What is mcp-odbc CLAUDE.md?

A project instruction guide for mcp-odbc, a Python server that connects to databases through ODBC and provides schema discovery and read-only queries. It explains the architecture, research files, technology choices, and rules contributors must follow.

Use it when developing mcp-odbc to understand its architecture, database drivers, MCP tools, configuration, security model, and validation process.

It gives an agent the project context it needs before changing code and points it to the main design documents.

How phil-cheesman/mcp-odbc configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to phil-cheesman/mcp-odbc. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/phil-cheesman/mcp-odbc/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/phil-cheesman/mcp-odbc

Made for: Claude Code.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/phil-cheesman/mcp-odbc/claude-md.svg)](https://agentmods.dev/instructions/phil-cheesman/mcp-odbc/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/phil-cheesman/mcp-odbc/claude-md"><img src="https://agentmods.dev/badge/instructions/phil-cheesman/mcp-odbc/claude-md.svg" alt="Measured on agentmods" height="20"></a>

Per session 1,743 This file is loaded in full into every session.

When invoked 1,743 The same file — it is already loaded in full.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.01743	$0.01743
Opus 5	$0.00872	$0.00872
Sonnet 5	$0.00349	$0.00349
Haiku 4.5	$0.00174	$0.00174

Measured 8d ago against content hash d6e6c2d6dc6d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

mcp-odbc 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.

CLAUDE.md · 205 lines

How it starts

The opening of the file, as written. The whole thing — 205 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md — mcp-odbc

Agent and contributor guide for the Universal ODBC MCP Server.

What This Is

mcp-odbc — a Python MCP server that connects to any ODBC data source, auto-detects the DBMS, and exposes schema discovery + read-only query tools. Designed for Claude Code but works with any MCP client.

Architecture (read before writing code)

MANDATORY: Read research/05_architecture_design.md before making any changes. It contains the full design spec including module structure, tool signatures, adapter pattern, config schema, and security model. All code should follow this design.

Key Research Files

File	What It Covers
`research/05_architecture_design.md`	START HERE — full architecture, module structure, phased roadmap
`research/01_mcp_sdk_patterns.md`	FastMCP v2 API, tool decorators, transport, error handling, testing
`research/02_existing_implementations.md`	4 repos analyzed, anti-patterns to avoid, ideas to steal
`research/03_pyodbc_drivers.md`	pyodbc catalog API, driver quirks, encoding, platform differences
`research/04_erp_schemas_detection.md`	12 ERP/DB systems, detection queries, SQL_DBMS_NAME values, drift

Tech Stack

FastMCP v2.x (fastmcp>=2.0,<3.0) — MCP framework, decorator-based tools
pyodbc >=5.0 — ODBC driver binding
Pydantic >=2.0 — config validation
Transport: STDIO (Claude Code native)
Packaging: pyproject.toml + hatchling
Testing: pytest + pytest-asyncio + FastMCP Client

Module Structure

mcp-odbc/
+-- pyproject.toml
+-- src/mcp_odbc/
|   +-- __init__.py
|   +-- server.py           # FastMCP server + tool registration + entry point
|   +-- connection.py       # ConnectionManager (lazy connect, health check, close)
|   +-- config.py           # Pydantic models, env var / INI loading
|   +-- query.py            # Query execution, read-only enforcement
|   +-- metadata.py         # Schema discovery, caching
|   +-- detection.py        # DBMS detection via SQL_DBMS_NAME
|   +-- formatting.py       # Markdown tables, JSON, value truncation
|   +-- errors.py           # SQLSTATE mapping, credential sanitization
|   +-- adapters/
|       +-- __init__.py     # Adapter registry + get_adapter()
|       +-- base.py         # SystemAdapter ABC
|       +-- generic.py      # GenericODBCAdapter (ODBC catalog fallback)
|       +-- netsuite.py     # OA_TABLES, OA_COLUMNS, OA_FKEYS
|       +-- mssql.py        # sys.* catalog views
|       +-- postgresql.py   # pg_catalog
|       +-- mysql.py        # INFORMATION_SCHEMA
|       +-- oracle.py       # ALL_* data dictionary
|       +-- (others)        # hana, db2, sage, quickbooks
+-- tests/
+-- config/config.example.ini
+-- research/               # Research docs (read-only reference)

Read the full file on GitHub · 205 lines

Changes

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 · 205 lines · 1,743 tokens per session scan A d6e6c2d6dc6d

Subscribe to this mod's changes

mcp-odbc CLAUDE.md is an instructions file published in the GitHub repository phil-cheesman/mcp-odbc (2 stars, last pushed 6mo ago), licensed MIT. It adds 1,743 tokens to every session, about $0.0087 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.

Databases

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.

vercel/next.js · 7,296 tokens

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.

openai/codex · 5,153 tokens

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).

microsoft/vscode · 6,785 tokens

mcp-odbc: Instructions file for Claude Code