20 Best MySQL MCP Servers, Compared (September 2026)
The short answer
For most readers, the server to install is MySQL MCP Server (designcomputer/mysql_mcp_server). It is a community favourite, had a commit 43 days ago, exposes three tools (execute_sql, get_schema_info, get_table_sample) with a tool description grade of A, and has a PyPI package with 9,926 downloads in a typical week. If your goal is strictly read-only access from Claude Code, MCP Server for MySQL (benborla/mcp-server-mysql) is the better answer: it is read-only, a community favourite, and its npm package had 13,650 downloads in a typical week.
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 : Developers wiring an AI assistant to MySQL for schema inspection and ad-hoc queries: it exposes execute_sql, get_schema_info, and get_table_sample.
- 2MCP Server for MySQL : Read-only schema inspection and querying of a MySQL database from Claude Code: it documents a mysql_query tool and a mysql://tables resource.
- 3DBHub : Local development or multi-database consolidation: it exposes a single MCP gateway to PostgreSQL, MySQL, SQL Server, MariaDB, and SQLite.
- 4MCP MariaDB Server : A MariaDB app that needs both SQL access and embedding-based search through one MCP server: it exposes query, schema, and vector store tools.
- 5DBCode : For MySQL users already working in VS Code/Cursor with DBCode connections: its built-in MCP server gives AI agents schema access and query execution.
Which one, for your situation
| Your situation | What to use |
|---|---|
| I need read-only MySQL access for an AI assistant | Use MCP Server for MySQL (benborla/mcp-server-mysql), because it is read-only, a community favourite, and had 13,650 npm downloads in a typical week. |
| I need one server for MySQL plus Postgres, SQL Server, or SQLite | Use DBHub (bytebase/dbhub), because it exposes a single MCP gateway to PostgreSQL, MySQL, SQL Server, MariaDB, and SQLite and had a commit 0 days ago with 77 commits in the last 12 weeks. |
| I need auditable DDL and operation logs for a shared MySQL | Use MCP MySQL Server (liliangshan/mcp-server-mysql), because it combines sql_query, permission checks, and operation log tools, though it is profiled Abandoned but popular and had 0 commits in the last 12 weeks. |
| I need MySQL in production with OAuth 2.1 and connection pooling | Use MySQL MCP Server (neverinfamous/mysql-mcp) for production MySQL workloads that require OAuth 2.1 and connection pooling; it is profiled Steady, exposes 43 tools, and had a commit 27 days ago. |
| I need natural language access to many database types | Use dbx (t8y2/dbx), because it is a community favourite universal database manager that provides natural language queries and database management through MCP and had a commit 0 days ago. |
| I need read-only investigation across fixed environments | Use MySQL Query MCP Server (devakone/mysql-query-mcp-server), because it exposes query, info, and environments tools, blocks write operations, and is profiled Steady with a commit 40 days ago. |
Top MCP servers for MySQL
| Best for | Profile | ||||||
|---|---|---|---|---|---|---|---|
| 1 | Developers wiring an AI assistant to MySQL for schema inspection and ad-hoc queries: it exposes execute_sql, get_schema_info, and get_table_sample. | Community favourite | 1,389 | +31 | 43 days ago | 88.4 | |
| 2 | Read-only schema inspection and querying of a MySQL database from Claude Code: it documents a mysql_query tool and a mysql://tables resource. | Community favourite | 2,119 | +75 | 49 days ago | 83.4 | |
| 3 | Local development or multi-database consolidation: it exposes a single MCP gateway to PostgreSQL, MySQL, SQL Server, MariaDB, and SQLite. | Community favourite | 3,493 | +168 | today | 69.8 | |
| 4 | A MariaDB app that needs both SQL access and embedding-based search through one MCP server: it exposes query, schema, and vector store tools. | Steady | 202 | +12 | 35 days ago | 66.5 | |
| 5 | For MySQL users already working in VS Code/Cursor with DBCode connections: its built-in MCP server gives AI agents schema access and query execution. | Community favourite | 347 | +17 | yesterday | 59.4 | |
| 6 | Teams running several MySQL and PostgreSQL databases at once: it generates per-database query, execute, transaction, schema, and performance tools. | Community favourite | 423 | +12 | 21 days ago | 58.6 | |
| 7 | When you need to manage and query multiple database types via natural language: it provides an MCP server for universal database access. | Community favourite | 19,200 | +4,291 | today | 57.3 | |
| 8 | Shared MySQL environments needing auditable DDL and DML: it combines sql_query, permission checks, and operation log tools. | Abandoned but popular | 14 | 0 | 115 days ago | 55.7 | |
| 9 | Connecting Gemini CLI, Claude Code, or Codex to a Cloud SQL MySQL database: it provides prebuilt generic tools and a custom tools framework. | Community favourite | 16,371 | +200 | today | 54.3 | |
| 10 | Production MySQL workloads requiring OAuth 2.1 and connection pooling: this server offers both. | Steady | 10 | +1 | 27 days ago | 53.0 | |
| 11 | A developer who needs to inspect and modify MySQL data from a terminal: it exposes query, schema, and write-confirmation tools through a CLI and MCP server. | Community favourite | 5,024 | +19 | today | 52.6 | |
| 12 | For read-only MySQL schema exploration from Claude Desktop: it connects through MCP with a default read-only mode for natural-language queries. | Abandoned but popular | 929 | +20 | 182 days ago | 51.9 | |
| 13 | Teams adopting Prisma 8 on new projects: it scaffolds apps, wires PostgreSQL or MongoDB, and installs agent skills for AI-driven ORM workflows. | Community favourite | 47,603 | +67 | today | 51.4 | |
| 14 | Teams that want one governed GraphQL and MCP surface over MySQL plus other data systems: it compiles natural language to SQL with schema discovery. | Community favourite | 3,165 | +29 | 3 days ago | 49.8 | |
| 15 | For an AI assistant that must run both SELECT and write queries against MySQL: it exposes query, execute, list_tables, and describe_table with prepared statement support. | Abandoned but popular | 168 | 0 | 305 days ago | 48.8 | |
| 16 | Read-only schema inspection and SELECT queries against a MySQL database, enforced by SQL validation and READ ONLY transactions. | Dormant | 14 | 0 | 119 days ago | 43.1 | |
| 17 | Natural-language querying of MySQL and PostgreSQL databases: it turns plain English into SQL via XiYanSQL and returns results. | Abandoned but popular | 240 | -1 | 215 days ago | 40.8 | |
| 18 | Managing several MySQL databases from an AI assistant while keeping credentials out of the model: it supports multiple header-configured connections and dynamic switching. | Dormant | 81 | 0 | 272 days ago | 40.1 | |
| 19 | When one MCP server must cover MySQL alongside Postgres, Redis, Elasticsearch, MongoDB, and LDAP: its per-connection read-only mode makes mixed read/write environments safe. | Steady | 82 | 0 | 11 days ago | 39.0 | |
| 20 | For teams that need read-only MySQL investigation across fixed environments: it exposes query, info, and environments tools and blocks write operations. | Steady | 13 | 0 | 40 days ago | 38.9 |
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: Developers wiring an AI assistant to MySQL for schema inspection and ad-hoc queries: it exposes execute_sql, get_schema_info, and get_table_sample.
The server exposes execute_sql, get_schema_info, and get_table_sample, and supports STDIO and SSE transports, SSH tunneling, and optional multi-database mode. It accepts only single SQL statements, so multi-statement queries such as USE db; SELECT ... are not supported.
GitHub stars1,389Stars / 30 days+31npm / typical weekShips no npm packagePyPI / typical week9.9Kmysql-mcp-serverTools exposed3Last commit43 days agoCommits / 12 weeks5Maintenance gradeATool descriptionsAScore 88.4: show every number behind it
- Adoption97 / 100 · weight 40%
- GitHub stars79
- PyPI downloads85
- 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
- Momentum47 / 100 · weight 14%
- Stars gained, relative to size59
- Stars gained, absolute61
- PyPI download trend9
- 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
- 88.4
- × relevance: the keyword is dedicated here
- 1.00
- × continuity: actively changing
- 1.00
- × evidence: widely adopted
- 1.00
- Composite score
- 88.4
Best for: Read-only schema inspection and querying of a MySQL database from Claude Code: it documents a mysql_query tool and a mysql://tables resource.
Its README documents a mysql_query tool for executing SQL and a mysql://tables resource listing tables and column metadata. It requires Node.js v20+ and MySQL 5.7+ (8.0+ recommended).
GitHub stars2,119Stars / 30 days+75npm / typical week13.7KPyPI / typical weekno attributed packageTools exposednever inspectedLast commit49 days agoCommits / 12 weeks7Maintenance gradeCTool descriptionsNot gradedScore 83.4: 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
- Maintenance75 / 100 · weight 24%
- Last commit touching this server88
- Repository maintenance grade55
- Commit cadence65
- Momentum57 / 100 · weight 14%
- Stars gained, relative to size76
- Stars gained, absolute76
- npm download trend0
- Tool quality≈65 / 100 · weight 13%
- Tool description quality≈65tool 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
- 83.4
- × relevance: the keyword is dedicated here
- 1.00
- × continuity: actively changing
- 1.00
- × evidence: widely adopted
- 1.00
- Composite score
- 83.4
Best for: Local development or multi-database consolidation: it exposes a single MCP gateway to PostgreSQL, MySQL, SQL Server, MariaDB, and SQLite.
DBHub is an MCP server that connects to PostgreSQL, MySQL, SQL Server, MariaDB, and SQLite, with README-documented tools including execute_sql, search_objects, opt-in explain_sql and health_check, and configurable custom tools. Before choosing it, note that npx installation requires Node.js >= 22.5.0 because DBHub uses the built-in node:sqlite module.
GitHub stars3,493Stars / 30 days+168npm / typical weekdownloads not countedPyPI / typical weekno attributed packageTools exposednever inspectedLast committodayCommits / 12 weeks77Maintenance gradeATool descriptionsNot gradedScore 69.8: 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
- Momentum90 / 100 · weight 14%
- Stars gained, relative to size90
- Stars gained, absolute90
- npm download trendnot measuredno download history for the selected registry
- Tool quality≈65 / 100 · weight 13%
- Tool description quality≈65tool 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
- 89.5
- × relevance: the keyword is declared here
- 0.78
- × continuity: actively changing
- 1.00
- × evidence: widely adopted
- 1.00
- Composite score
- 69.8
Best for: A MariaDB app that needs both SQL access and embedding-based search through one MCP server: it exposes query, schema, and vector store tools.
It implements an MCP interface for MariaDB with tools to list databases and tables, fetch table schemas, execute SQL, create databases, and manage vector stores if an embedding provider is configured. Before choosing it, know that it has no published npm or PyPI package, and execute_sql is read-only only when MCP_READ_ONLY is enabled.
GitHub stars202Stars / 30 days+12npm / typical weekShips no npm packagePyPI / typical weekno attributed packageTools exposednever inspectedLast commit35 days agoCommits / 12 weeks2Maintenance gradeDTool descriptionsNot gradedScore 66.5: 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
- Maintenance71 / 100 · weight 24%
- Last commit touching this server100
- Repository maintenance grade30
- Commit cadence40
- Momentum65 / 100 · weight 14%
- Stars gained, relative to size77
- Stars gained, absolute45
- npm download trendnot measuredno download history for the selected registry
- Tool quality≈65 / 100 · weight 13%
- Tool description quality≈65tool 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
- 66.5
- × relevance: the keyword is dedicated here
- 1.00
- × continuity: actively changing
- 1.00
- × evidence: widely adopted
- 1.00
- Composite score
- 66.5
Best for: For MySQL users already working in VS Code/Cursor with DBCode connections: its built-in MCP server gives AI agents schema access and query execution.
DBCode is a VS Code extension that can run an MCP server exposing configured databases, schemas, and query execution to AI agents. It is not a standalone server: it depends on the DBCode extension, an existing editor connection, and per-connection AI permissions.
GitHub stars347Stars / 30 days+17npm / typical weekdownloads not countedPyPI / typical weekno attributed packageTools exposednever inspectedLast commityesterdayCommits / 12 weeks71Maintenance gradeATool descriptionsNot gradedScore 59.4: 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
- Momentum66 / 100 · weight 14%
- Stars gained, relative to size76
- Stars gained, absolute51
- npm download trendnot measuredno download history for the selected registry
- Tool quality≈65 / 100 · weight 13%
- Tool description quality≈65tool 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
- 76.2
- × relevance: the keyword is declared here
- 0.78
- × continuity: actively changing
- 1.00
- × evidence: widely adopted
- 1.00
- Composite score
- 59.4
Best for: Teams running several MySQL and PostgreSQL databases at once: it generates per-database query, execute, transaction, schema, and performance tools.
It is a Go MCP server that connects to multiple databases concurrently and auto-generates database-specific tools for querying, executing statements, managing transactions, exploring schemas, and analyzing performance. Before choosing it, note that the README also lists SQLite and Oracle in its multi-database examples, but the description and supported-databases scope only confirm MySQL and PostgreSQL.
GitHub stars423Stars / 30 days+12npm / typical weekShips no npm packagePyPI / typical weekno attributed packageTools exposednever inspectedLast commit21 days agoCommits / 12 weeks102Maintenance gradeATool descriptionsNot gradedScore 58.6: show every number behind it
- Adoption66 / 100 · weight 40%
- GitHub stars66
- 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
- Momentum53 / 100 · weight 14%
- Stars gained, relative to size59
- Stars gained, absolute44
- npm download trendnot measuredno download history for the selected registry
- Tool quality≈65 / 100 · weight 13%
- Tool description quality≈65tool 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
- 75.1
- × relevance: the keyword is declared here
- 0.78
- × continuity: actively changing
- 1.00
- × evidence: widely adopted
- 1.00
- Composite score
- 58.6
Best for: When you need to manage and query multiple database types via natural language: it provides an MCP server for universal database access.
The README documents a desktop app, Docker, CLI, a built-in AI assistant, and an MCP server that handles natural language queries and database management. Its MCP tool list has not been inspected, so you must check the repository to see exactly what tools it exposes before choosing it.
GitHub stars19,200Stars / 30 days+4,291npm / typical weekdownloads not countedPyPI / typical weekno attributed packageTools exposednever inspectedLast committodayCommits / 12 weeks4,210Maintenance gradeATool descriptionsNot gradedScore 57.3: 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≈65 / 100 · weight 13%
- Tool description quality≈65tool 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
- 95.5
- × relevance: the keyword is tagged here
- 0.60
- × continuity: actively changing
- 1.00
- × evidence: widely adopted
- 1.00
- Composite score
- 57.3
Best for: Shared MySQL environments needing auditable DDL and DML: it combines sql_query, permission checks, and operation log tools.
The server exposes five tools: sql_query for DDL/DML, get_database_info, get_operation_logs, check_permissions, and get_ddl_sql_logs, and its README documents npm installation with environment-variable configuration. It assumes a MySQL connection configured through MYSQL_HOST, MYSQL_PORT, MYSQL_USER, MYSQL_PASSWORD, and MYSQL_DATABASE, and it is available as an npm package, not PyPI.
GitHub stars14Stars / 30 days0npm / typical week326PyPI / typical weekno attributed packageTools exposed5Last commit115 days agoCommits / 12 weeks0Maintenance gradeCTool descriptionsBScore 55.7: show every number behind it
- Adoption58 / 100 · weight 40%
- GitHub stars29
- npm downloads53
- Used through Glamanot measurednot used through Glama in the last 30 days
- Maintenance63 / 100 · weight 24%
- Last commit touching this server88
- Repository maintenance grade55
- Commit cadence5
- Momentum1 / 100 · weight 14%
- Stars gained, relative to size0
- Stars gained, absolute0
- npm download trend6
- 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
- 55.7
- × relevance: the keyword is dedicated here
- 1.00
- × continuity: actively changing
- 1.00
- × evidence: widely adopted
- 1.00
- Composite score
- 55.7
Best for: Connecting Gemini CLI, Claude Code, or Codex to a Cloud SQL MySQL database: it provides prebuilt generic tools and a custom tools framework.
MCP Toolbox for Databases connects AI agents, IDEs, and applications to databases over MCP; its README documents prebuilt generic tools (list_tables, execute_sql) and a framework for building custom database tools. Before choosing it for MySQL, note that the quick start's only run command shown in the README is for PostgreSQL, so check the Prebuilt Tools Reference for the Cloud SQL MySQL configuration.
GitHub stars16,371Stars / 30 days+200npm / typical weekShips no npm packagePyPI / typical weekno attributed packageTools exposednever inspectedLast committodayCommits / 12 weeks238Maintenance gradeATool descriptionsNot gradedScore 54.3: 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
- Momentum64 / 100 · weight 14%
- Stars gained, relative to size45
- Stars gained, absolute93
- npm download trendnot measuredno download history for the selected registry
- Tool quality≈65 / 100 · weight 13%
- Tool description quality≈65tool 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
- 90.5
- × relevance: the keyword is tagged here
- 0.60
- × continuity: actively changing
- 1.00
- × evidence: widely adopted
- 1.00
- Composite score
- 54.3
- 10
Best for: Production MySQL workloads requiring OAuth 2.1 and connection pooling: this server offers both.
It exposes 43 tools for CRUD, JSON operations, transactions, optimistic versioning, and schema management, plus resources for schema, performance, process lists, replication, and InnoDB diagnostics. It is built for MCP v2 streamable or stateless HTTP transport.
GitHub stars10Stars / 30 days+1npm / typical week81PyPI / typical weekno attributed packageTools exposed43Last commit27 days agoCommits / 12 weeks2,582Maintenance gradeATool descriptionsBScore 53.0: show every number behind it
- Adoption45 / 100 · weight 40%
- GitHub stars26
- npm downloads41
- 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
- Momentum24 / 100 · weight 14%
- Stars gained, relative to size36
- Stars gained, absolute14
- npm download trend12
- 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
- 62.4
- × relevance: the keyword is dedicated here
- 1.00
- × continuity: actively changing
- 1.00
- × evidence: modest but real audience
- 0.85
- Composite score
- 53.0
Best for: A developer who needs to inspect and modify MySQL data from a terminal: it exposes query, schema, and write-confirmation tools through a CLI and MCP server.
WhoDB CLI exposes 12 MCP tools for listing connections, schemas, tables, and columns, running queries, explaining plans, diffing schemas, auditing data quality, and confirming pending writes. It is a Go and TypeScript project that also ships as a browser app, desktop app, and Docker image, so the MCP server is one interface to a larger self-hosted database workspace.
GitHub stars5,024Stars / 30 days+19npm / typical weekShips no npm packagePyPI / typical weekno attributed packageTools exposed12Last committodayCommits / 12 weeks550Maintenance gradeATool descriptionsAScore 52.6: 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
- Momentum36 / 100 · weight 14%
- Stars gained, relative to size24
- Stars gained, absolute52
- npm download trendnot measuredno download history for the selected registry
- Tool quality98 / 100 · weight 13%
- Tool description quality90
- Built and inspected by Glama100
- Trust100 / 100 · weight 9%
- License100
- Published by the vendor it integrates100
- Weighted mean of the five
- 87.7
- × relevance: the keyword is tagged here
- 0.60
- × continuity: actively changing
- 1.00
- × evidence: widely adopted
- 1.00
- Composite score
- 52.6
Best for: For read-only MySQL schema exploration from Claude Desktop: it connects through MCP with a default read-only mode for natural-language queries.
It is a Node.js MCP server that installs via npm and exposes MCP stdio, MCP SSE, Streamable HTTP, and REST API interfaces for natural-language database access. It requires Node.js 20+ and installation as a global npm package.
GitHub stars929Stars / 30 days+20npm / typical week126PyPI / typical weekno attributed packageTools exposednever inspectedLast commit182 days agoCommits / 12 weeks0Maintenance gradeDTool descriptionsNot gradedScore 51.9: show every number behind it
- Adoption81 / 100 · weight 40%
- GitHub stars74
- npm downloads45
- 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
- Momentum41 / 100 · weight 14%
- Stars gained, relative to size56
- Stars gained, absolute53
- npm download trend0
- Tool quality≈65 / 100 · weight 13%
- Tool description quality≈65tool 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
- 66.5
- × relevance: the keyword is declared here
- 0.78
- × continuity: actively changing
- 1.00
- × evidence: widely adopted
- 1.00
- Composite score
- 51.9
Best for: Teams adopting Prisma 8 on new projects: it scaffolds apps, wires PostgreSQL or MongoDB, and installs agent skills for AI-driven ORM workflows.
The server is the Prisma 8 ORM toolchain, documented as scaffolding projects, initializing Prisma in existing apps, and installing agent skills for AI-driven database workflows. Its tool list was not measured, and it requires Node.js 24 or newer, so it is not a drop-in for older runtimes.
GitHub stars47,603Stars / 30 days+67npm / typical weekdownloads not countedPyPI / typical weekno attributed packageTools exposednever inspectedLast committodayCommits / 12 weeks357Maintenance gradeBTool descriptionsNot gradedScore 51.4: 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
- Momentum39 / 100 · weight 14%
- Stars gained, relative to size15
- Stars gained, absolute74
- npm download trendnot measuredno download history for the selected registry
- Tool quality≈65 / 100 · weight 13%
- Tool description quality≈65tool 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
- 85.7
- × relevance: the keyword is tagged here
- 0.60
- × continuity: actively changing
- 1.00
- × evidence: widely adopted
- 1.00
- Composite score
- 51.4
Best for: Teams that want one governed GraphQL and MCP surface over MySQL plus other data systems: it compiles natural language to SQL with schema discovery.
GraphJin is a compiler and runtime that exposes databases, warehouses, files, and workflows through GraphQL and MCP, with tools for catalog discovery, query validation, and runtime status. It supports MySQL among many systems, but the MCP tool list was not measured, so verify the actual exposed tools before relying on it for a specific workflow.
GitHub stars3,165Stars / 30 days+29npm / typical week518PyPI / typical weekno attributed packageTools exposednever inspectedLast commit3 days agoCommits / 12 weeks502Maintenance gradeATool descriptionsNot gradedScore 49.8: show every number behind it
- Adoption92 / 100 · weight 40%
- GitHub stars88
- npm downloads29downloads 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
- Momentum35 / 100 · weight 14%
- Stars gained, relative to size38
- Stars gained, absolute59
- npm download trend0
- Tool quality≈65 / 100 · weight 13%
- Tool description quality≈65tool 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
- 83.0
- × relevance: the keyword is tagged here
- 0.60
- × continuity: actively changing
- 1.00
- × evidence: widely adopted
- 1.00
- Composite score
- 49.8
Best for: For an AI assistant that must run both SELECT and write queries against MySQL: it exposes query, execute, list_tables, and describe_table with prepared statement support.
The server exposes five tools: connect_db, query for SELECT, execute for INSERT, UPDATE, or DELETE, list_tables, and describe_table, with optional prepared statement parameters documented for query and execute. Before choosing it, note that its connection configuration comes either from a mysql:// URL passed as an argument or from MYSQL_HOST, MYSQL_USER, MYSQL_PASSWORD, and MYSQL_DATABASE environment variables.
GitHub stars168Stars / 30 days0npm / typical week364PyPI / typical weekno attributed packageTools exposed5Last commit305 days agoCommits / 12 weeks0Maintenance gradeFTool descriptionsBScore 48.8: show every number behind it
- Adoption64 / 100 · weight 40%
- GitHub stars56
- npm downloads55
- Used through Glamanot measurednot used through Glama in the last 30 days
- Maintenance25 / 100 · weight 24%
- Last commit touching this server42
- Repository maintenance grade5
- Commit cadence5
- 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
- 48.8
- × relevance: the keyword is dedicated here
- 1.00
- × continuity: actively changing
- 1.00
- × evidence: widely adopted
- 1.00
- Composite score
- 48.8
- 16
Best for: Read-only schema inspection and SELECT queries against a MySQL database, enforced by SQL validation and READ ONLY transactions.
The server exposes a single query tool and table schema resources, all executed within READ ONLY transactions. Its tool list was not measured at publication, so verify the installed package before relying on it.
GitHub stars14Stars / 30 days0npm / typical week123PyPI / typical weekno attributed packageTools exposednever inspectedLast commit119 days agoCommits / 12 weeks0Maintenance gradeDTool descriptionsNot gradedScore 43.1: show every number behind it
- Adoption49 / 100 · weight 40%
- GitHub stars29
- npm downloads45
- Used through Glamanot measurednot used through Glama in the last 30 days
- Maintenance57 / 100 · weight 24%
- Last commit touching this server88
- Repository maintenance grade30
- Commit cadence5
- Momentum0 / 100 · weight 14%
- Stars gained, relative to size0
- Stars gained, absolute0
- npm download trend0
- Tool quality≈65 / 100 · weight 13%
- Tool description quality≈65tool 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
- 50.7
- × relevance: the keyword is dedicated here
- 1.00
- × continuity: actively changing
- 1.00
- × evidence: modest but real audience
- 0.85
- Composite score
- 43.1
Best for: Natural-language querying of MySQL and PostgreSQL databases: it turns plain English into SQL via XiYanSQL and returns results.
It exposes a get_data tool that converts natural language to SQL and executes it, plus resources that list databases and sample table contents. It requires Python 3.11+, and its default remote mode needs an API key, while the local mode uses a local model instead.
GitHub stars240Stars / 30 days-1npm / typical weekShips no npm packagePyPI / typical weekdownloads not countedxiyan-mcp-serverTools exposednever inspectedLast commit215 days agoCommits / 12 weeks0Maintenance gradeDTool descriptionsNot gradedScore 40.8: show every number behind it
- Adoption60 / 100 · weight 40%
- GitHub stars60
- npm downloadsnot measuredno npm package
- 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
- Momentum0 / 100 · weight 14%
- Stars gained, relative to size0
- Stars gained, absolute0
- npm download trendnot measuredno download history for the selected registry
- Tool quality≈65 / 100 · weight 13%
- Tool description quality≈65tool 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
- 52.3
- × relevance: the keyword is declared here
- 0.78
- × continuity: actively changing
- 1.00
- × evidence: widely adopted
- 1.00
- Composite score
- 40.8
- 18
Best for: Managing several MySQL databases from an AI assistant while keeping credentials out of the model: it supports multiple header-configured connections and dynamic switching.
This server provides a StreamableHTTP MCP endpoint for MySQL, and its README documents connection-management tools and SQL query tools. Before choosing it, the key requirement is Node.js 18+ and MySQL 5.7+ or 8.0+, with startup from a cloned TypeScript source tree after npm install and build.
GitHub stars81Stars / 30 days0npm / typical week14PyPI / typical weekno attributed packageTools exposednever inspectedLast commit272 days agoCommits / 12 weeks0Maintenance gradeCTool descriptionsNot gradedScore 40.1: show every number behind it
- Adoption52 / 100 · weight 40%
- GitHub stars48
- npm downloads25
- Used through Glamanot measurednot used through Glama in the last 30 days
- Maintenance38 / 100 · weight 24%
- Last commit touching this server42
- Repository maintenance grade55
- Commit cadence5
- Momentum0 / 100 · weight 14%
- Stars gained, relative to size0
- Stars gained, absolute0
- npm download trend0
- Tool quality≈65 / 100 · weight 13%
- Tool description quality≈65tool 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
- 47.2
- × relevance: the keyword is dedicated here
- 1.00
- × continuity: actively changing
- 1.00
- × evidence: modest but real audience
- 0.85
- Composite score
- 40.1
Best for: When one MCP server must cover MySQL alongside Postgres, Redis, Elasticsearch, MongoDB, and LDAP: its per-connection read-only mode makes mixed read/write environments safe.
Exposed tools cover system management (db_status, db_reload_config), Postgres queries and schema inspection, and Redis key operations, while the README documents MySQL, Elasticsearch, MongoDB, and LDAP support and setup by environment variables. The thing to know before choosing it: it runs through npx/npm and loads database drivers on demand, so a local --no-optional install requires the driver for each engine in use.
GitHub stars82Stars / 30 days0npm / typical weekdownloads not countedPyPI / typical weekno attributed packageTools exposed100Last commit11 days agoCommits / 12 weeks43Maintenance gradeBTool descriptionsBScore 39.0: show every number behind it
- Adoption48 / 100 · weight 40%
- GitHub stars48
- npm downloadsnot measurednpm publishes mcp-server-db from Nam088/mcp-database-server-v2
- 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
- Momentum0 / 100 · weight 14%
- Stars gained, relative to size0
- Stars gained, absolute0
- npm download trendnot measuredno download history for the selected registry
- Tool quality61 / 100 · weight 13%
- Tool description quality53
- 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
- 58.8
- × relevance: the keyword is declared here
- 0.78
- × continuity: actively changing
- 1.00
- × evidence: modest but real audience
- 0.85
- Composite score
- 39.0
Best for: For teams that need read-only MySQL investigation across fixed environments: it exposes query, info, and environments tools and blocks write operations.
The server exposes three tools: query for read-only SQL, info for database metadata, and environments for listing available MySQL environments. It requires configuration of at least one of four predefined environments (local, development, staging, production) via environment variables, and it does not support custom environment names.
GitHub stars13Stars / 30 days0npm / typical week42PyPI / typical weekno attributed packageTools exposed3Last commit40 days agoCommits / 12 weeks4Maintenance gradeATool descriptionsAScore 38.9: show every number behind it
- Adoption39 / 100 · weight 40%
- GitHub stars29
- npm downloads35
- Used through Glamanot measurednot used through Glama in the last 30 days
- Maintenance88 / 100 · weight 24%
- Last commit touching this server100
- 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
- 55.6
- × relevance: the keyword is dedicated here
- 1.00
- × continuity: actively changing
- 1.00
- × evidence: small audience
- 0.70
- Composite score
- 38.9
Questions people ask
Which one should I install if I use Claude Code and only want read-only access?
Use MCP Server for MySQL (benborla/mcp-server-mysql). It is read-only, a community favourite, and its npm package had 13,650 downloads in a typical week. It had a commit 49 days ago.
Which server should I use if I need MySQL and PostgreSQL together?
DBHub (bytebase/dbhub) is the active multi-database option: it exposes a single MCP gateway to PostgreSQL, MySQL, SQL Server, MariaDB, and SQLite and had a commit 0 days ago with 77 commits in the last 12 weeks. Multi Database MCP Server (FreePeak/db-mcp-server) also supports MySQL and PostgreSQL now, with per-database query, execute, transaction, schema, and performance tools, and had a commit 21 days ago.
Which servers can execute write queries and which are read-only?
mcp-mysql-server (f4ww4z/mcp-mysql-server) is described as best for an AI assistant that must run both SELECT and write queries and exposes query, execute, list_tables, and describe_table with prepared statement support. It is profiled Abandoned but popular, with a commit 305 days ago and 0 commits in the last 12 weeks. MCP Server for MySQL (benborla/mcp-server-mysql) and MySQL Query MCP Server (devakone/mcp-query-mcp-server) are the read-only options among these servers.
What should I be careful about with MySQL MCP Server (neverinfamous/mysql-mcp) in production?
It is the option described for production MySQL workloads requiring OAuth 2.1 and connection pooling. It exposes 43 tools and had a commit 27 days ago, and it is profiled Steady. It also had 10 GitHub stars and 81 npm downloads in a typical week.