not discuss permissions, timeout/performance limits, or whether truncation is signaled when max_resultats is reached, so it is informative but not fully exhaustive.

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?

The purpose and scope are front-loaded in the first sentence, followed by usage examples, engine behavior, exclusions, and the narrowing advice in a logical order. The list of four example questions is somewhat verbose and could be trimmed without loss, but every remaining sentence contributes actionable information.

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

Completeness5/5

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

For a seven-parameter search tool with no annotations and no output schema, the description covers what is searched, how results are shaped and grouped, which directories are skipped, which engine is used, and how to narrow the search. Nothing an agent needs in order to call this correctly is missing, aside from minor edge cases like truncation signaling.

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

Parameters3/5

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

Schema description coverage is 100%, so all seven parameters are already documented in the schema, making 3 the baseline. The description adds practical meaning to 'projets' and 'filtre_fichiers' by explaining that constraining them improves speed and readability of results, but it does not add syntax or behavioral detail beyond what the schema fields already state.

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?

States a specific verb and resource ('Cherche un texte ou une expression régulière dans le CONTENU des fichiers de tous les projets'), explicitly scoping to file contents across all projects at once, and describes the return shape (matches grouped by project with file and line number). The concrete example questions ('où est-ce que j'ai déjà écrit ce personnage', 'quels dépôts utilisent cette dépendance') make the distinction from filename-oriented siblings like trouver_fichiers unmistakable.

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 clear when-to-use guidance through four representative question types, which tells an agent the exact class of request this tool answers. It also advises narrowing with 'projets' and 'filtre_fichiers' whenever possible for speed and readability. It stops short of naming a specific alternative to use instead (e.g., for filename lookups), so no explicit when-not routing is present.

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