Available MCP tools
Access deep repository intelligence and codebase insights through AI Architect's MCP server
AI Architect's MCP server provides a comprehensive suite of tools for exploring, analyzing, and understanding your organization's codebase. These tools enable AI coding assistants to access deep repository intelligence, architectural insights, and code-level information across all your Git repositories.
Below is the complete list of MCP tools provided by AI Architect:
getCapabilities
Discover what repository intelligence and analysis capabilities this MCP server provides.
Returns comprehensive information about available repository data, dependency analysis features, architectural insights, and clustering patterns for your organization's Git repositories.
Use this to understand what repository information is available through this specialized service.
listRepositories
Browse all Git repositories in your organization. Returns comprehensive repository catalog with names, descriptions, and resource URIs.
Use this to discover available repositories, understand the organization's project landscape, identify microservices and components, or get an overview of all systems.
Each entry includes a resource URI for accessing detailed repository information.
Instant access to pre-indexed organizational repository data.
listClusters
View automatically identified clusters of related repositories in your organization.
Clusters represent groups of repositories with strong dependencies or architectural relationships, often forming subsystems or microservice groups.
Use this to understand system architecture, identify bounded contexts, discover service groupings, or analyze component relationships.
Returns cluster information with member repositories and their resource URIs.
getRepositoryInfo
Get comprehensive repository information including metadata, structure, and dependencies.
To access incoming dependencies (services depending on this repo): set includeIncomingDependencies=true.
To access outgoing dependencies (services this repo depends on): set includeOutgoingDependencies=true.
Edge data includes various dependency types - filter by edge.type field to isolate specific categories.
Smart defaults: dependencies auto-limited by detailLevel (summary: 10, standard: 25, full: unlimited).
Essential for understanding repository relationships, analyzing dependencies, investigating integration points, and assessing impact of changes.
Returns pre-analyzed dependency graphs and relationship data.
getClusterInfo
Examine a specific cluster of related repositories to understand subsystem architecture within your organization.
Returns all member repositories, their interdependencies, project summaries, and resource URIs.
Use this to analyze how repositories collaborate, understand service boundaries, explore microservice architectures, or investigate system decomposition patterns.
Valuable for architectural reviews and impact analysis.
searchRepositories
ONLY use when you DON'T know the repository name. If you know exact name, use getRepositoryInfo or getFieldPath directly.
Intelligent search across your organization's Git repositories using natural language queries.
Search by technology, functionality, frameworks, or project characteristics when repository name is unknown.
Uses TF-IDF algorithm on pre-indexed repository metadata for relevant results.
Examples: 'Python microservices', 'repositories using Redis', 'authentication services', 'React applications', 'payment processing systems', 'Kubernetes deployments'.
Returns repositories with relevance scores and direct access URIs.
searchWithinRepository
Search for content within a single repository including metadata and dependency data.
Searches metadata fields and optionally incoming_dependencies and outgoing_dependencies.
By default searches ALL data for comprehensive results.
Use includeIncomingDependencies=false and includeOutgoingDependencies=false for faster metadata-only search.
Returns filtered results with matches from metadata and dependencies.
Use when: You know which repo but need to find specific information without knowing exact field paths.
Natural language queries work well.
getRepositorySchema
Discover repository structure without fetching data.
Returns field names, types, array counts, and nested hierarchy.
Essential first step for exploring unfamiliar repositories.
getFieldPath
Extract specific nested field using dot notation and array indexing.
MOST EFFICIENT for surgical data extraction - returns only requested field vs full repository.
For dependencies: use 'incoming_dependencies' or 'outgoing_dependencies' paths with arraySlice, then filter by edge.type field to isolate specific categories.
Supports deep nesting, array slicing, and optional parent context.
Returns only the requested field data.
queryFieldAcrossRepositories
Query same field path across multiple repositories in single call.
Comparative analysis, pattern discovery, and technology audits across repos.
searchCode
Search code using zoekt index with powerful query syntax.
Supports file filters, exclusions, case sensitivity.
Returns code matches with snippets.
searchSymbols
Search for symbol definitions (functions, classes, methods) across indexed codebase.
getCode
Retrieve actual source code content from repository files.
Use after searchCode/searchSymbols to view the full code around matches.
Returns file contents with line numbers. Only available when reposDir is configured.
Last updated