Borrowing it
Nothing to install: this file belongs to haymon-ai/dbmcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/haymon-ai/dbmcp/master/CLAUDE.mdgit clone --depth 1 https://github.com/haymon-ai/dbmcpWrote 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/haymon-ai/dbmcp/claude-md)<a href="https://agentmods.dev/instructions/haymon-ai/dbmcp/claude-md"><img src="https://agentmods.dev/badge/instructions/haymon-ai/dbmcp/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 5.1 | $0.01801 | $0.01801 |
| Opus 5 | $0.00901 | $0.00901 |
| Sonnet 5 | $0.00360 | $0.00360 |
| Haiku 4.5 | $0.00180 | $0.00180 |
Grade A, and why
dbmcp 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 8d 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 — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
A single-binary MCP (Model Context Protocol) server for MySQL, MariaDB, PostgreSQL, and SQLite. Built in Rust with zero runtime dependencies.
Build & Test Commands
cargo build # debug build
cargo build --release # release build
cargo run -- stdio --db-backend mysql --db-user root # stdio transport
cargo run -- http --db-backend mysql --db-user root --host 127.0.0.1 --port 9001
cargo test # all tests
cargo test --workspace --lib --bins # unit tests only
cargo test <name> # single test
cargo test -- --nocapture # with stdout
cargo clippy --workspace --tests -- -D warnings # lint (warnings = errors)
cargo fmt --check # check formatting
cargo fmt # apply formatting
./tests/run.sh # integration tests (Docker required)
./tests/run.sh --filter mysql # filter by backend
Architecture
Cargo workspace: root binary (dbmcp) + 7 library crates under crates/. Workspace members use "crates/*" glob.
src/— Binary crate.cli.rsowns CLI parsing (clap with subcommands), tracing init, and subcommand dispatch.commands/common.rshosts the sharedDatabaseArgumentsgroup, theTryFrom<&DatabaseArguments> for DatabaseConfigconversion, and thecreate_serverfactory.commands/stdio.rsandcommands/http.rsown transport-specific execution;HttpArgumentsis private tohttp.rs.crates/config/(dbmcp-config) —Config,DatabaseConfig,HttpConfigstructs,DatabaseBackendenum (Mysql,Mariadb,Postgres,Sqliteviaclap::ValueEnum).DatabaseConfig::validate()andHttpConfig::validate()accumulate errors intoResult<(), Vec<ConfigError>>.crates/backend/(dbmcp-sql) — SharedAppErrortype, SQL read-only validation (validationmodule), identifier quoting/validation (identifiermodule), and request/response types (typesmodule).crates/server/(dbmcp-server) — Shared MCP tool implementations (toolsmodule) andserver_info(). Reused by all three database handler crates.crates/pii/(dbmcp-pii) — Regex-based PII detection (46 built-in entity types covering personal, financial, government, contact, network, digital-identity, and crypto categories) tagged byCategory(Personal,Financial,Government,Contact,Network,DigitalIdentity,Crypto), four anonymisation operators (replace,mask,redact,hash), and anAnalyzer::builder()entry point for category-filtered registries. Wired into query tool output behindPiiConfig. Canonical entity list:crates/pii/src/entity.rs(Entityenum); registration order:crates/pii/src/recognizers/mod.rs(all()).crates/mysql/(dbmcp-mysql) — MySQL/MariaDB backend: connection pooling, query operations, schema introspection, MCP handler viarmcp::tool_router.crates/postgres/(dbmcp-postgres) — PostgreSQL backend: per-database connection pool cache (moka), query operations, schema introspection, MCP handler.crates/sqlite/(dbmcp-sqlite) — SQLite backend: single-file connection, query operations, schema introspection, MCP handler.crates/sqlx-json/(sqlx-json) —RowExttrait for type-safe row-to-JSON conversion. Per-backend implementations forSqliteRow,PgRow, andMySqlRow.- Transport:
stdio(for Claude Desktop/Cursor) andhttp(Streamable HTTP with CORS via axum + tower-http). A transport subcommand is required —dbmcpwith no subcommand prints usage help and exits non-zero.
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.
- 8d ago First seen · 96 lines · 1,801 tokens per session scan A 7eaa26e304bd
dbmcp CLAUDE.md is an instructions file published in the GitHub repository haymon-ai/dbmcp (30 stars, last pushed 6d ago), licensed MIT. It adds 1,801 tokens to every session, about $0.0090 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 instructions, from other repositories
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.