apisql-mcp

An MCP server (Node.js) that lets MCP clients execute SQL against multiple database types via an apiSQL API gateway, with support for runtime switching between configured data sources (DS/SUDB), and both DDL/DML plus stored procedures/UDFs. It can run over MCP stdio by default and also offers a streamable HTTP transport mode.

Evaluated Mar 30, 2026 (0d ago)
Homepage ↗ Repo ↗ API Gateway mcp sql database api-gateway nodejs integration
⚙ Agent Friendliness
58
/ 100
Can an agent use this?
🔒 Security
65
/ 100
Is it safe for agents?
⚡ Reliability
32
/ 100
Does it work consistently?

Score Breakdown

⚙ Agent Friendliness

MCP Quality
78
Documentation
74
Error Messages
0
Auth Simplicity
75
Rate Limits
10

🔒 Security

TLS Enforcement
85
Auth Strength
70
Scope Granularity
50
Dep. Hygiene
55
Secret Handling
60

Security relies primarily on apiSQL gateway API key authorization and network routing (with a documented recommendation for least-privilege/read-only users). The README includes a real-looking example API key in plaintext, which is a risk as sample handling/rotation guidance is not discussed. No explicit documentation here about TLS requirements, key rotation, secret logging, rate limiting, or audit log retention—only that logs/audit exist via apiSQL.

⚡ Reliability

Uptime/SLA
0
Version Stability
55
Breaking Changes
35
Error Recovery
40
AF Security Reliability

Best When

You have an apiSQL account + gateway configured, want an MCP-friendly single entry point to many SQL engines, and you can enforce least-privilege at the gateway/data-source level.

Avoid When

You cannot enforce least-privilege (e.g., credentials allow writes/DDL broadly) or you need strong, explicitly documented operational guarantees (error semantics, retries, rate limits, SLAs) from this package itself.

Use Cases

  • Letting LLM/MCP agents query and analyze databases across multiple engines from one integration
  • Operational analytics/reporting using SQL with dynamic data-source switching
  • DB access in environments that prefer routing through a gateway rather than direct network exposure
  • Admin/automation workflows that require executing DDL/DML and stored procedures through an agent

Not For

  • Untrusted users/agents that should not have broad database modification capabilities
  • Read-only reporting scenarios where writes/DDL must be strictly prohibited
  • Environments requiring a local-only database connector without reliance on an external gateway/service
  • Strict compliance contexts where data residency, audit retention, and security controls must be formally documented

Interface

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

Authentication

Methods: Bearer token API key (APISQL_MCP_API_KEY) used when calling apiSQL API endpoint
OAuth: No Scopes: Yes

README indicates access control via apiSQL platform API key authorization and SUDB permissions, but does not document exact scope model/claims or how granular scopes map to DB actions.

Pricing

Free tier: No
Requires CC: No

No pricing information in provided content; apiSQL service is required so costs likely apply externally.

Agent Metadata

Pagination
none
Idempotent
False
Retry Guidance
Not documented

Known Gotchas

  • Credentials/permissions: the server can execute modifying SQL; least-privilege is critical
  • Dynamic DS/SUDB routing depends on the gateway URL containing /$sudb and on exact data source naming
  • Agents may issue heavy/long-running queries; there is no documented query timeout/limits here
  • Transport choice matters: stdio vs streamable-http requires correct client configuration

Alternatives

Full Evaluation Report

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

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 2026-03-30.

6533
Packages Evaluated
19870
Need Evaluation
586
Need Re-evaluation
Community Powered