mysql-mcp-server

Provides an MCP (Model Context Protocol) server for connecting to a MySQL database and exposing tools for SELECT-only querying, schema inspection (tables and columns), and execution-plan analysis via EXPLAIN/EXPLAIN ANALYZE. Also provides an execute tool for data-modifying statements (INSERT/UPDATE/DELETE) with a dry-run + confirmation token flow.

Evaluated Apr 04, 2026 (17d ago)
Repo ↗ Infrastructure mcp mysql database sql agent-tools schema-inspection query-execution explain go safety-controls
⚙ Agent Friendliness
59
/ 100
Can an agent use this?
🔒 Security
53
/ 100
Is it safe for agents?
⚡ Reliability
26
/ 100
Does it work consistently?

Score Breakdown

⚙ Agent Friendliness

MCP Quality
78
Documentation
76
Error Messages
0
Auth Simplicity
95
Rate Limits
0

🔒 Security

TLS Enforcement
60
Auth Strength
55
Scope Granularity
30
Dep. Hygiene
50
Secret Handling
70

Security controls described include: SELECT-only restriction on the query tool, a two-step dry-run + confirmation token process for data modifications, and confirmation token expiry after 5 minutes. Access control appears to rely on database user permissions (no additional auth/authorization for MCP clients described). TLS enforcement is not explicitly documented; assume HTTPS/TLS may not apply because it is a local MCP subprocess—MySQL connection encryption is unspecified. Credential handling is described via environment variables, but logging/redaction behavior is not specified.

⚡ Reliability

Uptime/SLA
0
Version Stability
40
Breaking Changes
30
Error Recovery
35
AF Security Reliability

Best When

You want an agent-friendly way to introspect and query a MySQL database locally/in your environment using MCP, and you can provide appropriately privileged (preferably read-only) credentials.

Avoid When

You need robust access control beyond database-user permissions, or you cannot enforce the two-step confirmation process for write operations.

Use Cases

  • Letting AI agents safely explore a MySQL schema (list tables, fetch table schema)
  • Answering questions over operational data using SELECT queries with result formatting
  • Performance troubleshooting by running EXPLAIN or EXPLAIN ANALYZE for a candidate query
  • Controlled, human/agent-mediated data changes (INSERT/UPDATE/DELETE) using a two-step dry-run + confirmation token workflow

Not For

  • Untrusted/anonymous clients or direct internet exposure
  • Environments that require strong user authentication/authorization at the API layer
  • Workloads requiring complex pagination controls or cursor-based retrieval
  • Bulk/long-running queries without governance (especially EXPLAIN ANALYZE)

Interface

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

Authentication

Methods: Environment-variable based database credentials (MYSQL_HOST/PORT/USER/PASSWORD/DATABASE) used by the MCP server
OAuth: No Scopes: No

No separate end-user auth is described for the MCP server itself; access control is primarily via the MySQL user permissions configured in the environment.

Pricing

Free tier: No
Requires CC: No

No pricing information provided; likely self-hosted.

Agent Metadata

Pagination
none
Idempotent
False
Retry Guidance
Not documented

Known Gotchas

  • The execute tool supports only INSERT/UPDATE/DELETE and uses dry_run + confirm_token; agents must follow the two-step pattern to avoid failed writes.
  • EXPLAIN ANALYZE may execute the query to gather real statistics; can be risky for long-running or heavy queries.
  • Query tool is restricted to SELECT statements only; agents may need to route data-modifying intent to the execute tool.

Alternatives

Full Evaluation Report

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

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