20 Best MySQL MCP Servers, Compared (October 2026)
The short answer
For most readers, MySQL MCP Server (designcomputer/mysql_mcp_server) is the server to install. It is a Community favourite with 3 tools, tool descriptions graded A, 7,280 PyPI downloads in a typical week, a commit 77 days ago, and 5 commits in the last 12 weeks. If you need read-only MySQL from Claude Code with an npm package, choose MCP Server for MySQL (benborla/mcp-server-mysql): it has 13,657 npm downloads in a typical week, ships mysql_query and mysql://tables, and keeps writes disabled unless env flags are set. If you need one server for MySQL alongside other databases, DBHub (bytebase/dbhub) is the better answer.
Whichever you choose, give it the narrowest access that still works (a read-only credential, a replica, a scratch account), and widen it only once you have watched what your agent actually asks for.
Glama operates the MCP registry these numbers are measured from, and sells MCP hosting and a gateway. No position on this page is paid for. How the registry is built.
Quick picks
- 1MySQL MCP Server : Ad-hoc MySQL database exploration before writing queries: it exposes three tools for schema metadata, table sampling, and SQL execution.
- 2MCP Server for MySQL : Teams needing read-only MySQL schema inspection and queries from Claude Code: it ships mysql_query and mysql://tables, with writes disabled unless env flags are set.
- 3DBHub : Querying MySQL alongside other databases from one MCP server: DBHub's README documents execute_sql and search_objects, plus optional explain_sql and health_check tools.
- 4MySQL Database Access : Auditing or querying a production MySQL database without write risk: it exposes four read-only tools for listing databases, tables, and schemas, and running SELECT queries.
- 5Multi Database MCP Server : Managing several MySQL databases at once in one agent session: it reads a multi-connection config and auto-generates per-database query, execute, transaction, schema, and performance tools.
Which one, for your situation
| Your situation | What to use |
|---|---|
| I need ad-hoc MySQL exploration before writing queries | MySQL MCP Server (designcomputer/mysql_mcp_server) fits: it exposes 3 tools for schema metadata, table sampling, and SQL execution, and its tool descriptions are graded A. |
| I need read-only MySQL from Claude Code over npm | MCP Server for MySQL (benborla/mcp-server-mysql) fits: it ships mysql_query and mysql://tables, has 13,657 npm downloads in a typical week, and keeps writes disabled unless env flags are set. |
| I query MySQL alongside PostgreSQL or SQLite | DBHub (bytebase/dbhub) is built for this: it connects to MySQL, PostgreSQL, SQLite, DuckDB and etc., and documents execute_sql and search_objects. |
| I need audited DDL and DML with permission controls | MCP MySQL Server (liliangshan/mcp-server-mysql) provides sql_query, permission checking, operation logs, and readonly/DDL/DROP/DELETE flags, with 5 tools and tool descriptions graded B. |
| I need governed read-write MySQL access with per-table roles | Faucet (faucetdb/faucet) exposes eight MCP tools for query, insert, update and delete, gated by per-table role-based access, and its tool descriptions are graded A. |
| I need Cloud SQL for MySQL from an IDE or agent | MCP Toolbox for Databases (googleapis/mcp-toolbox) provides prebuilt generic tools such as list_tables and execute_sql, with 16,673 stars on GitHub and a commit 3 days ago. |
Top MCP servers for MySQL
| Best for | Profile | ||||||
|---|---|---|---|---|---|---|---|
| 1 | Ad-hoc MySQL database exploration before writing queries: it exposes three tools for schema metadata, table sampling, and SQL execution. | Community favourite | 1,399 | +7 | 77 days ago | 84.7 | |
| 2 | Teams needing read-only MySQL schema inspection and queries from Claude Code: it ships mysql_query and mysql://tables, with writes disabled unless env flags are set. | Community favourite | 2,157 | +41 | 83 days ago | 80.9 | |
| 3 | Querying MySQL alongside other databases from one MCP server: DBHub's README documents execute_sql and search_objects, plus optional explain_sql and health_check tools. | Community favourite | 3,639 | +125 | 5 days ago | 69.0 | |
| 4 | Auditing or querying a production MySQL database without write risk: it exposes four read-only tools for listing databases, tables, and schemas, and running SELECT queries. | Community favourite | 72 | 0 | 26 days ago | 68.4 | |
| 5 | Managing several MySQL databases at once in one agent session: it reads a multi-connection config and auto-generates per-database query, execute, transaction, schema, and performance tools. | Community favourite | 468 | +50 | 2 days ago | 63.0 | |
| 6 | Semantic search over existing MariaDB data: the README documents vector-store tools for inserting documents and running embedding-based similarity queries. | Steady | 208 | +4 | 69 days ago | 61.6 | |
| 7 | Teams needing audited MySQL DDL and DML with permission controls: it provides sql_query, permission checking, operation logs, and readonly/DDL/DROP/DELETE flags. | Steady | 14 | 0 | 7 days ago | 60.3 | |
| 8 | VS Code users who want their AI agent to query MySQL: DBCode registers MCP tools automatically and gives agents existing connections, schemas, and query execution. | Community favourite | 357 | +9 | 6 days ago | 57.7 | |
| 9 | Teams already using DBX as their database manager who want MCP clients to query MySQL through the same desktop, Docker, or CLI install. | Community favourite | 27,039 | +9,004 | today | 57.5 | |
| 10 | Connecting an IDE or AI agent to Cloud SQL for MySQL for schema exploration: it provides prebuilt generic tools such as list_tables and execute_sql. | Community favourite | 16,673 | +259 | 3 days ago | 54.9 | |
| 11 | Developers working with an existing MySQL database who need an MCP client to connect, run SELECT queries, execute writes, and inspect tables and schema. | Abandoned but popular | 169 | +1 | 338 days ago | 52.7 | |
| 12 | Connecting Claude Desktop to MySQL, PostgreSQL, or Redis through one npm-installed server: it runs over stdio and defaults to read-only access. | Abandoned but popular | 940 | +6 | 215 days ago | 51.1 | |
| 13 | TypeScript apps on PostgreSQL or MongoDB adopting Prisma 8: its installers add agent skills for scaffolding contracts and driving ORM changes. | Community favourite | 47,694 | +34 | 2 days ago | 51.0 | |
| 14 | Agents querying mixed databases and files under access policy: it exposes a GraphQL and MCP surface with query_catalog discovery and read-only boundaries. | Community favourite | 3,213 | +52 | today | 51.0 | |
| 15 | Managing a hosted WhoDB platform project from an AI assistant: it exposes 155 tools covering datasets, ontologies, transforms, apps, bundles, and confirmation-gated writes. | Community favourite | 5,034 | +6 | today | 48.9 | |
| 16 | Multi-agent workflows that need MySQL updates without lost updates: it provides optimistic concurrency tools with _version checks and conditional updates. | Steady | 11 | 0 | 61 days ago | 48.4 | |
| 17 | Read-only data investigation against predefined MySQL environments: it exposes query, info and environments tools and has no write tools. | Steady | 13 | 0 | 74 days ago | 46.4 | |
| 18 | Read-only SQL against an AnalyticDB for MySQL cluster: it exposes execute_sql, get_query_plan and get_execution_plan, with execute_sql read-only unless write tools are explicitly enabled. | Steady | 32 | 0 | 81 days ago | 43.8 | |
| 19 | Governed read-write MySQL access for AI agents: it exposes eight MCP tools for query, insert, update and delete, gated by per-table role-based access. | Steady | 152 | No snapshot history | today | 43.5 | |
| 20 | Read-only inspection of a MySQL schema from an LLM: it exposes a query tool limited to SELECT statements and publishes table schemas as resources. | Dormant | 16 | +1 | 153 days ago | 42.7 |
The ranking, with the evidence
Each position is a weighted mean of adoption (40%), maintenance (24%), momentum (14%), tool description quality (13%) and trust (9%), multiplied by three attenuators: how directly the server is about MySQL (named for it, declaring it, tagged with it, or merely mentioning it), whether its repository is still moving, and how much independent evidence of adoption it has. Open the score on any entry to see every number, including the ones marked ≈, which were imputed from the median of the other candidates rather than measured. The maintenance grade on each entry is mostly issue responsiveness, release recency and open security alerts rather than commits, so a recent commit beside a low grade is two different measurements rather than a contradiction.
- Abandoned but popular: People use it, but its default branch has stopped moving. Fine to keep running, risky to adopt.
- Community favourite: Widely adopted and still actively maintained.
- Dormant: Neither changing nor widely adopted. Here because it still matches the search.
- Emerging: Small audience, growing quickly, maintained. The bet with the most upside.
- Steady: Maintained, modest audience, no surprises in either direction.
Best for: Ad-hoc MySQL database exploration before writing queries: it exposes three tools for schema metadata, table sampling, and SQL execution.
MySQL MCP Server runs over stdio or Streamable HTTP and exposes three tools: execute_sql, get_schema_info, and get_table_sample, covering SQL execution, schema inspection, and table row sampling. Its execute_sql tool accepts only single SQL statements, so multi-statement queries such as USE db; SELECT ... are not supported.
GitHub stars1,399Stars / 30 days+7npm / typical weekShips no npm packagePyPI / typical week7.3Kmysql-mcp-serverTools exposed3Last commit77 days agoCommits / 12 weeks5Maintenance gradeBTool descriptionsAScore 84.7: show every number behind it
- Adoption94 / 100 · weight 40%
- GitHub stars79
- PyPI downloads82
- Used through Glamanot measurednot used through Glama in the last 30 days
- Maintenance81 / 100 · weight 24%
- Last commit touching this server88
- Repository maintenance grade80
- Commit cadence65
- Momentum49 / 100 · weight 14%
- Stars gained, relative to size28
- Stars gained, absolute37
- PyPI download trend100
- Tool quality91 / 100 · weight 13%
- Tool description quality83
- Built and inspected by Glama100
- Trust100 / 100 · weight 9%
- License100
- Published by the vendor it integratesnot measurednot published by the vendor it integrates
- Weighted mean of the five
- 84.7
- × relevance: the keyword is dedicated here
- 1.00
- × continuity: actively changing
- 1.00
- × evidence: widely adopted
- 1.00
- Composite score
- 84.7
Best for: Teams needing read-only MySQL schema inspection and queries from Claude Code: it ships mysql_query and mysql://tables, with writes disabled unless env flags are set.
MCP Server for MySQL connects LLMs to MySQL through the Model Context Protocol, exposing the mysql_query tool and the mysql://tables resource for schema inspection and queries, with write operations disabled unless environment flags enable them. It requires Node.js v20+ and a MySQL user with appropriate privileges, and supports MySQL 5.7+ (8.0+ recommended).
GitHub stars2,157Stars / 30 days+41npm / typical week13.7KPyPI / typical weekno attributed packageTools exposednever inspectedLast commit83 days agoCommits / 12 weeks4Maintenance gradeDTool descriptionsNot gradedScore 80.9: show every number behind it
- Adoption100 / 100 · weight 40%
- GitHub stars83
- npm downloads88
- Used through Glamanot measurednot used through Glama in the last 30 days
- Maintenance64 / 100 · weight 24%
- Last commit touching this server88
- Repository maintenance grade30
- Commit cadence40
- Momentum55 / 100 · weight 14%
- Stars gained, relative to size55
- Stars gained, absolute65
- npm download trend44
- Tool quality≈68 / 100 · weight 13%
- Tool description quality≈68tool descriptions not yet scored
- Built and inspected by Glamanot measurednever built and inspected by Glama
- Trust100 / 100 · weight 9%
- License100
- Published by the vendor it integratesnot measurednot published by the vendor it integrates
- Weighted mean of the five
- 80.9
- × relevance: the keyword is dedicated here
- 1.00
- × continuity: actively changing
- 1.00
- × evidence: widely adopted
- 1.00
- Composite score
- 80.9
Best for: Querying MySQL alongside other databases from one MCP server: DBHub's README documents execute_sql and search_objects, plus optional explain_sql and health_check tools.
DBHub connects MCP-compatible clients to MySQL and other databases, and its README documents execute_sql and search_objects by default with opt-in explain_sql, health_check, and custom TOML-defined tools, plus an HTTP transport, Docker image, MCP Bundle, Claude Code plugin, and built-in workbench. It does not provide enterprise-level controls such as approval flow, access control, data masking, and audit logging, which its README notes are available in a separate product.
GitHub stars3,639Stars / 30 days+125npm / typical weekdownloads not countedPyPI / typical weekno attributed packageTools exposednever inspectedLast commit5 days agoCommits / 12 weeks94Maintenance gradeATool descriptionsNot gradedScore 69.0: show every number behind it
- Adoption89 / 100 · weight 40%
- GitHub stars89
- npm downloadsnot measurednpm names no repository for dbhub, so its downloads cannot be attributed
- Used through Glamanot measurednot used through Glama in the last 30 days
- Maintenance100 / 100 · weight 24%
- Last commit touching this server100
- Repository maintenance grade100
- Commit cadence100
- Momentum79 / 100 · weight 14%
- Stars gained, relative to size75
- Stars gained, absolute85
- npm download trendnot measuredno download history for the selected registry
- Tool quality≈68 / 100 · weight 13%
- Tool description quality≈68tool descriptions not yet scored
- Built and inspected by Glamanot measurednever built and inspected by Glama
- Trust100 / 100 · weight 9%
- License100
- Published by the vendor it integratesnot measurednot published by the vendor it integrates
- Weighted mean of the five
- 88.5
- × relevance: the keyword is declared here
- 0.78
- × continuity: actively changing
- 1.00
- × evidence: widely adopted
- 1.00
- Composite score
- 69.0
Best for: Auditing or querying a production MySQL database without write risk: it exposes four read-only tools for listing databases, tables, and schemas, and running SELECT queries.
MySQL Database Access exposes four tools (list_databases, list_tables, describe_table, and execute_query) and restricts query execution to SELECT, SHOW, DESCRIBE, and EXPLAIN statements. It assumes you can supply MySQL connection details such as host, port, user, and password as environment variables, and it offers no write path for any of its tools.
GitHub stars72Stars / 30 days0npm / typical week571PyPI / typical weekno attributed packageTools exposed4Last commit26 days agoCommits / 12 weeks7Maintenance gradeATool descriptionsAScore 68.4: show every number behind it
- Adoption66 / 100 · weight 40%
- GitHub stars47
- npm downloads59
- Used through Glamanot measurednot used through Glama in the last 30 days
- Maintenance93 / 100 · weight 24%
- Last commit touching this server100
- Repository maintenance grade100
- Commit cadence65
- Momentum10 / 100 · weight 14%
- Stars gained, relative to size0
- Stars gained, absolute0
- npm download trend39
- Tool quality73 / 100 · weight 13%
- Tool description quality65
- Built and inspected by Glama100
- Trust100 / 100 · weight 9%
- License100
- Published by the vendor it integratesnot measurednot published by the vendor it integrates
- Weighted mean of the five
- 68.4
- × relevance: the keyword is dedicated here
- 1.00
- × continuity: actively changing
- 1.00
- × evidence: widely adopted
- 1.00
- Composite score
- 68.4
Best for: Managing several MySQL databases at once in one agent session: it reads a multi-connection config and auto-generates per-database query, execute, transaction, schema, and performance tools.
The README documents a Go MCP server that reads a JSON connection config and auto-generates per-database query, execute, transaction, schema, and performance tools for each connected database. Before choosing it, note that it is built on the FreePeak/cortex framework and requires a connection config with credentials for each database.
GitHub stars468Stars / 30 days+50npm / typical weekShips no npm packagePyPI / typical weekno attributed packageTools exposednever inspectedLast commit2 days agoCommits / 12 weeks127Maintenance gradeATool descriptionsNot gradedScore 63.0: show every number behind it
- Adoption67 / 100 · weight 40%
- GitHub stars67
- npm downloadsnot measuredno npm package
- Used through Glamanot measurednot used through Glama in the last 30 days
- Maintenance100 / 100 · weight 24%
- Last commit touching this server100
- Repository maintenance grade100
- Commit cadence100
- Momentum88 / 100 · weight 14%
- Stars gained, relative to size100
- Stars gained, absolute69
- npm download trendnot measuredno download history for the selected registry
- Tool quality≈68 / 100 · weight 13%
- Tool description quality≈68tool descriptions not yet scored
- Built and inspected by Glamanot measurednever built and inspected by Glama
- Trust100 / 100 · weight 9%
- License100
- Published by the vendor it integratesnot measurednot published by the vendor it integrates
- Weighted mean of the five
- 80.8
- × relevance: the keyword is declared here
- 0.78
- × continuity: actively changing
- 1.00
- × evidence: widely adopted
- 1.00
- Composite score
- 63.0
Best for: Semantic search over existing MariaDB data: the README documents vector-store tools for inserting documents and running embedding-based similarity queries.
MCP MariaDB Server reads its connection details from environment variables such as DB_HOST, DB_USER and DB_PASSWORD, and its README documents tools for listing databases and tables, fetching table schemas with foreign-key relations, running read-only SELECT, SHOW and DESCRIBE statements, and optionally creating, populating and searching vector stores. The vector and embedding tools stay disabled unless EMBEDDING_PROVIDER is set to openai, gemini or huggingface, and each of those paths assumes the corresponding API key or HuggingFace model setting is supplied.
GitHub stars208Stars / 30 days+4npm / typical weekShips no npm packagePyPI / typical weekno attributed packageTools exposednever inspectedLast commit69 days agoCommits / 12 weeks2Maintenance gradeDTool descriptionsNot gradedScore 61.6: show every number behind it
- Adoption58 / 100 · weight 40%
- GitHub stars58
- npm downloadsnot measuredno npm package
- Used through Glamanot measurednot used through Glama in the last 30 days
- Maintenance64 / 100 · weight 24%
- Last commit touching this server88
- Repository maintenance grade30
- Commit cadence40
- Momentum38 / 100 · weight 14%
- Stars gained, relative to size44
- Stars gained, absolute29
- npm download trendnot measuredno download history for the selected registry
- Tool quality≈68 / 100 · weight 13%
- Tool description quality≈68tool descriptions not yet scored
- Built and inspected by Glamanot measurednever built and inspected by Glama
- Trust100 / 100 · weight 9%
- License100
- Published by the vendor it integrates100
- Weighted mean of the five
- 61.6
- × relevance: the keyword is dedicated here
- 1.00
- × continuity: actively changing
- 1.00
- × evidence: widely adopted
- 1.00
- Composite score
- 61.6
Best for: Teams needing audited MySQL DDL and DML with permission controls: it provides sql_query, permission checking, operation logs, and readonly/DDL/DROP/DELETE flags.
MCP MySQL Server is an npm-installable MCP server that exposes five tools: sql_query, get_database_info, get_operation_logs, check_permissions, and get_ddl_sql_logs. Before choosing it, note that DDL, DROP, and DELETE access is governed by environment flags ALLOW_DDL, ALLOW_DROP, and ALLOW_DELETE, while READONLY restricts permitted operations to SELECT and SHOW.
GitHub stars14Stars / 30 days0npm / typical week329PyPI / typical weekno attributed packageTools exposed5Last commit7 days agoCommits / 12 weeks2Maintenance gradeBTool descriptionsBScore 60.3: show every number behind it
- Adoption58 / 100 · weight 40%
- GitHub stars29
- npm downloads54
- Used through Glamanot measurednot used through Glama in the last 30 days
- Maintenance83 / 100 · weight 24%
- Last commit touching this server100
- Repository maintenance grade80
- Commit cadence40
- Momentum0 / 100 · weight 14%
- Stars gained, relative to size0
- Stars gained, absolute0
- npm download trend0
- Tool quality63 / 100 · weight 13%
- Tool description quality55
- Built and inspected by Glama100
- Trust100 / 100 · weight 9%
- License100
- Published by the vendor it integratesnot measurednot published by the vendor it integrates
- Weighted mean of the five
- 60.3
- × relevance: the keyword is dedicated here
- 1.00
- × continuity: actively changing
- 1.00
- × evidence: widely adopted
- 1.00
- Composite score
- 60.3
Best for: VS Code users who want their AI agent to query MySQL: DBCode registers MCP tools automatically and gives agents existing connections, schemas, and query execution.
It is a VS Code database client that can run an MCP server exposing the databases it manages, their schemas, and query execution, registered automatically for Copilot and Cursor and with one click for Antigravity, Windsurf, and Kiro. It is not a standalone server: the MCP layer ships inside the extension, so an agent needs the extension installed, connections already configured, and per-connection AI permissions set before it can reach MySQL.
GitHub stars357Stars / 30 days+9npm / typical weekdownloads not countedPyPI / typical weekno attributed packageTools exposednever inspectedLast commit6 days agoCommits / 12 weeks69Maintenance gradeATool descriptionsNot gradedScore 57.7: show every number behind it
- Adoption64 / 100 · weight 40%
- GitHub stars64
- npm downloadsnot measurednpm names no repository for dbcode, so its downloads cannot be attributed
- Used through Glamanot measurednot used through Glama in the last 30 days
- Maintenance100 / 100 · weight 24%
- Last commit touching this server100
- Repository maintenance grade100
- Commit cadence100
- Momentum48 / 100 · weight 14%
- Stars gained, relative to size53
- Stars gained, absolute40
- npm download trendnot measuredno download history for the selected registry
- Tool quality≈68 / 100 · weight 13%
- Tool description quality≈68tool descriptions not yet scored
- Built and inspected by Glamanot measurednever built and inspected by Glama
- Trust100 / 100 · weight 9%
- License100
- Published by the vendor it integratesnot measurednot published by the vendor it integrates
- Weighted mean of the five
- 74.0
- × relevance: the keyword is declared here
- 0.78
- × continuity: actively changing
- 1.00
- × evidence: widely adopted
- 1.00
- Composite score
- 57.7
Best for: Teams already using DBX as their database manager who want MCP clients to query MySQL through the same desktop, Docker, or CLI install.
DBX ships as a desktop application, a Docker image, a CLI, and an MCP server, and that MCP server lets a client issue natural language queries and manage databases including MySQL. Its exposed tool list is not published anywhere, so the specific MySQL operations available have to be verified after installing the dbx npm package.
GitHub stars27,039Stars / 30 days+9,004npm / typical weekdownloads not countedPyPI / typical weekno attributed packageTools exposednever inspectedLast committodayCommits / 12 weeks4,596Maintenance gradeATool descriptionsNot gradedScore 57.5: show every number behind it
- Adoption100 / 100 · weight 40%
- GitHub stars100
- npm downloadsnot measurednpm publishes dbx from samt/node-dbx
- Used through Glamanot measurednot used through Glama in the last 30 days
- Maintenance100 / 100 · weight 24%
- Last commit touching this server100
- Repository maintenance grade100
- Commit cadence100
- Momentum100 / 100 · weight 14%
- Stars gained, relative to size100
- Stars gained, absolute100
- npm download trendnot measuredno download history for the selected registry
- Tool quality≈68 / 100 · weight 13%
- Tool description quality≈68tool descriptions not yet scored
- Built and inspected by Glamanot measurednever built and inspected by Glama
- Trust100 / 100 · weight 9%
- License100
- Published by the vendor it integratesnot measurednot published by the vendor it integrates
- Weighted mean of the five
- 95.8
- × relevance: the keyword is tagged here
- 0.60
- × continuity: actively changing
- 1.00
- × evidence: widely adopted
- 1.00
- Composite score
- 57.5
Best for: Connecting an IDE or AI agent to Cloud SQL for MySQL for schema exploration: it provides prebuilt generic tools such as list_tables and execute_sql.
MCP Toolbox for Databases is an MCP server that connects AI agents, IDEs, and applications to enterprise databases through prebuilt generic tools such as list_tables and execute_sql, and it also provides a framework for defining custom tools with structured queries, semantic search, and NL2SQL. Its prebuilt tools are configured with a --prebuilt= flag in an MCP-compatible client, and the README lists MySQL support under Cloud SQL within Google Cloud.
GitHub stars16,673Stars / 30 days+259npm / typical weekShips no npm packagePyPI / typical weekno attributed packageTools exposednever inspectedLast commit3 days agoCommits / 12 weeks221Maintenance gradeATool descriptionsNot gradedScore 54.9: show every number behind it
- Adoption100 / 100 · weight 40%
- GitHub stars100
- npm downloadsnot measuredno npm package
- Used through Glamanot measurednot used through Glama in the last 30 days
- Maintenance100 / 100 · weight 24%
- Last commit touching this server100
- Repository maintenance grade100
- Commit cadence100
- Momentum69 / 100 · weight 14%
- Stars gained, relative to size51
- Stars gained, absolute97
- npm download trendnot measuredno download history for the selected registry
- Tool quality≈68 / 100 · weight 13%
- Tool description quality≈68tool descriptions not yet scored
- Built and inspected by Glamanot measurednever built and inspected by Glama
- Trust100 / 100 · weight 9%
- License100
- Published by the vendor it integratesnot measurednot published by the vendor it integrates
- Weighted mean of the five
- 91.5
- × relevance: the keyword is tagged here
- 0.60
- × continuity: actively changing
- 1.00
- × evidence: widely adopted
- 1.00
- Composite score
- 54.9
Best for: Developers working with an existing MySQL database who need an MCP client to connect, run SELECT queries, execute writes, and inspect tables and schema.
It is an MCP server for MySQL that exposes five tools: connect_db, query for SELECT statements, execute for INSERT, UPDATE, or DELETE statements, list_tables, and describe_table. The server requires MySQL connection details, supplied either through MYSQL_HOST, MYSQL_USER, MYSQL_PASSWORD, and MYSQL_DATABASE environment variables or as a connection string argument.
GitHub stars169Stars / 30 days+1npm / typical week329PyPI / typical weekno attributed packageTools exposed5Last commit338 days agoCommits / 12 weeks0Maintenance gradeDTool descriptionsBScore 52.7: show every number behind it
- Adoption64 / 100 · weight 40%
- GitHub stars56
- npm downloads54
- Used through Glamanot measurednot used through Glama in the last 30 days
- Maintenance32 / 100 · weight 24%
- Last commit touching this server42
- Repository maintenance grade30
- Commit cadence5
- Momentum17 / 100 · weight 14%
- Stars gained, relative to size27
- Stars gained, absolute16
- npm download trend0
- Tool quality63 / 100 · weight 13%
- Tool description quality55
- Built and inspected by Glama100
- Trust100 / 100 · weight 9%
- License100
- Published by the vendor it integratesnot measurednot published by the vendor it integrates
- Weighted mean of the five
- 52.7
- × relevance: the keyword is dedicated here
- 1.00
- × continuity: actively changing
- 1.00
- × evidence: widely adopted
- 1.00
- Composite score
- 52.7
Best for: Connecting Claude Desktop to MySQL, PostgreSQL, or Redis through one npm-installed server: it runs over stdio and defaults to read-only access.
Universal DB MCP documents MCP stdio, SSE, and Streamable HTTP interfaces plus a REST API, taking database credentials through CLI flags, environment variables, or HTTP headers. The prerequisite worth knowing before installing it this afternoon is Node.js 20 or newer with the universal-db-mcp npm package, since connection details are passed at startup rather than configured in the repository.
GitHub stars940Stars / 30 days+6npm / typical week91PyPI / typical weekno attributed packageTools exposednever inspectedLast commit215 days agoCommits / 12 weeks0Maintenance gradeDTool descriptionsNot gradedScore 51.1: show every number behind it
- Adoption81 / 100 · weight 40%
- GitHub stars74
- npm downloads42
- Used through Glamanot measurednot used through Glama in the last 30 days
- Maintenance46 / 100 · weight 24%
- Last commit touching this server68
- Repository maintenance grade30
- Commit cadence5
- Momentum32 / 100 · weight 14%
- Stars gained, relative to size30
- Stars gained, absolute33
- npm download trend34
- Tool quality≈68 / 100 · weight 13%
- Tool description quality≈68tool descriptions not yet scored
- Built and inspected by Glamanot measurednever built and inspected by Glama
- Trust100 / 100 · weight 9%
- License100
- Published by the vendor it integratesnot measurednot published by the vendor it integrates
- Weighted mean of the five
- 65.5
- × relevance: the keyword is declared here
- 0.78
- × continuity: actively changing
- 1.00
- × evidence: widely adopted
- 1.00
- Composite score
- 51.1
Best for: TypeScript apps on PostgreSQL or MongoDB adopting Prisma 8: its installers add agent skills for scaffolding contracts and driving ORM changes.
The repository documents Prisma 8, a TypeScript ORM whose installers write a prisma-8.md primer and one SKILL.md per workflow into the skill directories read by Claude Code, Cursor, Copilot Agent, and Devin, with prisma orm init and prisma skills sync handling scaffolding. It requires Node.js 24 or newer, and its documented databases are PostgreSQL and MongoDB, so MySQL work falls outside what the README describes.
GitHub stars47,694Stars / 30 days+34npm / typical weekdownloads not countedPyPI / typical weekno attributed packageTools exposednever inspectedLast commit2 days agoCommits / 12 weeks460Maintenance gradeBTool descriptionsNot gradedScore 51.0: show every number behind it
- Adoption100 / 100 · weight 40%
- GitHub stars100
- npm downloadsnot measurednpm names no repository for dev-env, so its downloads cannot be attributed
- Used through Glamanot measurednot used through Glama in the last 30 days
- Maintenance95 / 100 · weight 24%
- Last commit touching this server100
- Repository maintenance grade80
- Commit cadence100
- Momentum32 / 100 · weight 14%
- Stars gained, relative to size11
- Stars gained, absolute62
- npm download trendnot measuredno download history for the selected registry
- Tool quality≈68 / 100 · weight 13%
- Tool description quality≈68tool descriptions not yet scored
- Built and inspected by Glamanot measurednever built and inspected by Glama
- Trust100 / 100 · weight 9%
- License100
- Published by the vendor it integrates100
- Weighted mean of the five
- 85.0
- × relevance: the keyword is tagged here
- 0.60
- × continuity: actively changing
- 1.00
- × evidence: widely adopted
- 1.00
- Composite score
- 51.0
Best for: Agents querying mixed databases and files under access policy: it exposes a GraphQL and MCP surface with query_catalog discovery and read-only boundaries.
GraphJin runs as a service that serves GraphQL, REST and an MCP endpoint at /api/v1/mcp, where the documented tools include query_catalog for schema discovery, graphql_help, ask_graphjin_agent, gj_watch and gj_artifacts, with queries compiled to SQL against MySQL among other sources. Its built-in agent needs a model API key (OpenAI, Anthropic or Google) in the environment, and its actual exposed tool list has not been independently inspected.
GitHub stars3,213Stars / 30 days+52npm / typical week420PyPI / typical weekno attributed packageTools exposednever inspectedLast committodayCommits / 12 weeks522Maintenance gradeATool descriptionsNot gradedScore 51.0: show every number behind it
- Adoption92 / 100 · weight 40%
- GitHub stars88
- npm downloads28downloads show none of the weekday rhythm human traffic has; halved
- Used through Glamanot measurednot used through Glama in the last 30 days
- Maintenance100 / 100 · weight 24%
- Last commit touching this server100
- Repository maintenance grade100
- Commit cadence100
- Momentum46 / 100 · weight 14%
- Stars gained, relative to size51
- Stars gained, absolute70
- npm download trend8
- Tool quality≈68 / 100 · weight 13%
- Tool description quality≈68tool descriptions not yet scored
- Built and inspected by Glamanot measurednever built and inspected by Glama
- Trust100 / 100 · weight 9%
- License100
- Published by the vendor it integrates100
- Weighted mean of the five
- 85.0
- × relevance: the keyword is tagged here
- 0.60
- × continuity: actively changing
- 1.00
- × evidence: widely adopted
- 1.00
- Composite score
- 51.0
Best for: Managing a hosted WhoDB platform project from an AI assistant: it exposes 155 tools covering datasets, ontologies, transforms, apps, bundles, and confirmation-gated writes.
WhoDB CLI ships an MCP server with 155 tools, mostly whodb_platform_* operations for hosted datasets, ontologies, transforms, apps, and project bundles, while the README documents browser, desktop, and terminal clients connecting to MySQL among other databases. Before choosing it, note that most tools target a selected hosted platform project via workspace host, org, and project, and that writes are two-step: they return a confirmation token that must be passed to whodb_platform_confirm within five minutes.
GitHub stars5,034Stars / 30 days+6npm / typical weekShips no npm packagePyPI / typical weekno attributed packageTools exposed155Last committodayCommits / 12 weeks602Maintenance gradeATool descriptionsBScore 48.9: show every number behind it
- Adoption93 / 100 · weight 40%
- GitHub stars93
- npm downloadsnot measuredno npm package
- Used through Glamanot measurednot used through Glama in the last 30 days
- Maintenance100 / 100 · weight 24%
- Last commit touching this server100
- Repository maintenance grade100
- Commit cadence100
- Momentum21 / 100 · weight 14%
- Stars gained, relative to size14
- Stars gained, absolute33
- npm download trendnot measuredno download history for the selected registry
- Tool quality66 / 100 · weight 13%
- Tool description quality57
- Built and inspected by Glama100
- Trust100 / 100 · weight 9%
- License100
- Published by the vendor it integrates100
- Weighted mean of the five
- 81.5
- × relevance: the keyword is tagged here
- 0.60
- × continuity: actively changing
- 1.00
- × evidence: widely adopted
- 1.00
- Composite score
- 48.9
- 16
Best for: Multi-agent workflows that need MySQL updates without lost updates: it provides optimistic concurrency tools with _version checks and conditional updates.
MySQL MCP Server exposes 43 tools for read and write queries, transactions, schema creation and indexes, JSON manipulation, versioning, and pattern searches, and its README documents HTTP transport, resources, and prompts. It is distributed as an npm package (@neverinfamous/mysql-mcp) and a Docker image, so installing it assumes Node/npm or Docker.
GitHub stars11Stars / 30 days0npm / typical week70PyPI / typical weekno attributed packageTools exposed43Last commit61 days agoCommits / 12 weeks1,244Maintenance gradeATool descriptionsBScore 48.4: show every number behind it
- Adoption43 / 100 · weight 40%
- GitHub stars27
- npm downloads39
- Used through Glamanot measurednot used through Glama in the last 30 days
- Maintenance93 / 100 · weight 24%
- Last commit touching this server88dated from the last commit on the default branch, re-read from GitHub at publication; github.com shows a push 5 days ago, which counts every ref; the stored date would have published 5 days ago
- Repository maintenance grade100
- Commit cadence100
- Momentum0 / 100 · weight 14%
- Stars gained, relative to size0
- Stars gained, absolute0
- npm download trend0
- Tool quality63 / 100 · weight 13%
- Tool description quality55
- Built and inspected by Glama100
- Trust100 / 100 · weight 9%
- License100
- Published by the vendor it integratesnot measurednot published by the vendor it integrates
- Weighted mean of the five
- 56.9
- × relevance: the keyword is dedicated here
- 1.00
- × continuity: actively changing
- 1.00
- × evidence: modest but real audience
- 0.85
- Composite score
- 48.4
Best for: Read-only data investigation against predefined MySQL environments: it exposes query, info and environments tools and has no write tools.
The server exposes three tools (query, info and environments) that run read-only SELECT, SHOW and DESCRIBE statements against MySQL databases configured through environment variables, with optional SSL and query timeouts. Before choosing it, note that environment names are fixed to local, development, staging and production with no custom names allowed, and that credentials are supplied directly in the MCP configuration's env block.
GitHub stars13Stars / 30 days0npm / typical week49PyPI / typical weekno attributed packageTools exposed3Last commit74 days agoCommits / 12 weeks4Maintenance gradeATool descriptionsAScore 46.4: show every number behind it
- Adoption40 / 100 · weight 40%
- GitHub stars29
- npm downloads36
- Used through Glamanot measurednot used through Glama in the last 30 days
- Maintenance81 / 100 · weight 24%
- Last commit touching this server88
- Repository maintenance grade100
- Commit cadence40
- Momentum0 / 100 · weight 14%
- Stars gained, relative to size0
- Stars gained, absolute0
- npm download trend0
- Tool quality76 / 100 · weight 13%
- Tool description quality68
- Built and inspected by Glama100
- Trust100 / 100 · weight 9%
- License100
- Published by the vendor it integratesnot measurednot published by the vendor it integrates
- Weighted mean of the five
- 54.6
- × relevance: the keyword is dedicated here
- 1.00
- × continuity: actively changing
- 1.00
- × evidence: modest but real audience
- 0.85
- Composite score
- 46.4
Best for: Read-only SQL against an AnalyticDB for MySQL cluster: it exposes execute_sql, get_query_plan and get_execution_plan, with execute_sql read-only unless write tools are explicitly enabled.
Adb MySQL MCP Server exposes three tools, execute_sql, get_query_plan and get_execution_plan, and connects either directly to an AnalyticDB for MySQL cluster through ADB_MYSQL_* settings or by creating a temporary database account via Alibaba Cloud OpenAPI. It requires Python 3.13 or later and uv, and execute_sql stays read-only unless ENABLE_SQL_WRITE_TOOLS is set to true; the separate openapi tool group for cluster, whitelist and account management must be enabled explicitly and assumes an Alibaba Cloud AccessKey.
GitHub stars32Stars / 30 days0npm / typical weekShips no npm packagePyPI / typical week73adb-mysql-mcp-serverTools exposed3Last commit81 days agoCommits / 12 weeks4Maintenance gradeCTool descriptionsBScore 43.8: show every number behind it
- Adoption45 / 100 · weight 40%
- GitHub stars38
- PyPI downloads40
- Used through Glamanot measurednot used through Glama in the last 30 days
- Maintenance70 / 100 · weight 24%
- Last commit touching this server88
- Repository maintenance grade55
- Commit cadence40
- Momentum0 / 100 · weight 14%
- Stars gained, relative to size0
- Stars gained, absolute0
- PyPI download trendnot measuredno download history for the selected registry
- Tool quality58 / 100 · weight 13%
- Tool description quality50
- Built and inspected by Glama100
- Trust100 / 100 · weight 9%
- License100
- Published by the vendor it integrates100
- Weighted mean of the five
- 51.5
- × relevance: the keyword is dedicated here
- 1.00
- × continuity: actively changing
- 1.00
- × evidence: modest but real audience
- 0.85
- Composite score
- 43.8
Best for: Governed read-write MySQL access for AI agents: it exposes eight MCP tools for query, insert, update and delete, gated by per-table role-based access.
Faucet connects to MySQL and other SQL databases, introspects the schema, and exposes eight MCP tools at /mcp covering service and table listing, table description, query, insert, update, delete, and raw SQL. Before choosing it, note that deletes and updates require a filter, raw SQL runs only on services with raw_sql_allowed enabled, and no npm or PyPI package is published, so it runs as a Go binary or Docker image.
GitHub stars152Stars / 30 daysno snapshot historynpm / typical weekShips no npm packagePyPI / typical weekno attributed packageTools exposed8Last committodayCommits / 12 weeks26Maintenance gradeATool descriptionsAScore 43.5: show every number behind it
- Adoption55 / 100 · weight 40%
- GitHub stars55
- npm downloadsnot measuredno npm package
- Used through Glamanot measurednot used through Glama in the last 30 days
- Maintenance97 / 100 · weight 24%
- Last commit touching this server100
- Repository maintenance grade100
- Commit cadence85
- Momentum≈0 / 100 · weight 14%
- Stars gained, relative to sizenot measuredno snapshot history yet
- Stars gained, absolutenot measuredno snapshot history yet
- npm download trendnot measuredno download history for the selected registry
- Tool quality88 / 100 · weight 13%
- Tool description quality80
- Built and inspected by Glama100
- Trust100 / 100 · weight 9%
- License100
- Published by the vendor it integratesnot measurednot published by the vendor it integrates
- Weighted mean of the five
- 65.6
- × relevance: the keyword is declared here
- 0.78
- × continuity: actively changing
- 1.00
- × evidence: modest but real audience
- 0.85
- Composite score
- 43.5
- 20
Best for: Read-only inspection of a MySQL schema from an LLM: it exposes a query tool limited to SELECT statements and publishes table schemas as resources.
The server runs over stdio against a MySQL database and documents a query tool that takes a SQL string executed inside a READ ONLY transaction, alongside resources that publish per-table JSON schema with column names and data types. Setup requires passing a full mysql:// connection URI, credentials included, as a command argument, and the README states Node v18 or newer.
GitHub stars16Stars / 30 days+1npm / typical week88PyPI / typical weekno attributed packageTools exposednever inspectedLast commit153 days agoCommits / 12 weeks0Maintenance gradeDTool descriptionsNot gradedScore 42.7: show every number behind it
- Adoption46 / 100 · weight 40%
- GitHub stars31
- npm downloads41
- Used through Glamanot measurednot used through Glama in the last 30 days
- Maintenance46 / 100 · weight 24%
- Last commit touching this server68
- Repository maintenance grade30
- Commit cadence5
- Momentum22 / 100 · weight 14%
- Stars gained, relative to size38
- Stars gained, absolute16
- npm download trend0
- Tool quality≈68 / 100 · weight 13%
- Tool description quality≈68tool descriptions not yet scored
- Built and inspected by Glamanot measurednever built and inspected by Glama
- Trust100 / 100 · weight 9%
- License100
- Published by the vendor it integratesnot measurednot published by the vendor it integrates
- Weighted mean of the five
- 50.2
- × relevance: the keyword is dedicated here
- 1.00
- × continuity: actively changing
- 1.00
- × evidence: modest but real audience
- 0.85
- Composite score
- 42.7
Questions people ask
How do I choose between MySQL MCP Server and MCP Server for MySQL?
MySQL MCP Server (designcomputer/mysql_mcp_server) exposes 3 tools, its tool descriptions are graded A, and it had 7,280 PyPI downloads in a typical week. MCP Server for MySQL (benborla/mcp-server-mysql) offers read-only MySQL schema inspection and queries, has 2,157 stars on GitHub and 13,657 npm downloads in a typical week, and ships mysql_query and mysql://tables. Pick MySQL MCP Server for a 3-tool surface on PyPI; pick MCP Server for MySQL if you want an npm package and Claude Code read-only use.
What does MCP Server for MySQL require before it will write to my database?
Writes are disabled unless env flags are set. Without those flags it provides read-only access to MySQL databases, enabling LLMs to inspect database schemas and execute read-only queries. It ships mysql_query and mysql://tables, and it had a commit 83 days ago and 4 commits in the last 12 weeks.
Does DBHub only work with MySQL?
No. DBHub is a universal database MCP server connecting to MySQL, PostgreSQL, SQLite, DuckDB and etc. Its README documents execute_sql and search_objects, plus optional explain_sql and health_check tools. It had 3,639 stars on GitHub, gained 125 stars per 30 days, and a commit 5 days ago.
What should I check before using MySQL MCP Server (neverinfamous/mysql-mcp) with multiple agents?
It provides optimistic concurrency tools with _version checks and conditional updates, which matters for multi-agent workflows that need MySQL updates without lost updates. It exposes 43 tools, and its tool descriptions are graded B, so review the tool surface before exposing it. It had a commit 61 days ago and 1,244 commits in the last 12 weeks.
Is Faucet suitable for governed read-write MySQL access?
Yes. Faucet is for governed read-write MySQL access for AI agents. It exposes eight MCP tools for query, insert, update and delete, gated by per-table role-based access, and its tool descriptions are graded A. It had a commit 0 days ago and 26 commits in the last 12 weeks.
Which server should I use for read-only MySQL querying?
MCP Server for MySQL (benborla/mcp-server-mysql) provides read-only access, ships mysql_query and mysql://tables, and has writes disabled unless env flags are set. MySQL Database Access (dpflucas/mysql-mcp-server) also provides read-only access and exposes four read-only tools for listing databases, tables, and schemas, and running SELECT queries. Choose MCP Server for MySQL if you need an npm package and Claude Code; choose MySQL Database Access if you want a 4-tool read-only surface with tool descriptions graded A.