More screenshots

    Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    Enterprise-SQL-MCP-Guard

    1

    Hardened read-only SQL agent skill for safe database discovery, PII-redacted analytics, and schema auditing.

    $14

    Secure checkout via Stripe

    Money-back guarantee

    Converts to your local currency at checkout

    Security scanned
    Enterprise-SQL-MCP-Guard

    Enterprise-SQL-MCP-Guard

    Example session with this skill installed

    Analyze the billing_ledgers table to find the total overdue_usd grouped by payment_status. verify the schema first.

    • Read your context and instructions
    • Compiled the enterprise-sql-mcp-guard

    I have inspected the database schema and executed a read-only aggregation on the billing ledgers.

    Overdue Billing Summary

    payment_statusinvoice_counttotal_overdue_usdavg_invoice_value
    OVERDUE41$3,214,500.80$78,402.45
    DISPUTED15$1,102,400.15$73,493.34
    PENDING_WIRE82$0.00$45,210.12
    SETTLED312$0.00$42,100.50

    Telemetry Data:

    • Execution Time: 1.42 ms
    • Security Status: PASSED
    • Truncated: False

    Next steps

    1. Run a join with institutional_clients to see which tiers own these overdue invoices.
    2. Filter for specific client_id values to drill down into high-value disputed cases.
    3. Check the idx_billing_status index usage if query performance drops on larger datasets.

    Connects securely to your tools. The creator never sees your data.

    About this skill

    Querying production databases often carries the risk of accidental mutations, performance degradation, or PII exposure. This skill provides a hardened, zero-trust gateway for agents to perform read-only SQL analysis and schema discovery without risking data integrity.

    What it does

    • Read-Only Enforcement uses a two-tier defense including AST validation and SQLite URI mode=ro to block all DML and DDL operations.
    • Schema Discovery provides a dedicated tool to inspect tables, columns, indexes, and row estimates without manual PRAGMA calls.
    • Automated Guardrails enforces row-count ceilings, payload byte limits, and execution timeouts to protect the agent's context window.
    • Security Sanitization redacts PII and sensitive tokens like API keys or password hashes from query results.
    • Query Optimization allows agents to run EXPLAIN QUERY PLAN to verify index utilization before executing complex joins.

    How it works

    1. Schema Discovery: The agent calls inspect_schema to map the database structure and avoid identifier hallucinations.
    2. Safe Querying: The agent executes SELECT or WITH statements via the execute_readonly_query tool.
    3. Validation: Every query passes through a regex and AST gate to ensure no mutating keywords are present.
    4. Telemetry Audit: Use get_server_telemetry to monitor execution latencies, blocked attempts, and server health.

    Frameworks & tools

    This skill is built for Model Context Protocol (MCP) environments using Python and aiosqlite. It is compatible with Claude Code, Cursor, and other MCP-enabled IDEs.

    Why this beats prompting it yourself

    Prompting an agent to be "read-only" is unreliable and prone to injection or accidental UPDATE commands. This skill moves enforcement from the prompt to the runtime, ensuring that even if the agent tries to mutate data, the database driver and AST validator will deterministically block it.

    Use cases

    • Revenue Analytics: Aggregating billing ledgers and client tiers to find payment exposure.
    • Data Debugging: Investigating API usage logs for high-latency endpoints or HTTP error spikes.
    • Index Auditing: Verifying that production queries are properly using B-Tree indexes to prevent table scans.
    • PII-Safe Reporting: Generating business intelligence reports that automatically mask sensitive user data.

    Known limitations

    Supports SQLite only. Hard ceiling of 100 rows per result and 64KB payload limit. Queries exceeding 3 seconds are automatically terminated(all three thresholds are configurable via environment variables).

    SQLite only. Hard 100-row and 64KB payload limits. 3.0s execution timeout. No support for DDL, DML, or administrative commands.

    How to use

    1. 1

      Connect your agent to the Agensi MCP

      Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup

    2. 2

      Sign in to Agensi

      Your agent shows a sign-in link. Sign in and click Allow.

    3. 3

      Ask for what you need

      Your agent loads this skill and uses it on your task. It always asks before any payment.

    Reviews

    No reviews yet

    Be one of the first to try it. Every listed skill goes through the trust checks below.

    Security scanned

    Checked by our 8-point scan before listing

    Fresh listing

    Recently published to Agensi

    Money-back guarantee

    Doesn't do what its page promises? You get your money back.

    Trust & safety

    Security scan

    Security scan passed 5 days ago

    Requires

    Sqlite
    python 3.11+
    SQLite database
    Python
    Enterprise Sql Guard MCP
    Git

    Permissions

    Terminal / Shell
    Read Files
    Environment Variables

    Allowed Hosts

    sqlite.org

    File Scopes

    .db
    .sqlite
    .sqlite3

    Strict read-only file access via SQLite URI (?mode=ro) and PRAGMA query_only = ON. Environment variables are used solely to configure the local database path, query timeout (3.0s), and row/payload bounds. Zero external network calls or disk writes are ever performed.

    Listed5 days ago
    Updatedtoday

    What's inside

    Frequently Asked Questions

    This skill uses a multi-layered 'Zero Trust' approach, combining Abstract Syntax Tree (AST) validation to block mutating keywords with driver-level read-only enforcement to ensure data remains untouched.

    It is built for the Model Context Protocol (MCP) and is fully compatible with MCP-enabled environments like Claude Code, Cursor, Antigravity and various IDE-integrated agents.

    The skill includes built-in PII redaction and security sanitization that automatically identifies and masks sensitive tokens, such as password hashes or API keys, before they reach the agent's context window.

    Currently, this skill is specifically optimized for SQLite databases, providing deep schema discovery and query optimization tools tailored for that environment.

    To prevent 'context stuffing' and ensure high performance, the skill enforces a 100-row result ceiling, a 64KB payload limit, and a strict 3-second execution timeout.

    You will receive the full MCP server implementation, the schema discovery toolset, and the telemetry auditing suite, designed for immediate deployment into your Python-based environment.

    New in Data & Databases