Skip to main content
Glama
mdz-axo

PT-MCP (Paul Test Man Context Protocol)

by mdz-axo

enrich_context

Enhance codebase understanding by integrating YAGO knowledge graph data and Schema.org semantic annotations to provide contextual insights about project structure and relationships.

Instructions

Enrich codebase context with knowledge graph data from YAGO 4.5 and Schema.org annotations

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
pathYesRoot directory path
analysis_resultNoPrevious analysis result from analyze_codebase (optional)
enrichment_levelNoLevel of enrichment (minimal: frameworks+languages, standard: +dependencies, comprehensive: +dev deps+patterns)standard
include_yagoNoInclude YAGO knowledge graph entity linking
include_schemaNoInclude Schema.org semantic annotations
max_entitiesNoMaximum entities to resolve from YAGO

Implementation Reference

  • Core handler function that executes the enrich_context tool logic: extracts entities, resolves YAGO knowledge graph entities, applies Schema.org annotations, computes confidence stats, and generates structured metadata.
    export async function enrichContext(args: EnrichContextArgs): Promise<EnrichedContext> { const { path, analysis_result, enrichment_level = 'standard', include_yago = true, include_schema = true, max_entities = 10, } = args; const result: EnrichedContext = { path, enrichment_metadata: { level: enrichment_level, timestamp: new Date().toISOString(), cache_hits: 0, yago_queries: 0, }, }; // If no analysis provided, we can only do minimal enrichment if (!analysis_result) { return { ...result, yago_entities: {}, schema_annotation: {}, json_ld: {}, }; } const db = await getDatabase(); const yagoResolver = getYAGOResolver(); const schemaMapper = getSchemaMapper(); // Extract entities from analysis const entities = extractEntitiesFromAnalysis(analysis_result, enrichment_level); // YAGO enrichment if (include_yago) { const yagoEntities: { [key: string]: YAGOEntity[] } = {}; let cacheHits = 0; let yagoQueries = 0; for (const [name, type] of entities.slice(0, max_entities)) { try { // Check if already cached const entity = db.findEntityByName(name); if (entity?.id) { const mapping = db.findYAGOMappingByEntityId(entity.id); if (mapping) { cacheHits++; } else { yagoQueries++; } } else { yagoQueries++; } // Resolve entity (uses cache automatically) const resolved = await yagoResolver.resolveEntity(name, 3); if (resolved.length > 0) { yagoEntities[name] = resolved; // Store in database if not exists if (!entity) { const entityId = await db.insertEntity({ name, type: type as EntityType, source_file: path, metadata: { detected_from: 'analysis' }, }); // Store high-confidence mapping if (resolved[0].confidence >= 0.9) { await db.upsertYAGOMapping({ entity_id: entityId, yago_uri: resolved[0].uri, yago_type: resolved[0].type, confidence: resolved[0].confidence, facts: { facts: resolved[0].facts }, }); } } } } catch (error) { console.error(`Failed to resolve YAGO entity for ${name}:`, error); } } result.yago_entities = yagoEntities; result.enrichment_metadata!.cache_hits = cacheHits; result.enrichment_metadata!.yago_queries = yagoQueries; // Calculate confidence stats const allEntities = Object.values(yagoEntities).flat(); if (allEntities.length > 0) { const autoLinked = allEntities.filter((e) => e.confidence >= 0.9).length; const avgConfidence = allEntities.reduce((sum, e) => sum + e.confidence, 0) / allEntities.length; result.confidence_stats = { total_entities: allEntities.length, auto_linked: autoLinked, needs_review: allEntities.length - autoLinked, avg_confidence: Math.round(avgConfidence * 100) / 100, }; } } // Schema.org enrichment if (include_schema) { const schemaType = schemaMapper.detectCodebaseType(analysis_result); const properties = schemaMapper.extractProperties(analysis_result); result.schema_annotation = { '@type': schemaType, ...properties, }; // Generate JSON-LD result.json_ld = schemaMapper.generateJSONLD({ entity_id: 0, // Temporary, will be assigned when stored schema_type: schemaType, properties, context_url: 'https://schema.org', }); } return result; }
  • TypeScript interfaces defining input (EnrichContextArgs) and output (EnrichedContext) schemas for the tool.
    export interface EnrichContextArgs { path: string; analysis_result?: any; enrichment_level?: 'minimal' | 'standard' | 'comprehensive'; include_yago?: boolean; include_schema?: boolean; max_entities?: number; } export interface EnrichedContext { path: string; schema_annotation?: any; yago_entities?: { [key: string]: YAGOEntity[]; }; json_ld?: any; confidence_stats?: { total_entities: number; auto_linked: number; needs_review: number; avg_confidence: number; }; enrichment_metadata?: { level: string; timestamp: string; cache_hits: number; yago_queries: number; }; }
  • Tool dispatch handler in switch statement that invokes the enrichContext function and formats the response for MCP.
    case "enrich_context": { const result = await enrichContext(args as any); const formatted = formatEnrichedContext(result); return { content: [ { type: "text", text: formatted, }, ], }; }
  • MCP tool registration schema in ListToolsRequestSchema response, defining input schema and description.
    name: "enrich_context", description: "Enrich codebase context with knowledge graph data from YAGO 4.5 and Schema.org annotations", inputSchema: { type: "object", properties: { path: { type: "string", description: "Root directory path", }, analysis_result: { type: "object", description: "Previous analysis result from analyze_codebase (optional)", }, enrichment_level: { type: "string", enum: ["minimal", "standard", "comprehensive"], description: "Level of enrichment (minimal: frameworks+languages, standard: +dependencies, comprehensive: +dev deps+patterns)", default: "standard", }, include_yago: { type: "boolean", description: "Include YAGO knowledge graph entity linking", default: true, }, include_schema: { type: "boolean", description: "Include Schema.org semantic annotations", default: true, }, max_entities: { type: "number", description: "Maximum entities to resolve from YAGO", default: 10, minimum: 1, maximum: 50, }, }, required: ["path"], },
  • Helper function to format the EnrichedContext output into readable markdown text used in the tool response.
    export function formatEnrichedContext(context: EnrichedContext): string { const lines: string[] = []; lines.push(`# Enriched Context: ${context.path}`); lines.push(''); // Schema.org annotation if (context.schema_annotation) { lines.push('## Schema.org Annotation'); lines.push('```json'); lines.push(JSON.stringify(context.schema_annotation, null, 2)); lines.push('```'); lines.push(''); } // YAGO entities if (context.yago_entities && Object.keys(context.yago_entities).length > 0) { lines.push('## YAGO Knowledge Graph Entities'); lines.push(''); for (const [name, entities] of Object.entries(context.yago_entities)) { lines.push(`### ${name}`); for (const entity of entities) { lines.push(`- **${entity.label}** (confidence: ${entity.confidence.toFixed(2)})`); lines.push(` - Type: ${entity.type}`); lines.push(` - URI: ${entity.uri}`); if (entity.description) { lines.push(` - Description: ${entity.description}`); } if (entity.facts.length > 0) { lines.push(` - Facts: ${entity.facts.length} relationships`); } } lines.push(''); } } // Confidence stats if (context.confidence_stats) { lines.push('## Confidence Statistics'); lines.push(`- Total entities: ${context.confidence_stats.total_entities}`); lines.push(`- Auto-linked (≥0.9): ${context.confidence_stats.auto_linked}`); lines.push(`- Needs review (<0.9): ${context.confidence_stats.needs_review}`); lines.push(`- Average confidence: ${context.confidence_stats.avg_confidence}`); lines.push(''); } // Enrichment metadata if (context.enrichment_metadata) { lines.push('## Enrichment Metadata'); lines.push(`- Level: ${context.enrichment_metadata.level}`); lines.push(`- Timestamp: ${context.enrichment_metadata.timestamp}`); lines.push(`- Cache hits: ${context.enrichment_metadata.cache_hits}`); lines.push(`- YAGO queries: ${context.enrichment_metadata.yago_queries}`); lines.push(''); } // JSON-LD if (context.json_ld) { lines.push('## JSON-LD Structured Data'); lines.push('```json'); lines.push(JSON.stringify(context.json_ld, null, 2)); lines.push('```'); } return lines.join('\n'); }

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/mdz-axo/pt-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server