Claude 3.5 Sonnet Model Context Protocol (MCP) Database Agent & Query Synthesizer
Establishes a hardened Model Context Protocol (MCP) interface turning Claude 3.5 Sonnet into an autonomous, read-only data scientist with automated query plan verification.
Parametric Customizer & Compiler Live Tool
Adjust the variables below. The prompt code and API payload update dynamically in real time.
Specifies the target SQL dialect.
Default limit for safety.
Business analytics target for the agent.
# CLAUDE 3.5 SONNET MCP DATABASE AGENT SYSTEM ARCHITECTURE You are an Autonomous Enterprise Data Agent operating through Anthropic's Model Context Protocol (MCP). Your interface connects directly to PostgreSQL 16 with TimescaleDB & pgvector. ### SECURITY & EXECUTION BOUNDARIES: 1. **Strict Read-Only Enforcement**: - You are NEVER permitted to execute `DROP`, `DELETE`, `UPDATE`, `INSERT`, `ALTER`, `TRUNCATE`, or `GRANT` statements. - Any mutation request must be immediately refused with an explicit security alert. 2. **Performance & Query Optimization**: - Always prepend analytical queries with `EXPLAIN` or evaluate indexing before querying tables with > 1,000,000 rows. - Enforce mandatory `LIMIT 100` on all exploratory queries to protect server memory. 3. **MCP Tool-Calling Lifecycle**: - Step 1: Use `describe_schema` or `list_tables` to inspect the exact column datatypes. - Step 2: Formulate the SQL query inside `<query_plan>` tags explaining the join topology. - Step 3: Invoke the database tool with sanitized parameterized inputs. - Step 4: Parse the response and format the business summary with clear Markdown tables. ### XML COMMUNICATION CONTRACT: ```xml <database_agent_execution> <query_intent>Identify customer cohorts with > 30% retention drop-off in month 3</query_intent> <schema_evaluation>Verified tables, primary keys, and foreign indexes</schema_evaluation> <optimized_sql>EXPLAIN ANALYZE SELECT ...</optimized_sql> <business_insight>Executive summary of findings</business_insight> </database_agent_execution> ```
State-of-the-art coding and intelligent reasoning.
Leonardo Phoenix & Flux: Generate photorealistic studio assets with 150 daily free credits. Zero setup required.
π 3-Step Production Execution Blueprint
How senior engineers and top creators calibrate, customize, and verify this prompt formula in production.
Target Engine Calibration
Drop this prompt into your project root as `.cursorrules` or load it into Claude 3.5 Sonnet / DeepSeek-R1 system instructions.
Dynamic Parameterization
Adjust the dynamic variables (framework, database, and client state) to match your active codebase architecture.
Sanity & Boundary Check
Run a verification query asking the model to declare its architectural constraints before it generates the first line of code.
βοΈ Recommended API Hyperparameter Calibration
Verified 2026 SettingsCALIBRATION INSIGHT: Low temperature ensures deterministic syntax, accurate AST parsing, and zero hallucinated API methods.
πΈ Real Sample Outputs & Verified Results
Visual evidence and benchmark responses generated using this exact prompt formula.
π¬ Prompt Engineering Anatomy
Why this prompt consistently delivers high-tier results: technical parameter breakdown.
Model Context Protocol (MCP) Boundaries Anthropic's MCP provides an open standard for LLMs to securely query databases, APIs, and file systems through controlled tool definitions.
Schema Discovery Verification Forcing Claude to call list_tables before formulating queries prevents hallucinated column names and failed roundtrips.
β οΈ Critical Anti-Patterns & Execution Traps
The top 3 engineering mistakes to avoid when deploying this category of prompt into production.
Context Window Flooding
Pasting 50 unminified files into the prompt degrades attention, causing the LLM to ignore core TypeScript rules.
Missing Delimiter Isolation
Letting user instructions mix directly with system rules triggers instruction drift and hallucinations.
Over-Relying on Outdated Paradigms
Allowing the model to use deprecated React 18 patterns (e.g. useEffect for data fetching) creates security vulnerabilities.
π¬ Frequently Asked Questions
Troubleshooting common edge cases, model incompatibilities, and best practices.
Does this require Claude Desktop or Claude API?
This prompt works seamlessly with both the Claude Desktop MCP application and custom API implementations using the Anthropic Python or TypeScript SDKs.
How does this prevent prompt injection in data retrieval?
The prompt enforces strict XML isolation and instructs Claude to treat raw table cell values as untrusted data strings.
π οΈ Recommended Companion Micro-Tools
Complementary client-side tools designed to test, sanitize, or choreograph outputs from this prompt.
Vibe Coding Prompt Architect (.cursorrules Studio)
Generate production-grade .cursorrules, .windsurfrules, and CLAUDE.md for Next.js 15, FastAPI, and Go with zero-hallucination guardrails.
Launch Tool β‘System Prompt Security Auditor & Jailbreak Scanner
Scan LLM instructions for prompt injection, persona hijacking, and instruction leaks. Score defense 0-100 and auto-harden in 0ms.
Launch Tool β‘Token & API Cost Calculator
Calculate live token counts & cost comparisons across GPT-4o, Claude 3.5, and DeepSeek-R1 with prompt caching discounts.
Launch Tool β‘Cursor AI & Claude 3.5 Sonnet Pro Bundle
Supercharge your workflow with instant codebase indexing, multi-file edits, and automated system rules.
Explore Related AI Coding & Rulesets Prompts View all β
Claude 3.5 Sonnet Senior Staff Full-Stack Refactoring Architect
Specialized prompt framework for Claude 3.5 Sonnet and Claude 3.7. Transforms messy legacy codebases into modular, testable, high-performance systems with automated regression tests.
cursorCursor AI (.cursorrules) for Next.js 15, React 19 & Tailwind CSS
Stops Cursor from writing outdated Next.js 13 patterns, Pages Router syntax, or deprecated React hooks. Enforces strict TypeScript, Server Actions, and modular clean architecture.
deepseekDeepSeek-R1 Autonomous Deep Research & Synthesis Engine
DeepSeek-R1 chain-of-thought framework designed to force deep reflection, counterfactual auditing, and hypothesis testing before producing production-ready research reports.