io.github.andezdev/tokenlite-mysql-mcp
A secure, efficient, and intelligent MySQL server for the Model Context Protocol
The current version, v4.1.0, was published to the official MCP registry on 2026-06-07. It is distributed as @andezdev/tokenlite-mysql-mcp on npm, filed under Databases by this index, and declares 27 environment variables. Removals and unreachable sources are measured across every server this index tracks, contract drift across the servers that answer in consecutive snapshots; the index's current counts put this record in context.
Using io.github.andezdev/tokenlite-mysql-mcp in Claude, Cursor, Gemini CLI, Cline, or Zed?
MCP tool contracts can change remotely with no version bump. The mcpindex gate pins each contract and HOLDs the call when it drifts-before your agent acts. Zero credentials. This is not the package install for this server itself (use Install this server for that).
Rewrites your MCP host config so each server launches behind the gate. Inspect first: curl -fsSL https://mcpindex.ai/install.sh | less
uv tool install mcpindex-gate && mcpindex-config-wireSemantic screen found no manipulation pattern in the description. Conformance probe not yet run.
mcpindex.integrity.descriptionpassINFOevidence“No malicious instructions found”via static_description
- - Semantic screen only - the deterministic conformance probe has not run on this server
- - Confidence is reported but not yet calibrated (v1)
- - Screen reads the tool description, not the live behavior
- - advisory
- - registry description only no input schema
- - screen model 8b
- - Still current: the description we screened is unchanged, re-checked against the registry
Semantic screen: an LLM judge reads the tool description for hidden instructions (status PARTIAL). A pass means the description is not lying, not that the tool is safe: a high-capability tool with an honest description still warrants caution. The deterministic conformance probe has not been run on this server yet, so the screen here is semantic-only. Posture: advisory. Confidences are reported but not yet calibrated (calibrated=false at v1). Full verdict history is not shown on this page.
Own this server? Screen its description →
That verdict was true at screening time (snapshot 2026-08-31).
Contracts can change after screening, with no version bump. The gate pins io.github.andezdev/tokenlite-mysql-mcp’s tool contracts on first sight and holds any silent change before your agent acts - the check that keeps being true on Tuesday.
See your first HOLD in 2 minutes →
Related: how to trust an MCP server · screen before install · silent contract drift
People vet a server before wiring it in. One line on your project site or docs answers that with an independent record: screening verdict, registry provenance, contract drift history. It stays current as new screens and drift events land.
[Independent trust record for io.github.andezdev/tokenlite-mysql-mcp](https://mcpindex.ai/server/io-github-andezdev-tokenlite-mysql-mcp) - screening verdict, registry provenance, and contract drift monitoring.<a href="https://mcpindex.ai/server/io-github-andezdev-tokenlite-mysql-mcp">Independent trust record for io.github.andezdev/tokenlite-mysql-mcp</a> - screening verdict, registry provenance, and contract drift monitoring.A live verdict badge for your README or listing. It reflects the current screen, links back here, and updates when the verdict does.
[](https://mcpindex.ai/server/io-github-andezdev-tokenlite-mysql-mcp)<a href="https://mcpindex.ai/server/io-github-andezdev-tokenlite-mysql-mcp"><img src="https://mcpindex.ai/api/v1/badge/io-github-andezdev-tokenlite-mysql-mcp" alt="mcpindex verdict" height="20" /></a>DB_HOSTMySQL Host address (defaults to localhost)
DB_PORTMySQL Port (defaults to 3306)
DB_USERMySQL Username (defaults to root)
DB_PASSWORDMySQL Password (defaults to empty string)
DB_NAMEMySQL Database name
MCP_EXPLAIN_MAX_SCAN_ROWSEXPLAIN guardrail: max estimated rows for unindexed full table scans before blocking (defaults to 1000). MCP_SAFE_QUERY_MAX_ROWS is a deprecated alias.
MCP_QUERY_ROW_LIMITMax rows returned per SELECT; injected as LIMIT at the AST level (defaults to 500)
MCP_SAFE_QUERY_MAX_ROWSDeprecated alias for MCP_EXPLAIN_MAX_SCAN_ROWS
MCP_SAFE_QUERY_ENABLE_BLOCKINGEnable or disable the EXPLAIN guardrail (defaults to true)
MCP_METADATA_PATHAbsolute path to your custom metadata.json dictionary
MCP_TEMPLATES_PATHAbsolute path to your custom templates.json pre-approved queries
TOOL_PREFIXPrefix for tool names, e.g., to run multiple instances (defaults to DB_NAME, e.g. mydb_). Only set to override.
MCP_RATE_LIMIT_RPMMax tool invocations per minute, sliding window (defaults to 60). Set to 0 to disable.
MYSQL_QUERY_TIMEOUTMax execution time for a query in milliseconds to protect against DoS (defaults to 15000)
MYSQL_CONNECTION_LIMITMax concurrent pool connections (defaults to 10)
MYSQL_CONNECT_TIMEOUTMax time to wait for a connection socket to establish in milliseconds (defaults to 10000)
MYSQL_RETRY_ATTEMPTSMax retries on transient connection errors (defaults to 3)
MYSQL_RETRY_DELAY_MSBase delay in milliseconds for exponential backoff between retries (defaults to 1000)
MYSQL_QUEUE_LIMITMax queued requests when all pool connections are busy to prevent memory leak (defaults to 50)
MCP_DDL_CACHE_TTLTime-to-live in seconds for cached DDL statements (defaults to 60)
MCP_LOG_LEVELMinimum severity level for MCP log notifications (defaults to info). Levels: debug, info, notice, warning, error, critical, alert, emergency
ALLOW_INSERT_OPERATIONEnable INSERT and REPLACE queries (defaults to false)
ALLOW_UPDATE_OPERATIONEnable UPDATE queries (defaults to false)
ALLOW_DELETE_OPERATIONEnable DELETE and TRUNCATE queries (defaults to false)
ALLOW_DDL_OPERATIONEnable Data Definition Language queries like CREATE, ALTER, DROP, RENAME (defaults to false)
DB_SSLEnable TLS for the MySQL connection (defaults to false)
DB_SSL_REJECT_UNAUTHORIZEDReject self-signed or untrusted TLS certificates when DB_SSL is true (defaults to true)
Self-hosted homelab log intelligence over MCP, CLI, and REST with SQLite/FTS.
Provision PostgreSQL, manage Apache Kafka, and deploy apps with Aiven - all from your AI assistant.
Fail-closed, read-only PostgreSQL and MongoDB access for AI agents over MCP.