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/afgong/sqlite-mcp-server/claude-mdgit clone --depth 1 https://github.com/afgong/sqlite-mcp-serverWrote 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/afgong/sqlite-mcp-server/claude-md)<a href="https://agentmods.dev/instructions/afgong/sqlite-mcp-server/claude-md"><img src="https://agentmods.dev/badge/instructions/afgong/sqlite-mcp-server/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 | $0.00491 | $0.00491 |
| Opus 5 | $0.00246 | $0.00246 |
| Sonnet 5 | $0.00098 | $0.00098 |
| Haiku 4.5 | $0.00049 | $0.00049 |
Grade A, and why
sqlite-mcp-server 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 3d 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.
What it actually says
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
Project Overview
This is a SQLite Explorer MCP (Model Context Protocol) Server built with the FastMCP framework. It provides safe, read-only access to SQLite databases through MCP tools that can be used by LLMs.
Key Commands
Installation and Setup
# Install dependencies
pip install -r requirements.txt
# Install for Claude Desktop
fastmcp install sqlite_explorer.py --name "SQLite Explorer" -e SQLITE_DB_PATH=/path/to/db
# Run the server directly
fastmcp run sqlite_explorer.py
Testing the Server
# Test with FastMCP's built-in testing
fastmcp test sqlite_explorer.py
# Run with environment variable
SQLITE_DB_PATH=/path/to/your/database.db fastmcp run sqlite_explorer.py
Architecture
Core Components
sqlite_explorer.py:164 - Main MCP server implementation with three key tools:
read_query()- Execute SELECT queries with safety validationslist_tables()- List all database tablesdescribe_table()- Get table schema information
SQLiteConnection class:16-28 - Context manager for database connections with proper cleanup
Safety Features
- Read-only access (only SELECT and WITH queries allowed)
- Query validation and sanitization
- Parameter binding support
- Row limit enforcement (default 1000 rows)
- Multiple statement detection and blocking
Environment Configuration
SQLITE_DB_PATH- Required environment variable pointing to the SQLite database file- Server uses log level "CRITICAL" to suppress progress output
MCP Integration
This server follows the FastMCP framework patterns:
- Uses
@mcp.tool()decorators to expose functions as MCP tools - Implements proper error handling with descriptive messages
- Returns structured data as lists and dictionaries
- Integrates with Claude Desktop and Cline VSCode plugin
Development Notes
- The codebase includes comprehensive documentation in
mcp-documentation.txtandfastmcp-documentation.txt - All database operations use SQLite's row factory for dictionary-style access
- Query validation prevents SQL injection and ensures read-only access
- The server is designed to be deployed as an MCP tool for LLM interactions
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.
- 3d ago First seen · 67 lines · 491 tokens per session scan A 0c625b428aa6
sqlite-mcp-server CLAUDE.md is an instructions file published in the GitHub repository afgong/sqlite-mcp-server (0 stars, last pushed 11mo ago), licensed MIT. It adds 491 tokens to every session, about $0.0025 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
seekstone CLAUDE.md
Instructions for shaqmughal/seekstone, covering claude.md, what this repo is, commands, the harness itself (run after npm install) and architecture.
plan-forge database.instructions.md
Database patterns for .NET — Dapper/EF Core, parameterized queries, migration strategy.
pg-dash CLAUDE.md
Claude Code instructions for indiekitai/pg-dash, covering pg-dash claude.md, 项目结构, 构建与测试, 发版纪律(强制) and 发版检查清单(每次 npm publish 前必须按序执行).
jdbc-driver CLAUDE.md
Claude Code instructions for keboola/jdbc-driver, covering claude.md, project overview, build & test commands, jdbc driver and vscode sqltools extension.
MCP-SqlServer CLAUDE.md
Claude Code instructions for Aron-Valenzuela/MCP-SqlServer, covering claude.md, project overview, setup (for each user), 1. install dependencies and 2. configure claude desktop.
plsql-intelligence AGENTS.md
Instructions for MuhDur/plsql-intelligence, covering agents.md — plsql-intelligence, founder constraints (plan.md §3, non-negotiable), plan rules to internalize (plan.md §4), rule 1 – absolute (do not ever violate this) and irreversible git & filesystem actions.