Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
COADOR_REPOYesAbsolute path to the Android project repository to serve over MCP. Required to prevent the server from silently following an unrelated working directory.
COADOR_KB_DIRNoDirectory to store the generated knowledge base. Defaults to .coador/ inside the repository.

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": false
}
prompts
{
  "listChanged": false
}
resources
{
  "subscribe": false,
  "listChanged": false
}

Tools

Functions exposed to the LLM to take actions

NameDescription
kb_statusB

Report whether the knowledge base exists and is current.

kb_overviewA

What kind of project this is: stack, variants, modules and testing, in one answer. Call this first.

kb_list_layersB

List the layers of the knowledge base and how much each one detected.

kb_get_sectionA

Read one section: what was detected, and the facts that prove it. Inventory items are paged; pass next_cursor back as cursor. Section ids come from kb_list_layers, kb_search or kb_overview.

kb_searchC

Search the knowledge base in plain language or by identifier (for example 'how are UI tests run', 'Hilt', 'testInstrumentationRunner').

kb_refreshA

Rescan the repository. Only needed when kb_status reports the knowledge base as missing or stale; a scan of a large project takes a few seconds.

Prompts

Interactive templates invoked by user choice

NameDescription

No prompts

Resources

Contextual data attached and managed by the client

NameDescription
layers_resourceThe layers of the knowledge base.

TDQS

A3.7/5.0

Scored across 6 tools

Disambiguation5/5

Each tool has a distinct role: status checks existence, refresh rescans, overview gives project summary, list_layers shows structural layers, get_section reads detailed sections, and search finds content by query. The descriptions explicitly clarify when to use each, with no overlapping purposes.

Naming Consistency4/5

All tools share a consistent kb_ prefix and snake_case style, making them predictable. However, the pattern mixes bare verbs (kb_search, kb_refresh) with noun forms (kb_status, kb_overview) and verb_noun forms (kb_list_layers, kb_get_section), a minor deviation from a uniform convention.

Tool Count5/5

Six tools is well-scoped for a read-only knowledge base server. Each tool covers a necessary part of the discovery and retrieval workflow, with no redundant or missing operations.

Completeness5/5

The set covers the full lifecycle: checking KB status, refreshing when stale, getting an overview, listing layers, reading sections with paging, and searching. This provides complete coverage for navigating and querying the knowledge base.

Maintenance

ActivityMaintained
ResponsivenessNo issues