mcp-server-sql

A Spring Boot-based SQL execution service intended to be used as part of a Spring AI MCP (Model/Chat/Prompt) setup. It runs SQL queries and writes query results to a CSV file, and supports SQL update operations (INSERT/UPDATE/DELETE) returning affected row counts and execution timing. Database connection is configured via application.yml (MySQL + HikariCP).

Evaluated Apr 04, 2026 (17d ago)
Repo ↗ Databases mcp spring-boot java sql mysql csv-export agent-tools data-integration
⚙ Agent Friendliness
24
/ 100
Can an agent use this?
🔒 Security
23
/ 100
Is it safe for agents?
⚡ Reliability
15
/ 100
Does it work consistently?

Score Breakdown

⚙ Agent Friendliness

MCP Quality
35
Documentation
35
Error Messages
0
Auth Simplicity
20
Rate Limits
0

🔒 Security

TLS Enforcement
0
Auth Strength
30
Scope Granularity
0
Dep. Hygiene
50
Secret Handling
40

TLS requirements for DB connections and any server endpoints are not documented. The service likely uses raw DB credentials configured in application.yml; no API-level auth/authorization or scope granularity is described. Because it appears to execute SQL supplied by the caller (example shows raw SQL), it is vulnerable to SQL injection/abuse unless the MCP tool layer enforces strict allowlists and parameterization. Dependency hygiene cannot be assessed from provided content.

⚡ Reliability

Uptime/SLA
0
Version Stability
40
Breaking Changes
0
Error Recovery
20
AF Security Reliability

Best When

You need a simple agent-accessible SQL query/update tool that writes outputs to files, and you can deploy it with strict operational controls and a controlled database user/permissions.

Avoid When

You cannot restrict/validate SQL, or you need robust API-level contracts (OpenAPI), explicit rate limiting, or comprehensive error/timeout semantics.

Use Cases

  • Allow an AI agent/tool to run read-only SQL queries and export results to CSV for downstream processing
  • Run controlled SQL update operations and return affected row counts for workflow automation
  • Provide a lightweight MCP tool boundary around an application’s SQL access (where agent-to-DB capability is intentionally limited)

Not For

  • Running arbitrary untrusted SQL directly from a user/agent without sanitization and guardrails
  • High-assurance production database administration
  • Use cases requiring strong observability (audit trails), fine-grained authorization, or schema-level safety controls (not documented here)

Interface

REST API
No
GraphQL
No
gRPC
No
MCP Server
Yes
SDK
No
Webhooks
No

Authentication

Methods: Database credentials via application.yml (username/password)
OAuth: No Scopes: No

No user-facing/API authentication is described for the service itself. Authentication appears to be implicit via the DB credentials used by the running service. Authorization/guardrails for agent calls are not described.

Pricing

Free tier: No
Requires CC: No

No pricing information provided (appears to be self-hosted open-source style project).

Agent Metadata

Pagination
none
Idempotent
False
Retry Guidance
Not documented

Known Gotchas

  • Service accepts arbitrary SQL (based on examples/description), which can be dangerous if the agent is not constrained to safe statements/allowlists.
  • Writing results to local filesystem paths requires the hosting environment to have correct permissions and stable storage semantics.
  • No documented limits, timeouts, or backpressure; long-running queries may cause tool timeouts or resource exhaustion.
  • No documented schema/column typing or escaping rules for CSV output.

Alternatives

Full Evaluation Report

Comprehensive deep-dive: security analysis, reliability audit, agent experience review, cost modeling, competitive positioning, and improvement roadmap for mcp-server-sql.

AI-powered analysis · PDF + markdown · Delivered within 30 minutes

$99

Package Brief

Quick verdict, integration guide, cost projections, gotchas with workarounds, and alternatives comparison.

Delivered within 10 minutes

$3

Score Monitoring

Get alerted when this package's AF, security, or reliability scores change significantly. Stay ahead of regressions.

Continuous monitoring

$3/mo

Scores are editorial opinions as of 2026-04-04.

8642
Packages Evaluated
17761
Need Evaluation
586
Need Re-evaluation
Community Powered