ArchLens
Creates, lists, and reads numbered Architecture Decision Records (ADRs) stored as Markdown files, allowing AI agents to capture, organize, and retrieve architectural decisions as Markdown documents.
Loads pluggable architecture review rule packs from user-supplied YAML files (via ARCHLENS_RULES_DIR), letting the server apply custom, domain-specific design review rules.
This server does not currently have a deployable release on Glama. Follow the repository's setup instructions to install and configure it for your MCP client, including any required credentials and local dependencies.
ArchLens
An MCP server for AI-assisted architecture governance. Let any MCP client write Architecture Decision Records and review designs against pluggable, domain-specific rule packs.
Features
create_adr,list_adrs,read_adr: numbered Markdown ADRsget_review_rules,list_domains: rule packs for general, insurance, banking, healthcare, agentic-aireview_design: pairs your design with the rule checklist; the LLM returns PASS/FAIL/UNKNOWN with evidenceCustom packs: set
ARCHLENS_RULES_DIRto a folder of your own YAML files
Related MCP server: AdrMcp
Install
git clone https://github.com/ptrivedi74/archlens && cd archlens
python -m venv .venv && .venv\Scripts\activate # Windows
pip install -e ".[dev]"
pytest -q
mcp dev src/archlens/server.py # MCP inspectorReview
examples/sample_design.mdagainst the insurance and agentic-ai rules, then record the key decision as an ADR.
Roadmap
PDF/Markdown ingestion tool
Mermaid/C4 diagram generation from ADRs
GitHub Action: review design docs on pull requests
Packs: EU AI Act, NIST AI RMF, TOGAF, Well-Architected
License
MIT
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
This server cannot be deployed
Maintenance
Related MCP Connectors
Append-only decisions with provenance, supersession, retrieval, and audited MCP actions.
Governed data discovery, exact queries, decisions, simulations, and runtime utilities over MCP.
Publish and share access-controlled Markdown documents from any MCP-enabled AI tool.
Render, verify, describe, and safely edit Mermaid diagrams through MCP.
Related MCP Servers
- FlicenseNot gradedqualityDmaintenanceEnables preserving, querying, and managing engineering decisions with reasoning and evidence through CLI, HTTP API, and MCP tools.16-
- AlicenseNot gradedqualityBmaintenanceAn MCP server that turns a folder of Markdown ADRs into live tools for AI agents: search, author, validate, link, and trace architectural decisions, with preview-by-default writes.1MIT
- AlicenseAqualityBmaintenanceAn artifact manager MCP server for system specifications, providing tools and resources to create, read, update, list, validate, and manage MADR 4.0.0-derived Architecture Decision Records (ADRs) stored as markdown files.124211 PyPI2AGPL 3.0
- AlicenseBqualityCmaintenanceEnables managing Architecture Decision Records by showing the ADR directory, listing existing ADR files, and generating new ADR markdown stubs via natural language.35 npmISC