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 instructions/hadi21k/database-mcp/claude-mdgit clone --depth 1 https://github.com/hadi21k/database-mcpWrote 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/instructions/hadi21k/database-mcp/claude-md)<a href="https://agentmods.dev/instructions/hadi21k/database-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/hadi21k/database-mcp/claude-md.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 | $0.01618 | $0.01618 |
| Opus 5 | $0.00809 | $0.00809 |
| Sonnet 5 | $0.00324 | $0.00324 |
| Haiku 4.5 | $0.00162 | $0.00162 |
Grade A, and why
database-mcp CLAUDE.md 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 5d 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 — 145 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
Project Overview
Database MCP Server — a Model Context Protocol server that gives AI assistants read-only access to SQL Server and PostgreSQL databases. Built with TypeScript, Node.js 18+, ESM modules, and the @modelcontextprotocol/sdk.
Commands
npm run build # Compile TypeScript → build/
npm run dev # Watch mode compilation
npm start # Run server (node build/index.js)
npm test # Run all tests (Vitest)
npm run test:unit # Unit tests only
npm run test:integration # Integration tests only
npm run test:watch # Tests in watch mode
npm run test:coverage # Coverage report (V8 provider)
Architecture
Layers
index.ts (entry)
→ ConfigLoader (env/file/CLI config)
→ SqlServerMcpServer (server.ts)
→ ConnectionManager (pool-per-profile, lazy init, multi-database)
→ IDatabaseDriver (driver abstraction per profile)
→ SqlServerDriver (mssql package)
→ PostgresDriver (postgres/porsager package)
→ ToolRegistry → 11 tools (BaseTool subclasses)
→ ResourceRegistry → 3 resources (BaseResource subclasses)
→ StdioServerTransport (MCP stdio transport)
Driver Abstraction
The IDatabaseDriver interface (src/database/interfaces/database-driver.ts) abstracts all database-specific operations. Each database type implements this interface:
- SqlServerDriver (
src/database/drivers/sqlserver.driver.ts) — usesmssqlConnectionPool,sys.*views for metadata,TOPfor row limiting - PostgresDriver (
src/database/drivers/postgres.driver.ts) — usespostgres(porsager) tagged template queries,pg_catalog/information_schemafor metadata,LIMITfor row limiting
Tools and resources interact only with IDatabaseDriver, never with database-specific APIs.
Key Directories
src/config/— Config loading (ConfigLoader) and types (ConnectionProfile,DatabaseType, connection string parsing)src/core/— Abstract base classes (BaseTool,BaseResource) and registriessrc/database/—ConnectionManager(pool management, driver creation)src/database/interfaces/—IDatabaseDriverinterface and result type interfacessrc/database/drivers/— Database-specific driver implementations and factorysrc/tools/— MCP tool implementations:- Universal: list-schemas, list-tables, describe-table, get-relationships, get-indexes, run-select-query, explain-query, estimate-cost
- PostgreSQL-only: list-materialized-views, list-extensions, list-enums
src/resources/— MCP resource implementations (table-schema, database-info, connection-profiles) usingdb:///URI schemesrc/utils/— Dialect-aware query validation (validation.ts) and error sanitization (error-handler.ts)tests/unit/— Vitest unit tests
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.
- 5d ago First seen · 145 lines · 1,618 tokens per session scan A 25eca91b8962
database-mcp CLAUDE.md is an instructions file published in the GitHub repository hadi21k/database-mcp (3 stars, last pushed 1mo ago), licensed MIT. It adds 1,618 tokens to every session, about $0.0081 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 2026-08-31.
Other instructions, from other repositories
lms-front AGENTS.md
AGENTS.md instructions for guillermoscript/lms-front, covering claude.md, project overview, commands, development and database (supabase).
lms-front CLAUDE.md
Claude Code instructions for guillermoscript/lms-front, covering claude.md, project overview, commands, architecture and multi-tenancy.
postgres-skills AGENTS.md
Instructions for neondatabase/postgres-skills, covering agents.md, repository overview, creating a new skill, directory structure and naming conventions.
rails_ai_agents AGENTS.md
AGENTS.md instructions for ThibautBaissac/rails_ai_agents, covering project configuration, tech stack, architecture, key commands and tests.
pgroles AGENTS.md
AGENTS.md instructions for thepartly/pgroles, covering agents.md, build & test commands, format + lint (always run before committing), unit tests (no database needed) and integration tests (requires live postgresql).
pg_exporter AGENTS.md
Instructions for nbari/pg_exporter, covering agents.md, project shape, first steps, devpod workflow (preferred) and local commands.