{"$schema":"https://wellknown.network/schemas/agent-record-v1.json","schemaVersion":"1","id":"ag_j9k9ep5efay7","handle":"mcp-architecture-gliner","url":"https://wellknown.network/agents/mcp-architecture-gliner","links":{"self":"https://wellknown.network/agents/mcp-architecture-gliner/record.json","html":"https://wellknown.network/agents/mcp-architecture-gliner","markdown":"https://wellknown.network/agents/mcp-architecture-gliner/record.md","api":"https://wellknown.network/api/v1/agents/mcp-architecture-gliner","status":"https://wellknown.network/api/v1/agents/mcp-architecture-gliner/status","claim":"https://wellknown.network/agents/mcp-architecture-gliner/claim","claimApi":"https://wellknown.network/api/v1/claims","claimDescriptor":"https://wellknown.network/agents/mcp-architecture-gliner/claim.json","badge":"https://wellknown.network/agents/mcp-architecture-gliner/badge.svg","openapi":"https://wellknown.network/openapi.json","history":"https://wellknown.network/api/v1/agents/mcp-architecture-gliner/history","tools":"https://wellknown.network/api/v1/agents/mcp-architecture-gliner/tools"},"ard":{"identifier":"urn:air::server:mcp-architecture-gliner","type":"application/mcp-server-card+json"},"kind":"mcp_server","declared":{"name":"mcp-architecture-gliner","summary":"MCP server for architecture-specific entity extraction using GLiNER with TOGAF ADM phase awareness","description":"# 🏗️ Architecture-Focused MCP GLiNER Server\n\n> **Enhanced GLiNER-based entity extraction for software architecture documents with TOGAF ADM phase awareness and role-based contextual processing, implemented as an MCP (Model Context Protocol) server.**\n\n[![Python 3.9+](https://img.shields.io/badge/python-3.9+-blue.svg)](https://www.python.org/downloads/)\n[![FastMCP](https://img.shields.io/badge/FastMCP-2.10+-green.svg)](https://github.com/jlowin/fastmcp)\n[![GLiNER](https://img.shields.io/badge/GLiNER-0.0.18+-orange.svg)](https://github.com/urchade/GLiNER)\n[![MCP](https://img.shields.io/badge/MCP-Compatible-blue.svg)](https://github.com/modelcontextprotocol)\n\n## 🎯 Overview\n\nThis project transforms the basic GLiNER NER model into a specialized **MCP (Model Context Protocol) server** for software architecture document analysis. It provides intelligent entity extraction that understands TOGAF ADM phases, architecture roles, and contextual relationships to help architects make better decisions and retrieve relevant guidelines.\n\nThe server implements the MCP protocol, making it compatible with Claude Desktop, Cody, and other MCP-enabled clients.\n\n### Key Differentiators\n\n- **Architecture-Specific Intelligence**: Pre-configured with 200+ architecture-specific entity labels\n- **TOGAF ADM Integration**: Phase-aware processing for all 10 TOGAF ADM phases\n- **Role-Based Filtering**: Customized extraction for different architect roles\n- **Contextual Scoring**: Relevance-weighted entity scoring based on project context\n- **Document Classification**: Automatic analysis of document type and complexity\n\n## 🚀 Quick Start\n\n### 🎯 Easiest Way (Using uvx)\n\n```bash\n# Install uvx if you don't have it\ncurl -LsSf https://astral.sh/uv/install.sh | sh\n\n# Run the MCP server directly (no installation needed!)\nuvx mcp-architecture-gliner\n```\n\nThen configure your MCP client (like Claude Desktop) to use:\n```json\n{\n  \"mcpServers\": {\n    \"architecture-gliner\": {\n      \"command\": \"uvx\",\n      \"arg…","publisher":null,"homepage":"https://github.com/yourusername/mcp-architecture-gliner#readme","repository":"https://github.com/yourusername/mcp-architecture-gliner/blob/main/CHANGELOG.md","version":"1.0.0","license":"MIT","protocols":["mcp"],"tags":["architecture","entity-extraction","fastmcp","gliner","mcp","model-context-protocol","named-entity-recognition","togaf"],"pricing":null,"endpoints":[{"url":"pypi:mcp-architecture-gliner","type":"package_pypi","auth":null,"probeable":false}],"skills":null,"tools":null,"extra":null,"attribution":{"kind":"pypi","name":"pypi","license":"pypi","repoUrl":"pypi","summary":"pypi","version":"pypi","description":"pypi","homepageUrl":"pypi"}},"derived":{"capabilities":[{"slug":"documents.extraction","name":"Data Extraction","confidence":1,"provenance":"derived"}],"categories":["documents"],"language":"en"},"observed":{"status":"unknown","statusReason":"Distributed as a package to run locally; no network endpoint to check.","lastOkAt":null,"lastProbedAt":null,"statusComputedAt":null,"reliability30d":null,"latestObservations":[],"tools":null,"package":{"name":"mcp-architecture-gliner","registry":"pypi","observedAt":"2026-10-28T09:23:18.802Z","publishedAt":"2025-07-31T03:18:48.454188Z","latestVersion":"1.0.0"},"toolSurface":null,"endpointFacts":[]},"verification":{"claimed":false,"claimedAt":null,"proofs":[]},"provenance":{"sources":[{"source":"pypi","key":"mcp-architecture-gliner","url":"https://pypi.org/project/mcp-architecture-gliner/","firstSeenAt":"2026-09-10T00:23:35.980Z","fetchedAt":"2026-10-28T09:22:44.463Z","normalizedAt":"2026-10-28T09:22:44.463Z"}]},"firstSeenAt":"2026-09-10T00:23:35.980Z","updatedAt":"2026-10-28T09:23:18.802Z"}