Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add rules/yangkyeongmo/mcp-server-openmetadata/architecturegit clone --depth 1 https://github.com/yangkyeongmo/mcp-server-openmetadataWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/rules/yangkyeongmo/mcp-server-openmetadata/architecture)<a href="https://agentmods.dev/rules/yangkyeongmo/mcp-server-openmetadata/architecture"><img src="https://agentmods.dev/badge/rules/yangkyeongmo/mcp-server-openmetadata/architecture.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.01479 | $0.01479 |
| Opus 5 | $0.00740 | $0.00740 |
| Sonnet 5 | $0.00296 | $0.00296 |
| Haiku 4.5 | $0.00148 | $0.00148 |
Grade A, and why
architecture scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 201 lines — stays where its author put it; the contents beside it link to each section on GitHub.
At the start of every response, say "APPLIED ARCHITECTURE RULE".
Code Architecture of /src
The /src directory implements a Model Context Protocol (MCP) server for OpenMetadata, providing programmatic access to OpenMetadata's REST API through a standardized interface. The architecture follows a modular, layered design that enables comprehensive data catalog and metadata management operations.
Core Entry Points
main.py: Simple entry point that delegates to main()
main.py: Central orchestration module that:
- Configures CLI interface with Click for transport selection (stdio/sse)
- Dynamically loads and registers API modules based on user selection
- Maps API types to their respective function collections
- Initializes OpenMetadata client with environment-based authentication
- Manages server lifecycle with chosen transport protocol
server.py: MCP server definition and configuration providing:
- FastMCP server instance creation
- Transport abstraction layer (stdio/sse)
- Server lifecycle management
Configuration Layer
enums.py: Defines APIType enum with OpenMetadata API categories:
- Core Entities: TABLE, DATABASE, SCHEMA, COLUMN
- Data Assets: DASHBOARD, CHART, PIPELINE, TOPIC
- Data Quality: DATAQUALITYTESTS, TESTCASES, METRICS, PROFILER
- Governance: CLASSIFICATION, TAG, GLOSSARY, POLICY
- Lineage & Usage: LINEAGE, USAGE, COST
- System Management: SERVICES, INGESTION, WEBHOOKS, BOTS
Environment variable management for OpenMetadata connection:
OPENMETADATA_HOST: OpenMetadata server URLOPENMETADATA_JWT_TOKEN: JWT token for API authenticationOPENMETADATA_USERNAME: Username for basic authenticationOPENMETADATA_PASSWORD: Password for basic authentication
OpenMetadata Integration Layer (/openmetadata/)
The architecture uses a consistent modular pattern across specialized API modules:
Common Module Structure
Each module follows this standardized pattern:
- API Client Setup: Imports and configures specific OpenMetadata API client
- Function Registry:
get_all_functions()returns list of (function, name, description) tuples - Async API Functions: Transform OpenMetadata API calls into MCP-compatible responses
- Tool Definitions: MCP Tool objects with JSON schema validation
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 4d ago First seen · 201 lines · 1,479 tokens per session scan A f44e49189987
architecture is a cursor rule published in the GitHub repository yangkyeongmo/mcp-server-openmetadata (24 stars, last pushed 1y ago), licensed MIT. It adds 1,479 tokens to every session, about $0.0074 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other cursor rules, from other repositories
lighter-safety
Safety contract for the Lighter MCP server. Apply whenever a lighter tool is invoked.
angular-20
This rule provides comprehensive best practices and coding standards for Angular development, focusing on modern TypeScript, standalone components, signals, and performance optimizations.
dev-standard
Apache Superset development standards and guidelines for Cursor IDE.
cli-error-handling
CLI command error handling patterns.
prefer-direct-imports-over-module-mocks
Prefer extracting a testable core over vi.mock / vi.resetModules when unit tests need to reach production logic entangled with config, env, or singletons.
control-plane-descriptors
Control plane descriptor and instance implementation patterns.