20 Best MySQL MCP Servers, Compared (September 2026)
The short answer
Most readers should use MCP Server for MySQL (benborla/mcp-server-mysql). It is read-only, so an LLM can inspect schemas and execute read-only queries without write access, and it is active: 23 commits on its default branch in the last 12 weeks, with a last commit 43 days ago. It also publishes an npm package that had 13,885 downloads in a typical week. If you need an agent to write to the database, the better answer is MySQL MCP Server (neverinfamous/mysql-mcp), which exposes read/write query, schema, JSON, transaction, and monitoring tools.
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
- 1MCP Server for MySQL : Read-only analytics on a live MySQL database: it exposes query and schema inspection tools without write access.
- 2MySQL MCP Server : For AI assistants that need to query and inspect MySQL databases: it exposes SQL execution, schema introspection, and table sampling tools.
- 3DBHub : Read-only querying across PostgreSQL, MySQL, MariaDB, SQL Server, and SQLite: it exposes execute_sql and search_objects while supporting read-only mode.
- 4MCP MariaDB Server : Teams needing both relational SQL and vector similarity search in MariaDB, with read-only query enforcement and optional embedding providers.
- 5DBCode : AI agents in VS Code-family editors needing database access: it exposes an MCP server with schema access and query execution.
Which one, for your situation
| Your situation | What to use |
|---|---|
| I need read-only access to a live MySQL database | Use MCP Server for MySQL (benborla/mcp-server-mysql): it exposes query and schema inspection without write access, had 23 commits in the last 12 weeks, and has an npm package. |
| I need an agent to run writes and transactions | Use MySQL MCP Server (neverinfamous/mysql-mcp): it exposes read/write query, schema, JSON, transaction, and monitoring tools. |
| I want to query MySQL in plain language | Use XiYan MCP Server: it exposes a get_data tool that converts natural language to SQL, though it had no commits in the last 12 weeks. |
| I need one MCP server for MySQL and several other databases | Use DBHub: it is for read-only querying across PostgreSQL, MySQL, MariaDB, SQL Server, and SQLite. |
| I need ad-hoc exploration and editing from a terminal | Use whodb-cli: it exposes schema, query, and write tools. |
Top MCP servers for MySQL
| Best for | Profile | ||||||
|---|---|---|---|---|---|---|---|
| 1 | Read-only analytics on a live MySQL database: it exposes query and schema inspection tools without write access. | Community favourite | 2,108 | +83 | 43 days ago | 87.7 | |
| 2 | For AI assistants that need to query and inspect MySQL databases: it exposes SQL execution, schema introspection, and table sampling tools. | Community favourite | 1,382 | +30 | 37 days ago | 82.7 | |
| 3 | Read-only querying across PostgreSQL, MySQL, MariaDB, SQL Server, and SQLite: it exposes execute_sql and search_objects while supporting read-only mode. | Community favourite | 3,480 | +167 | today | 70.0 | |
| 4 | Teams needing both relational SQL and vector similarity search in MariaDB, with read-only query enforcement and optional embedding providers. | Emerging | 201 | +14 | 29 days ago | 67.5 | |
| 5 | AI agents in VS Code-family editors needing database access: it exposes an MCP server with schema access and query execution. | Community favourite | 345 | +21 | today | 60.4 | |
| 6 | Teams running AI assistants against several SQL databases at once: it exposes per-database query, execute, transaction, schema, and performance tools. | Community favourite | 420 | +11 | 15 days ago | 58.8 | |
| 7 | Database management across many engines from an MCP client: it exposes natural language query and management tools. | Community favourite | 18,438 | +3,644 | today | 57.5 | |
| 8 | Interactive SQL administration of a MySQL database from an MCP client: it exposes query, schema-inspection, permission-checking, and logging tools. | Abandoned but popular | 14 | 0 | 109 days ago | 57.0 | |
| 9 | Operational work on a live MySQL database: it exposes read/write query, schema, JSON, transaction, and monitoring tools through MCP. | Steady | 10 | +2 | 21 days ago | 54.6 | |
| 10 | Connecting AI agents and IDEs to Google Cloud databases: it provides prebuilt generic tools and a framework for custom database tools. | Community favourite | 16,332 | +192 | today | 54.4 | |
| 11 | Querying and analyzing data across multiple database types via natural language, with a read-only mode for safety. | Abandoned but popular | 926 | +22 | 175 days ago | 53.5 | |
| 12 | Ad-hoc exploration and editing of a database through an AI assistant: it exposes schema, query, and write tools. | Community favourite | 5,020 | +19 | today | 52.7 | |
| 13 | Organizations that want AI agents to query databases and APIs through a single GraphQL and MCP endpoint, using its built-in agent for validated, policy-aware access. | Community favourite | 3,162 | +29 | 2 days ago | 51.8 | |
| 14 | Managing Prisma Postgres databases through an MCP server, since that is the task this server's interface is built around. | Community favourite | 47,609 | +56 | today | 51.4 | |
| 15 | For using AI models to query and modify a MySQL database safely, this server exposes five tools for connections, queries, and schema inspection. | Abandoned but popular | 168 | 0 | 298 days ago | 48.9 | |
| 16 | Teams needing one MCP server across several database engines: it exposes tools for Postgres, Redis, Elasticsearch, MySQL, MongoDB, and LDAP. | Emerging | 82 | +82 | 5 days ago | 48.3 | |
| 17 | Read-only schema discovery and SELECT queries against a MySQL database: it exposes a query tool and table schema resources. | Dormant | 14 | 0 | 113 days ago | 43.5 | |
| 18 | MySQL users who want to query by asking plain-language questions: it exposes a get_data tool that converts natural language to SQL. For text-to-SQL queries, it is a strong choice. | Abandoned but popular | 242 | +1 | 209 days ago | 43.1 | |
| 19 | Database developers and admins who need to query, modify, and alter a MySQL schema from an AI assistant: it exposes query, write, and DDL tools. | Dormant | 33 | 0 | 239 days ago | 40.7 | |
| 20 | Managing multiple MySQL connections from an AI assistant: it exposes tools to add, select, and remove connections plus SQL execution. | Dormant | 81 | 0 | 266 days ago | 40.4 |
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: Read-only analytics on a live MySQL database: it exposes query and schema inspection tools without write access.
The server provides a mysql_query tool for executing SQL and a mysql://tables resource for listing tables and column metadata, with write operations off by default. It requires Node.js 20 or newer and a MySQL 5.7+ instance.
GitHub stars2,108Stars / 30 days+83npm / typical week13.9KTools exposednever inspectedLast commit43 days agoCommits / 12 weeks23Maintenance gradeCTool descriptionsNot gradedScore 87.7: 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
- Maintenance86 / 100 · weight 24%
- Last commit touching this server100
- Repository maintenance grade55
- Commit cadence85
- Momentum67 / 100 · weight 14%
- Stars gained, relative to size79
- Stars gained, absolute78
- npm download trend32
- 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
- 87.7
- × relevance: the keyword is dedicated here
- 1.00
- × continuity: actively changing
- 1.00
- × evidence: widely adopted
- 1.00
- Composite score
- 87.7
Best for: For AI assistants that need to query and inspect MySQL databases: it exposes SQL execution, schema introspection, and table sampling tools.
The server exposes three tools: execute_sql for running SQL statements, get_schema_info for column metadata, and get_table_sample for previewing rows. Before choosing it, note that it accepts only single SQL statements and does not support multi-statement queries.
GitHub stars1,382Stars / 30 days+30npm / typical weekShips no npm packageTools exposed3Last commit37 days agoCommits / 12 weeks8Maintenance gradeATool descriptionsAScore 82.7: show every number behind it
- Adoption79 / 100 · weight 40%
- GitHub stars79
- npm downloadsnot measuredno npm package
- 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
- Momentum59 / 100 · weight 14%
- Stars gained, relative to size58
- Stars gained, absolute60
- npm download trendnot measuredno npm download history
- 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
- 82.7
- × relevance: the keyword is dedicated here
- 1.00
- × continuity: actively changing
- 1.00
- × evidence: widely adopted
- 1.00
- Composite score
- 82.7
Best for: Read-only querying across PostgreSQL, MySQL, MariaDB, SQL Server, and SQLite: it exposes execute_sql and search_objects while supporting read-only mode.
DBHub is an MCP server that connects to five database engines and exposes tools for executing SQL, searching schema objects, explaining queries, and checking health. Note that it requires Node.js 22.5.0 or newer, as it relies on the built-in node:sqlite module.
GitHub stars3,480Stars / 30 days+167npm / typical weekdownloads not countedTools exposednever inspectedLast committodayCommits / 12 weeks76Maintenance gradeATool descriptionsNot gradedScore 70.0: 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
- Momentum90 / 100 · weight 14%
- Stars gained, relative to size89
- Stars gained, absolute90
- npm download trendnot measuredno npm download history
- 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
- 89.7
- × relevance: the keyword is declared here
- 0.78
- × continuity: actively changing
- 1.00
- × evidence: widely adopted
- 1.00
- Composite score
- 70.0
Best for: Teams needing both relational SQL and vector similarity search in MariaDB, with read-only query enforcement and optional embedding providers.
This server exposes tools for database and schema inspection, read-only SQL execution, database creation, and optional vector store management with embedding providers. Note that the vector store tools require configuring an embedding provider such as OpenAI, Gemini, or HuggingFace.
GitHub stars201Stars / 30 days+14npm / typical weekShips no npm packageTools exposednever inspectedLast commit29 days agoCommits / 12 weeks2Maintenance gradeDTool descriptionsNot gradedScore 67.5: 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
- Momentum70 / 100 · weight 14%
- Stars gained, relative to size84
- Stars gained, absolute48
- npm download trendnot measuredno npm download history
- 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
- 67.5
- × relevance: the keyword is dedicated here
- 1.00
- × continuity: actively changing
- 1.00
- × evidence: widely adopted
- 1.00
- Composite score
- 67.5
Best for: AI agents in VS Code-family editors needing database access: it exposes an MCP server with schema access and query execution.
It runs an MCP server that gives AI agents access to connected databases, their schemas, and query execution. It is packaged as a VS Code extension, so agents reach the MCP tools through VS Code, Cursor, Antigravity, Windsurf, Kiro, or the
DBCode: Connect an AI Agentcommand.GitHub stars345Stars / 30 days+21npm / typical weekdownloads not countedTools exposednever inspectedLast committodayCommits / 12 weeks68Maintenance gradeATool descriptionsNot gradedScore 60.4: show every number behind it
- Adoption63 / 100 · weight 40%
- GitHub stars63
- 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
- Momentum73 / 100 · weight 14%
- Stars gained, relative to size86
- Stars gained, absolute54
- npm download trendnot measuredno npm download history
- 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
- 77.4
- × relevance: the keyword is declared here
- 0.78
- × continuity: actively changing
- 1.00
- × evidence: widely adopted
- 1.00
- Composite score
- 60.4
Best for: Teams running AI assistants against several SQL databases at once: it exposes per-database query, execute, transaction, schema, and performance tools.
It generates a distinct set of query, execute, transaction, schema, and performance tools for each configured database connection, with per-database guards for read-only access, row limits, masking, and query timeouts. It is distributed as a Go module, so an installer should expect to build or fetch a Go binary rather than install an npm package.
GitHub stars420Stars / 30 days+11npm / typical weekShips no npm packageTools exposednever inspectedLast commit15 days agoCommits / 12 weeks102Maintenance gradeATool descriptionsNot gradedScore 58.8: 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
- Momentum52 / 100 · weight 14%
- Stars gained, relative to size58
- Stars gained, absolute44
- npm download trendnot measuredno npm download history
- 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
- 75.4
- × relevance: the keyword is declared here
- 0.78
- × continuity: actively changing
- 1.00
- × evidence: widely adopted
- 1.00
- Composite score
- 58.8
Best for: Database management across many engines from an MCP client: it exposes natural language query and management tools.
DBX is an MCP server that lets clients query and manage databases through natural language. Its README does not enumerate the MCP tools it exposes, so the exact tool set is unknown until run.
GitHub stars18,438Stars / 30 days+3,644npm / typical weekdownloads not countedTools exposednever inspectedLast committodayCommits / 12 weeks4,169Maintenance 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 npm download history
- 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: Interactive SQL administration of a MySQL database from an MCP client: it exposes query, schema-inspection, permission-checking, and logging tools.
The server exposes five MCP tools for running SQL DDL/DML queries, retrieving database information, checking permissions, and reading operation and DDL logs. Before choosing it, note that it expects MySQL connection details to be supplied as environment variables.
GitHub stars14Stars / 30 days0npm / typical week333Tools exposed5Last commit109 days agoCommits / 12 weeks0Maintenance gradeCTool descriptionsBScore 57.0: 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
- Maintenance63 / 100 · weight 24%
- Last commit touching this server88
- Repository maintenance grade55
- Commit cadence5
- Momentum10 / 100 · weight 14%
- Stars gained, relative to size0
- Stars gained, absolute0
- npm download trend41
- 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
- 57.0
- × relevance: the keyword is dedicated here
- 1.00
- × continuity: actively changing
- 1.00
- × evidence: widely adopted
- 1.00
- Composite score
- 57.0
Best for: Operational work on a live MySQL database: it exposes read/write query, schema, JSON, transaction, and monitoring tools through MCP.
The server exposes MCP tools for MySQL read and write queries, table and schema operations, indexes, transactions, JSON manipulation, and resources for schema, status, processlist, and performance. Before choosing it, note that it includes write and schema-altering tools, so it is not read-only.
GitHub stars10Stars / 30 days+2npm / typical week84Tools exposed43Last commit21 days agoCommits / 12 weeks2,585Maintenance gradeATool descriptionsBScore 54.6: 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
- Momentum36 / 100 · weight 14%
- Stars gained, relative to size48
- Stars gained, absolute20
- npm download trend35
- 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
- 64.2
- × relevance: the keyword is dedicated here
- 1.00
- × continuity: actively changing
- 1.00
- × evidence: modest but real audience
- 0.85
- Composite score
- 54.6
Best for: Connecting AI agents and IDEs to Google Cloud databases: it provides prebuilt generic tools and a framework for custom database tools.
The server exposes prebuilt generic tools for direct database interaction and doubles as a framework for building custom tools with structured queries, semantic search, and NL2SQL. It targets Google Cloud database services, which are the supported set listed in its documentation.
GitHub stars16,332Stars / 30 days+192npm / typical weekShips no npm packageTools exposednever inspectedLast committodayCommits / 12 weeks250Maintenance gradeATool descriptionsNot gradedScore 54.4: 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
- Momentum63 / 100 · weight 14%
- Stars gained, relative to size44
- Stars gained, absolute92
- npm download trendnot measuredno npm download history
- 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
- 90.7
- × relevance: the keyword is tagged here
- 0.60
- × continuity: actively changing
- 1.00
- × evidence: widely adopted
- 1.00
- Composite score
- 54.4
Best for: Querying and analyzing data across multiple database types via natural language, with a read-only mode for safety.
The server exposes MCP and HTTP interfaces for natural-language querying and schema analysis across supported databases. It assumes a Node.js runtime, as it is installed and launched through npm.
GitHub stars926Stars / 30 days+22npm / typical week130Tools exposednever inspectedLast commit175 days agoCommits / 12 weeks0Maintenance gradeCTool descriptionsNot gradedScore 53.5: 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
- Maintenance52 / 100 · weight 24%
- Last commit touching this server68
- Repository maintenance grade55
- Commit cadence5
- Momentum43 / 100 · weight 14%
- Stars gained, relative to size58
- Stars gained, absolute55
- 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
- 68.6
- × relevance: the keyword is declared here
- 0.78
- × continuity: actively changing
- 1.00
- × evidence: widely adopted
- 1.00
- Composite score
- 53.5
Best for: Ad-hoc exploration and editing of a database through an AI assistant: it exposes schema, query, and write tools.
The server exposes 12 tools for running SQL, inspecting schemas and tables, explaining query plans, and confirming writes. It lists existing database connections but does not include a tool for creating or managing them.
GitHub stars5,020Stars / 30 days+19npm / typical weekShips no npm packageTools exposed12Last committodayCommits / 12 weeks601Maintenance gradeATool descriptionsAScore 52.7: 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 size25
- Stars gained, absolute52
- npm download trendnot measuredno npm download history
- 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
- 87.8
- × relevance: the keyword is tagged here
- 0.60
- × continuity: actively changing
- 1.00
- × evidence: widely adopted
- 1.00
- Composite score
- 52.7
Best for: Organizations that want AI agents to query databases and APIs through a single GraphQL and MCP endpoint, using its built-in agent for validated, policy-aware access.
GraphJin exposes GraphQL and MCP interfaces that compile natural-language agent instructions into queries across databases, warehouses, files, and other systems, and it includes a built-in agent that performs discovery before acting. It can run as a standalone service or Docker image and expects a model API key for the agentic mode.
GitHub stars3,162Stars / 30 days+29npm / typical week518Tools exposednever inspectedLast commit2 days agoCommits / 12 weeks496Maintenance gradeATool descriptionsNot gradedScore 51.8: 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
- Momentum56 / 100 · weight 14%
- Stars gained, relative to size38
- Stars gained, absolute59
- npm download trend86
- 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
- 86.3
- × relevance: the keyword is tagged here
- 0.60
- × continuity: actively changing
- 1.00
- × evidence: widely adopted
- 1.00
- Composite score
- 51.8
Best for: Managing Prisma Postgres databases through an MCP server, since that is the task this server's interface is built around.
The server exposes an MCP interface for managing Prisma Postgres databases. Its README documents Prisma Next, a TypeScript rewrite of Prisma ORM, and does not list the server's tools.
GitHub stars47,609Stars / 30 days+56npm / typical weekdownloads not countedTools exposednever inspectedLast committodayCommits / 12 weeks353Maintenance 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
- Momentum37 / 100 · weight 14%
- Stars gained, relative to size14
- Stars gained, absolute71
- npm download trendnot measuredno npm download history
- 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
- 85.7
- × relevance: the keyword is tagged here
- 0.60
- × continuity: actively changing
- 1.00
- × evidence: widely adopted
- 1.00
- Composite score
- 51.4
Best for: For using AI models to query and modify a MySQL database safely, this server exposes five tools for connections, queries, and schema inspection.
This server gives AI models access to a MySQL database through five tools: connect_db, query, execute, list_tables, and describe_table. The main setup requirement is a MySQL connection string and a Node.js runtime to run via npx.
GitHub stars168Stars / 30 days0npm / typical week396Tools exposed5Last commit298 days agoCommits / 12 weeks0Maintenance gradeFTool descriptionsBScore 48.9: 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
- 48.9
- × relevance: the keyword is dedicated here
- 1.00
- × continuity: actively changing
- 1.00
- × evidence: widely adopted
- 1.00
- Composite score
- 48.9
Best for: Teams needing one MCP server across several database engines: it exposes tools for Postgres, Redis, Elasticsearch, MySQL, MongoDB, and LDAP.
It exposes connection status and config reload tools, plus Postgres tools for querying, schema inspection, and write SQL, and Redis tools for key operations. Note that the package exposes 100 tools, fewer than its README advertises.
GitHub stars82Stars / 30 days+82npm / typical weekdownloads not countedTools exposed100Last commit5 days agoCommits / 12 weeks43Maintenance gradeBTool descriptionsAScore 48.3: 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
- Momentum91 / 100 · weight 14%
- Stars gained, relative to size100
- Stars gained, absolute77
- npm download trendnot measuredno npm download history
- Tool quality71 / 100 · weight 13%
- Tool description quality63
- 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
- 72.9
- × relevance: the keyword is declared here
- 0.78
- × continuity: actively changing
- 1.00
- × evidence: modest but real audience
- 0.85
- Composite score
- 48.3
- 17
Best for: Read-only schema discovery and SELECT queries against a MySQL database: it exposes a query tool and table schema resources.
The server exposes a query tool for read-only SQL and table schema resources discovered from database metadata. It requires Node.js v18 or newer and is configured with a MySQL connection string.
GitHub stars14Stars / 30 days0npm / typical week130Tools exposednever inspectedLast commit113 days agoCommits / 12 weeks0Maintenance gradeDTool descriptionsNot gradedScore 43.5: 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≈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
- 51.2
- × relevance: the keyword is dedicated here
- 1.00
- × continuity: actively changing
- 1.00
- × evidence: modest but real audience
- 0.85
- Composite score
- 43.5
Best for: MySQL users who want to query by asking plain-language questions: it exposes a get_data tool that converts natural language to SQL. For text-to-SQL queries, it is a strong choice.
The README documents a get_data tool that turns natural language into SQL and returns query results, plus resources that list databases and sample table contents. It requires Python 3.11+, and the default remote mode needs an API key for the XiYanSQL model, though a local mode is available.
GitHub stars242Stars / 30 days+1npm / typical weekShips no npm packageTools exposednever inspectedLast commit209 days agoCommits / 12 weeks0Maintenance gradeDTool descriptionsNot gradedScore 43.1: 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
- Momentum19 / 100 · weight 14%
- Stars gained, relative to size23
- Stars gained, absolute14
- npm download trendnot measuredno npm download history
- 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
- 55.3
- × relevance: the keyword is declared here
- 0.78
- × continuity: actively changing
- 1.00
- × evidence: widely adopted
- 1.00
- Composite score
- 43.1
Best for: Database developers and admins who need to query, modify, and alter a MySQL schema from an AI assistant: it exposes query, write, and DDL tools.
The server exposes tools for connecting to a MySQL database, running SELECT and write queries, and managing tables, columns, indexes, and foreign keys. It requires an existing MySQL connection with credentials and can perform both data changes and schema modifications.
GitHub stars33Stars / 30 days0npm / typical week91Tools exposed7Last commit239 days agoCommits / 12 weeks0Maintenance gradeDTool descriptionsBScore 40.7: show every number behind it
- Adoption48 / 100 · weight 40%
- GitHub stars38
- 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
- Momentum0 / 100 · weight 14%
- Stars gained, relative to size0
- Stars gained, absolute0
- npm download trend0
- Tool quality68 / 100 · weight 13%
- Tool description quality60
- 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
- 47.9
- × relevance: the keyword is dedicated here
- 1.00
- × continuity: actively changing
- 1.00
- × evidence: modest but real audience
- 0.85
- Composite score
- 40.7
- 20
Best for: Managing multiple MySQL connections from an AI assistant: it exposes tools to add, select, and remove connections plus SQL execution.
The server exposes connection-management tools (add_connection, list_connections, select_database, remove_connection) and SQL tools (execute_query, show_tables, describe_table, show_databases) over the StreamableHTTP MCP protocol. It keeps session state in memory, so restarting the server requires reinitializing the MCP client.
GitHub stars81Stars / 30 days0npm / typical week14Tools exposednever inspectedLast commit266 days agoCommits / 12 weeks0Maintenance gradeCTool descriptionsNot gradedScore 40.4: 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≈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
- 47.5
- × relevance: the keyword is dedicated here
- 1.00
- × continuity: actively changing
- 1.00
- × evidence: modest but real audience
- 0.85
- Composite score
- 40.4
Questions people ask
Does MCP Server for MySQL allow writes?
No. It is read-only: its tools let an LLM inspect schemas and execute read-only queries, without write access. For write operations, use a server such as MySQL MCP Server (neverinfamous/mysql-mcp), which exposes read/write query, schema, JSON, transaction, and monitoring tools.
Which MCP server has the most tools?
mcp-server-db exposed 100 tools. Those tools cover Postgres, Redis, Elasticsearch, MySQL, MongoDB, and LDAP, so not all of them are MySQL-specific. Among MySQL-focused servers, MySQL MCP Server (neverinfamous/mysql-mcp) exposed 43 tools.
Is XiYan MCP Server actively maintained?
XiYan MCP Server is marked Abandoned but popular. Its last commit was 209 days ago and it had 0 commits in the last 12 weeks, so it is not receiving regular maintenance. It still exposes a get_data tool that converts natural language to SQL, but review it carefully before pointing it at a live database.
How do DBHub and Multi Database MCP Server differ?
DBHub is for read-only querying across PostgreSQL, MySQL, MariaDB, SQL Server, and SQLite. Multi Database MCP Server supports MySQL and PostgreSQL and exposes per-database query, execute, transaction, schema, and performance tools. Choose DBHub for read-only multi-engine access, and Multi Database MCP Server when you need transactions and execution across MySQL and PostgreSQL.