Skip to main content
Glama

20 Best MySQL MCP Servers, Compared (November 2026)

Updated 20 of 652 MySQL servers in the Glama registryRebuilt weekly

The short answer

Most readers should reach for MySQL MCP Server (designcomputer/mysql_mcp_server): it had 7,648 PyPI downloads in a typical week, 3 tools, a tool description grade of A, and its last commit was 11 days ago. If you need a universal server with more recent commit activity, use DBHub (bytebase/dbhub), whose last commit was 0 days ago and which had 70 commits in the last 12 weeks. DBHub also exposes execute_sql and search_objects.

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 querying, schema inspection, and table sampling by an AI assistant: it exposes execute_sql, get_schema_info, and get_table_sample tools.
  • 2MCP Server for MySQL : Teams that need read-only LLM access to a MySQL database: the mysql_query tool runs queries read-only by default, with writes behind opt-in flags.
  • 3MySQL Database Access : Read-only MySQL database inspection from an MCP client: it exposes list_databases, list_tables, describe_table, and execute_query for SELECT, SHOW, DESCRIBE, and EXPLAIN only.
  • 4DBHub : Connecting an MCP client to MySQL for ad hoc SQL and schema search: it exposes execute_sql and search_objects as its two tools.
  • 5MCP MariaDB Server : Semantic search stored in MariaDB: it ships vector store create, insert, and search tools alongside standard SQL tools, backed by OpenAI, Gemini, or HuggingFace embeddings.

Which one, for your situation

Your situationWhat to use
I want a MySQL-only server with measured PyPI downloadsUse MySQL MCP Server (designcomputer/mysql_mcp_server): it had 7,648 PyPI downloads in a typical week, 3 tools, and a tool description grade of A.
I need read-only queries with writes behind opt-in flagsUse MCP Server for MySQL (benborla/mcp-server-mysql): its mysql_query tool runs queries read-only by default, with writes behind opt-in flags.
I want an actively maintained universal database serverUse DBHub (bytebase/dbhub): its last commit was 0 days ago, it had 70 commits in the last 12 weeks, and it exposes execute_sql and search_objects.
I need per-table role-based CRUD permissionsUse Faucet (faucetdb/faucet): it exposes describe, query, insert, update and delete tools with per-table role-based access.
I need vector search stored in MariaDBUse MCP MariaDB Server (MariaDB/mcp): it ships vector store create, insert, and search tools alongside standard SQL tools.
I need data quality monitoring that can gate CIUse scherlok (rbmuller/scherlok): it profiles tables, stores a baseline, and exposes watch/check/verify tools to detect anomalies and gate CI.

Top MCP servers for MySQL

Profile
1Community favourite1,409+147.6K11 days ago86.4
2Abandoned but popular2,210+6414.2K104 days ago82.3
3Community favourite75+457147 days ago72.2
4Community favourite3,803+189–today70.6
5Steady218+12–4 days ago66.9
6Community favourite480+17–23 days ago60.2
7Emerging170+26–21 days ago59.6
8Community favourite365+10–2 days ago57.3
9Community favourite29,390+3,359–today56.7
10Abandoned but popular171+3308360 days ago56.7
11Community favourite16,820+210–2 days ago53.8
12Abandoned but popular943+384237 days ago52.0
13Steady110633 days ago52.0
14Community favourite3,234+293922 days ago51.6
15Community favourite5,050+23–today50.0
16Community favourite47,659-44–2 days ago48.3
17Steady14045228 days ago43.8
18Dormant16091174 days ago43.2
19Steady14+4492 days ago43.0
20Dormant8107327 days ago41.3

The ranking, with the evidence

  • Best for: Ad hoc MySQL querying, schema inspection, and table sampling by an AI assistant: it exposes execute_sql, get_schema_info, and get_table_sample tools.

    The server exposes three tools: execute_sql for SQL execution, get_schema_info for column metadata, and get_table_sample for small row samples. It requires MySQL credentials through environment variables, and its README warns that .env files are not found when Claude Code or Claude Desktop launches the server from its own working directory.

    Score 86.4: show every number behind it
    • Adoption94 / 100 · weight 40%
      • GitHub stars79
      • PyPI downloads83
      • Used through Glamanot measured
        not used through Glama in the last 30 days
    • Maintenance83 / 100 · weight 24%
      • Last commit touching this server100
      • Repository maintenance grade80
      • Commit cadence40
    • Momentum57 / 100 · weight 14%
      • Stars gained, relative to size39
      • Stars gained, absolute48
      • 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 measured
        not published by the vendor it integrates
    Weighted mean of the five
    86.4
    × relevance: the keyword is dedicated here
    1.00
    × continuity: actively changing
    1.00
    × evidence: widely adopted
    1.00
    Composite score
    86.4
  • Best for: Teams that need read-only LLM access to a MySQL database: the mysql_query tool runs queries read-only by default, with writes behind opt-in flags.

    The server exposes a mysql_query tool for executing SQL and a mysql://tables resource listing tables and column metadata, configured through MYSQL_HOST, MYSQL_PORT, MYSQL_USER, MYSQL_PASS and MYSQL_DB environment variables and launched via npx or in an HTTP remote mode with bearer token auth. It assumes Node.js v20+ and a MySQL user with appropriate privileges, and write operations stay disabled until ALLOW_INSERT_OPERATION, ALLOW_UPDATE_OPERATION or ALLOW_DELETE_OPERATION is set.

    Score 82.3: show every number behind it
    • Adoption100 / 100 · weight 40%
      • GitHub stars84
      • npm downloads88
      • Used through Glamanot measured
        not used through Glama in the last 30 days
    • Maintenance57 / 100 · weight 24%
      • Last commit touching this server88
      • Repository maintenance grade30
      • Commit cadence5
    • Momentum77 / 100 · weight 14%
      • Stars gained, relative to size68
      • Stars gained, absolute73
      • npm download trend100
    • Tool quality≈68 / 100 · weight 13%
      • Tool description quality≈68
        tool descriptions not yet scored
      • Built and inspected by Glamanot measured
        never built and inspected by Glama
    • Trust100 / 100 · weight 9%
      • License100
      • Published by the vendor it integratesnot measured
        not published by the vendor it integrates
    Weighted mean of the five
    82.3
    × relevance: the keyword is dedicated here
    1.00
    × continuity: actively changing
    1.00
    × evidence: widely adopted
    1.00
    Composite score
    82.3
  • Best for: Read-only MySQL database inspection from an MCP client: it exposes list_databases, list_tables, describe_table, and execute_query for SELECT, SHOW, DESCRIBE, and EXPLAIN only.

    The server exposes four tools for listing databases and tables, describing schemas, and running read-only queries: list_databases, list_tables, describe_table, and execute_query. Its MCP configuration requires MySQL connection environment variables such as MYSQL_HOST, MYSQL_PORT, MYSQL_USER, and MYSQL_PASSWORD, with MYSQL_DATABASE optional.

    Score 72.2: show every number behind it
    • Adoption66 / 100 · weight 40%
      • GitHub stars47
      • npm downloads59
      • Used through Glamanot measured
        not used through Glama in the last 30 days
    • Maintenance81 / 100 · weight 24%
      • Last commit touching this server88
      • Repository maintenance grade80
      • Commit cadence65
    • Momentum56 / 100 · weight 14%
      • Stars gained, relative to size52
      • Stars gained, absolute27
      • npm download trend100
    • Tool quality73 / 100 · weight 13%
      • Tool description quality65
      • Built and inspected by Glama100
    • Trust100 / 100 · weight 9%
      • License100
      • Published by the vendor it integratesnot measured
        not published by the vendor it integrates
    Weighted mean of the five
    72.2
    × relevance: the keyword is dedicated here
    1.00
    × continuity: actively changing
    1.00
    × evidence: widely adopted
    1.00
    Composite score
    72.2
  • 4

    DBHub

    Community favourite
    bytebase/dbhub ↗

    Best for: Connecting an MCP client to MySQL for ad hoc SQL and schema search: it exposes execute_sql and search_objects as its two tools.

    DBHub provides an MCP interface to MySQL and other databases through execute_sql and search_objects, its two default tools. Its explain_sql and health_check tools are opt-in, so a default setup omits query-plan and connection-health capabilities unless they are enabled.

    Score 70.6: show every number behind it
    • Adoption90 / 100 · weight 40%
      • GitHub stars90
      • npm downloadsnot measured
        npm names no repository for dbhub, so its downloads cannot be attributed
      • Used through Glamanot measured
        not used through Glama in the last 30 days
    • Maintenance100 / 100 · weight 24%
      • Last commit touching this server100
      • Repository maintenance grade100
      • Commit cadence100
    • Momentum92 / 100 · weight 14%
      • Stars gained, relative to size91
      • Stars gained, absolute92
      • npm download trendnot measured
        no download history for the selected registry
    • Tool quality68 / 100 · weight 13%
      • Tool description quality60
      • Built and inspected by Glama100
    • Trust100 / 100 · weight 9%
      • License100
      • Published by the vendor it integratesnot measured
        not published by the vendor it integrates
    Weighted mean of the five
    90.5
    × relevance: the keyword is declared here
    0.78
    × continuity: actively changing
    1.00
    × evidence: widely adopted
    1.00
    Composite score
    70.6
  • Best for: Semantic search stored in MariaDB: it ships vector store create, insert, and search tools alongside standard SQL tools, backed by OpenAI, Gemini, or HuggingFace embeddings.

    MCP MariaDB Server documents tools for listing databases and tables, retrieving table schemas with foreign key relations, executing read-only SELECT, SHOW, and DESCRIBE queries, and creating databases, with optional vector store tools for inserting documents and running semantic search. The vector tools stay disabled unless EMBEDDING_PROVIDER is set with a matching API key, and no npm or PyPI package is published, so it is run from the repository.

    Score 66.9: show every number behind it
    • Adoption59 / 100 · weight 40%
      • GitHub stars59
      • npm downloadsnot measured
        no npm package
      • Used through Glamanot measured
        not used through Glama in the last 30 days
    • Maintenance71 / 100 · weight 24%
      • Last commit touching this server100
        dated from the last commit on the default branch, re-read from GitHub at publication; the stored date would have published 90 days ago
      • Repository maintenance grade30
      • Commit cadence40
    • Momentum63 / 100 · weight 14%
      • Stars gained, relative to size75
      • Stars gained, absolute45
      • npm download trendnot measured
        no download history for the selected registry
    • Tool quality≈68 / 100 · weight 13%
      • Tool description quality≈68
        tool descriptions not yet scored
      • Built and inspected by Glamanot measured
        never built and inspected by Glama
    • Trust100 / 100 · weight 9%
      • License100
      • Published by the vendor it integrates100
    Weighted mean of the five
    66.9
    × relevance: the keyword is dedicated here
    1.00
    × continuity: actively changing
    1.00
    × evidence: widely adopted
    1.00
    Composite score
    66.9
  • Best for: A single AI agent session spanning multiple MySQL and PostgreSQL databases: the README documents per-database query, execute, transaction, schema, and performance tools.

    The README documents a server that connects to multiple configured databases and generates per-database tools for queries, statement execution, transactions, schema exploration, and performance analysis. No npm package is published and no PyPI package is attributed, so installation depends on the repository's documented deployment options rather than a package manager.

    Score 60.2: show every number behind it
    • Adoption67 / 100 · weight 40%
      • GitHub stars67
      • npm downloadsnot measured
        no npm package
      • Used through Glamanot measured
        not used through Glama in the last 30 days
    • Maintenance100 / 100 · weight 24%
      • Last commit touching this server100
      • Repository maintenance grade100
      • Commit cadence100
    • Momentum61 / 100 · weight 14%
      • Stars gained, relative to size68
      • Stars gained, absolute51
      • npm download trendnot measured
        no download history for the selected registry
    • Tool quality≈68 / 100 · weight 13%
      • Tool description quality≈68
        tool descriptions not yet scored
      • Built and inspected by Glamanot measured
        never built and inspected by Glama
    • Trust100 / 100 · weight 9%
      • License100
      • Published by the vendor it integratesnot measured
        not published by the vendor it integrates
    Weighted mean of the five
    77.2
    × relevance: the keyword is declared here
    0.78
    × continuity: actively changing
    1.00
    × evidence: widely adopted
    1.00
    Composite score
    60.2
  • Best for: Teams needing governed CRUD access to a MySQL database with per-table role-based permissions: it exposes describe, query, insert, update and delete tools from one binary.

    Faucet connects to a database, introspects its schema at runtime, and exposes eight MCP tools (list services, list tables, describe table, query, insert, update, delete, raw SQL) alongside a generated REST API and OpenAPI spec. It is installed as a single Go binary or Docker image rather than a published npm or PyPI package, and its write tools enforce safeguards: update and delete require a filter expression, and raw SQL runs only on services configured with raw_sql_allowed.

    Score 59.6: show every number behind it
    • Adoption56 / 100 · weight 40%
      • GitHub stars56
      • npm downloadsnot measured
        no npm package
      • Used through Glamanot measured
        not used through Glama in the last 30 days
    • Maintenance92 / 100 · weight 24%
      • Last commit touching this server100
      • Repository maintenance grade80
      • Commit cadence85
    • Momentum83 / 100 · weight 14%
      • Stars gained, relative to size100
      • Stars gained, absolute58
      • npm download trendnot measured
        no 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 measured
        not published by the vendor it integrates
    Weighted mean of the five
    76.4
    × relevance: the keyword is declared here
    0.78
    × continuity: actively changing
    1.00
    × evidence: widely adopted
    1.00
    Composite score
    59.6
  • 8

    DBCode

    Community favourite▼ 1
    dbcodeio/public ↗

    Best for: Working inside VS Code with existing database connections: the extension's MCP server reuses those connections to expose schemas and run queries.

    DBCode is a VS Code extension that can run an MCP server exposing the databases and schemas of its configured connections and executing queries against them. The MCP server is a feature of the extension rather than a standalone package, so it requires DBCode installed in VS Code or a compatible fork, and agents act through the existing connections under per-connection AI permissions.

    Score 57.3: show every number behind it
    • Adoption64 / 100 · weight 40%
      • GitHub stars64
      • npm downloadsnot measured
        npm names no repository for dbcode, so its downloads cannot be attributed
      • Used through Glamanot measured
        not used through Glama in the last 30 days
    • Maintenance95 / 100 · weight 24%
      • Last commit touching this server100
      • Repository maintenance grade80
      • Commit cadence100
    • Momentum52 / 100 · weight 14%
      • Stars gained, relative to size59
      • Stars gained, absolute43
      • npm download trendnot measured
        no download history for the selected registry
    • Tool quality≈68 / 100 · weight 13%
      • Tool description quality≈68
        tool descriptions not yet scored
      • Built and inspected by Glamanot measured
        never built and inspected by Glama
    • Trust100 / 100 · weight 9%
      • License100
      • Published by the vendor it integratesnot measured
        not published by the vendor it integrates
    Weighted mean of the five
    73.5
    × relevance: the keyword is declared here
    0.78
    × continuity: actively changing
    1.00
    × evidence: widely adopted
    1.00
    Composite score
    57.3
  • 9

    dbx

    Community favourite▼ 1
    t8y2/dbx ↗

    Best for: Managing multiple databases from desktop, Docker, or CLI: dbx includes an MCP server and built-in AI assistant.

    The dbx project provides an MCP server alongside a database manager documented for desktop, Docker, CLI, and built-in AI assistant use, with MCP described as enabling natural-language queries and database management. Its MCP tool list has not been inspected, so the specific MCP operations available cannot be confirmed from the material.

    Score 56.7: show every number behind it
    • Adoption100 / 100 · weight 40%
      • GitHub stars100
      • npm downloadsnot measured
        npm publishes dbx from samt/node-dbx
      • Used through Glamanot measured
        not used through Glama in the last 30 days
    • Maintenance95 / 100 · weight 24%
      • Last commit touching this server100
      • Repository maintenance grade80
      • Commit cadence100
    • Momentum100 / 100 · weight 14%
      • Stars gained, relative to size100
      • Stars gained, absolute100
      • npm download trendnot measured
        no download history for the selected registry
    • Tool quality≈68 / 100 · weight 13%
      • Tool description quality≈68
        tool descriptions not yet scored
      • Built and inspected by Glamanot measured
        never built and inspected by Glama
    • Trust100 / 100 · weight 9%
      • License100
      • Published by the vendor it integratesnot measured
        not published by the vendor it integrates
    Weighted mean of the five
    94.5
    × relevance: the keyword is tagged here
    0.60
    × continuity: actively changing
    1.00
    × evidence: widely adopted
    1.00
    Composite score
    56.7
  • Best for: AI-assisted MySQL work that needs schema inspection as well as reads and writes: it exposes query, execute, list_tables, and describe_table tools.

    It exposes five tools: connect_db for database connection, query for SELECT statements, execute for INSERT, UPDATE, or DELETE statements, list_tables, and describe_table. It requires MySQL connection details, supplied either as a URI argument to the npx command or through MYSQL_HOST, MYSQL_USER, MYSQL_PASSWORD, and MYSQL_DATABASE environment variables.

    Score 56.7: show every number behind it
    • Adoption64 / 100 · weight 40%
      • GitHub stars56
      • npm downloads53
      • Used through Glamanot measured
        not used through Glama in the last 30 days
    • Maintenance32 / 100 · weight 24%
      • Last commit touching this server42
      • Repository maintenance grade30
      • Commit cadence5
    • Momentum46 / 100 · weight 14%
      • Stars gained, relative to size39
      • Stars gained, absolute24
      • npm download trend84
    • Tool quality63 / 100 · weight 13%
      • Tool description quality55
      • Built and inspected by Glama100
    • Trust100 / 100 · weight 9%
      • License100
      • Published by the vendor it integratesnot measured
        not published by the vendor it integrates
    Weighted mean of the five
    56.7
    × relevance: the keyword is dedicated here
    1.00
    × continuity: actively changing
    1.00
    × evidence: widely adopted
    1.00
    Composite score
    56.7
  • Best for: MySQL schema exploration and querying from an MCP-compatible IDE: the README documents prebuilt generic tools such as list_tables and execute_sql.

    MCP Toolbox for Databases is an open source MCP server whose README documents prebuilt generic database tools such as list_tables and execute_sql, alongside a framework for custom tools. Prebuilt database access requires adding an MCP client configuration and setting database-specific environment variables.

    Score 53.8: show every number behind it
    • Adoption100 / 100 · weight 40%
      • GitHub stars100
      • npm downloadsnot measured
        no npm package
      • Used through Glamanot measured
        not used through Glama in the last 30 days
    • Maintenance95 / 100 · weight 24%
      • Last commit touching this server100
      • Repository maintenance grade80
      • Commit cadence100
    • Momentum65 / 100 · weight 14%
      • Stars gained, relative to size46
      • Stars gained, absolute94
      • npm download trendnot measured
        no download history for the selected registry
    • Tool quality≈68 / 100 · weight 13%
      • Tool description quality≈68
        tool descriptions not yet scored
      • Built and inspected by Glamanot measured
        never built and inspected by Glama
    • Trust100 / 100 · weight 9%
      • License100
      • Published by the vendor it integratesnot measured
        not published by the vendor it integrates
    Weighted mean of the five
    89.7
    × relevance: the keyword is tagged here
    0.60
    × continuity: actively changing
    1.00
    × evidence: widely adopted
    1.00
    Composite score
    53.8
  • Best for: A MySQL setup that must stay read-only: it runs as an MCP stdio server with read-only access by default.

    Universal DB MCP connects AI clients to MySQL and other databases through MCP stdio, SSE, Streamable HTTP, and a REST API, with connection details supplied by CLI flags or headers. Before choosing it, note that its MCP setup requires Node.js 20 or newer and passes database credentials as command-line arguments in the client configuration.

    Score 52.0: show every number behind it
    • Adoption81 / 100 · weight 40%
      • GitHub stars74
      • npm downloads41
      • Used through Glamanot measured
        not used through Glama in the last 30 days
    • Maintenance46 / 100 · weight 24%
      • Last commit touching this server68
      • Repository maintenance grade30
      • Commit cadence5
    • Momentum40 / 100 · weight 14%
      • Stars gained, relative to size23
      • Stars gained, absolute26
      • npm download trend89
    • Tool quality≈68 / 100 · weight 13%
      • Tool description quality≈68
        tool descriptions not yet scored
      • Built and inspected by Glamanot measured
        never built and inspected by Glama
    • Trust100 / 100 · weight 9%
      • License100
      • Published by the vendor it integratesnot measured
        not published by the vendor it integrates
    Weighted mean of the five
    66.7
    × relevance: the keyword is declared here
    0.78
    × continuity: actively changing
    1.00
    × evidence: widely adopted
    1.00
    Composite score
    52.0
  • Best for: AI agents that need MySQL writes under access control: it exposes read/write query, transaction, and schema tools plus OAuth 2.1.

    It exposes 43 tools for MySQL read/write queries, transactions, JSON operations, schema and index management, and also documents resources and HTTP transport. Because it includes write, drop-table, and transaction tools, it should be connected only to a database where those operations are allowed.

    Score 52.0: show every number behind it
    • Adoption42 / 100 · weight 40%
      • GitHub stars27
      • npm downloads38
      • Used through Glamanot measured
        not 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 size0
      • Stars gained, absolute0
      • npm download trend84
    • Tool quality63 / 100 · weight 13%
      • Tool description quality55
      • Built and inspected by Glama100
    • Trust100 / 100 · weight 9%
      • License100
      • Published by the vendor it integratesnot measured
        not published by the vendor it integrates
    Weighted mean of the five
    61.2
    × relevance: the keyword is dedicated here
    1.00
    × continuity: actively changing
    1.00
    × evidence: modest but real audience
    0.85
    Composite score
    52.0
  • 14

    GraphJin

    Community favourite▼ 3
    dosco/graphjin ↗

    Best for: Natural-language querying of an existing MySQL database under policy controls: the README documents MCP access, schema discovery, and guarded query execution.

    GraphJin documents a GraphQL and MCP interface for querying databases and other sources, with automatic schema discovery, SQL compilation, and a built-in agent available through an MCP tool. The built-in agent needs a model API key such as OPENAI_API_KEY, ANTHROPIC_API_KEY, or GOOGLE_APIKEY, so the natural-language agent is not enabled by installation alone.

    Score 51.6: show every number behind it
    • Adoption92 / 100 · weight 40%
      • GitHub stars88
      • npm downloads28
        downloads show none of the weekday rhythm human traffic has; halved
      • Used through Glamanot measured
        not 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 size38
      • Stars gained, absolute59
      • npm download trend72
    • Tool quality≈68 / 100 · weight 13%
      • Tool description quality≈68
        tool descriptions not yet scored
      • Built and inspected by Glamanot measured
        never built and inspected by Glama
    • Trust100 / 100 · weight 9%
      • License100
      • Published by the vendor it integrates100
    Weighted mean of the five
    86.0
    × relevance: the keyword is tagged here
    0.60
    × continuity: actively changing
    1.00
    × evidence: widely adopted
    1.00
    Composite score
    51.6
  • 15

    whodb-cli

    Community favourite▼ 1
    clidey/whodb ↗

    Best for: Existing WhoDB users managing hosted platform resources including MySQL: the MCP server exposes setup guidance and whodb_platform_* actions for datasets, ontologies, apps, and bundles.

    The README documents an interactive TUI, programmatic commands, and an MCP server; the exposed MCP tools number 156 and center on whodb_mcp_setup plus whodb_platform_* actions for hosted datasets, ontologies, apps, bundles, and related resources. The exposed tools are oriented toward WhoDB hosted platform resources and setup guidance, so a MySQL-only query workflow should confirm that those actions fit before installing.

    Score 50.0: show every number behind it
    • Adoption93 / 100 · weight 40%
      • GitHub stars93
      • npm downloadsnot measured
        no npm package
      • Used through Glamanot measured
        not used through Glama in the last 30 days
    • Maintenance100 / 100 · weight 24%
      • Last commit touching this server100
      • Repository maintenance grade100
      • Commit cadence100
    • Momentum38 / 100 · weight 14%
      • Stars gained, relative to size27
      • Stars gained, absolute56
      • npm download trendnot measured
        no 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 integrates100
    Weighted mean of the five
    83.3
    × relevance: the keyword is tagged here
    0.60
    × continuity: actively changing
    1.00
    × evidence: widely adopted
    1.00
    Composite score
    50.0
  • 16

    Prisma MCP Server

    Community favourite▲ 1
    prisma/orm ↗

    Best for: Prisma 8 on PostgreSQL with an AI agent: the README documents installing workflow-specific SKILL.md files and a prisma-8 primer.

    The README documents Prisma 8 ORM setup and installing agent skills for AI agent runtimes, including workflow-specific SKILL.md files and a prisma-8 primer. Its description targets Prisma Postgres databases rather than MySQL, and the available material does not document the MCP tools exposed.

    Score 48.3: show every number behind it
    • Adoption100 / 100 · weight 40%
      • GitHub stars100
      • npm downloadsnot measured
        npm names no repository for dev-env, so its downloads cannot be attributed
      • Used through Glamanot measured
        not 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 measured
        no download history for the selected registry
    • Tool quality≈68 / 100 · weight 13%
      • Tool description quality≈68
        tool descriptions not yet scored
      • Built and inspected by Glamanot measured
        never built and inspected by Glama
    • Trust100 / 100 · weight 9%
      • License100
      • Published by the vendor it integrates100
    Weighted mean of the five
    80.5
    × relevance: the keyword is tagged here
    0.60
    × continuity: actively changing
    1.00
    × evidence: widely adopted
    1.00
    Composite score
    48.3
  • Best for: Teams that need an MCP agent to run DDL and DML against MySQL under configurable permissions: sql_query alongside check_permissions and operation logs makes changes auditable.

    MCP MySQL Server exposes five tools: sql_query for SQL including DDL and DML, get_database_info for database and table information, check_permissions for permission status, and get_operation_logs and get_ddl_sql_logs for operation history. It is distributed as the npm package @liangshanli/mcp-server-mysql and requires MySQL connection environment variables, with READONLY, ALLOW_DDL, ALLOW_DROP, and ALLOW_DELETE documented for controlling write operations.

    Score 43.8: show every number behind it
    • Adoption59 / 100 · weight 40%
      • GitHub stars29
      • npm downloads54
        downloads capped: not corroborated by repository audience
      • Used through Glamanot measured
        not used through Glama in the last 30 days
    • Maintenance77 / 100 · weight 24%
      • Last commit touching this server100
      • Repository maintenance grade55
      • Commit cadence40
    • Momentum25 / 100 · weight 14%
      • Stars gained, relative to size0
      • Stars gained, absolute0
      • npm download trend100
    • Tool quality63 / 100 · weight 13%
      • Tool description quality55
      • Built and inspected by Glama100
    • Trust100 / 100 · weight 9%
      • License100
      • Published by the vendor it integratesnot measured
        not published by the vendor it integrates
    Weighted mean of the five
    62.6
    × relevance: the keyword is dedicated here
    1.00
    × continuity: actively changing
    1.00
    × evidence: small audience
    0.70
    Composite score
    43.8
  • Best for: Read-only MySQL schema inspection and SELECT querying from an LLM: it documents a query tool, exposes table schema resources, and enforces READ ONLY transactions.

    The server documents a query tool that executes read-only SQL and exposes table schema information as resources over MCP, configured with a MySQL connection URI. Before choosing it, note that it requires Node.js v18 or later and a MySQL connection URI, and its scope is limited to read-only SELECT queries with no data or schema modification.

    Score 43.2: show every number behind it
    • Adoption46 / 100 · weight 40%
      • GitHub stars31
      • npm downloads42
      • Used through Glamanot measured
        not used through Glama in the last 30 days
    • Maintenance46 / 100 · weight 24%
      • Last commit touching this server68
      • Repository maintenance grade30
      • Commit cadence5
    • Momentum25 / 100 · weight 14%
      • Stars gained, relative to size0
      • Stars gained, absolute0
      • npm download trend100
    • Tool quality≈68 / 100 · weight 13%
      • Tool description quality≈68
        tool descriptions not yet scored
      • Built and inspected by Glamanot measured
        never built and inspected by Glama
    • Trust100 / 100 · weight 9%
      • License100
      • Published by the vendor it integratesnot measured
        not published by the vendor it integrates
    Weighted mean of the five
    50.8
    × relevance: the keyword is dedicated here
    1.00
    × continuity: actively changing
    1.00
    × evidence: modest but real audience
    0.85
    Composite score
    43.2
  • Best for: Monitoring MySQL table data quality from an MCP client: it profiles tables, stores a baseline, and exposes watch/check/verify tools to detect anomalies and gate CI.

    Scherlok exposes eight MCP tools for listing visible tables, profiling a MySQL connection, comparing later profiles against a stored baseline, reading anomaly history, and returning CI-style pass/fail gates. Before choosing it, note that it assumes a configured warehouse connection resolved server-side, so the model never receives or supplies the connection.

    Score 43.0: show every number behind it
    • Adoption41 / 100 · weight 40%
      • GitHub stars29
      • PyPI downloads36
      • Used through Glamanot measured
        not used through Glama in the last 30 days
    • Maintenance95 / 100 · weight 24%
      • Last commit touching this server100
      • Repository maintenance grade80
      • Commit cadence100
    • Momentum40 / 100 · weight 14%
      • Stars gained, relative to size61
      • Stars gained, absolute27
      • PyPI download trend20
    • Tool quality85 / 100 · weight 13%
      • Tool description quality77
      • Built and inspected by Glama100
    • Trust100 / 100 · weight 9%
      • License100
      • Published by the vendor it integratesnot measured
        not published by the vendor it integrates
    Weighted mean of the five
    64.9
    × relevance: the keyword is declared here
    0.78
    × continuity: actively changing
    1.00
    × evidence: modest but real audience
    0.85
    Composite score
    43.0
  • Best for: Managing multiple MySQL connections and running CRUD through an AI assistant: it documents connection add/select/remove and SQL query/schema inspection tools.

    The README documents MCP tools for adding, listing, selecting, and removing MySQL connections, plus executing SQL, listing tables and databases, and describing table schemas. Before choosing it, note that it runs as a local StreamableHTTP server with header-based credentials or AI-added connections, and restarting the server clears in-memory sessions.

    Score 41.3: show every number behind it
    • Adoption49 / 100 · weight 40%
      • GitHub stars48
      • npm downloads10
        downloads show none of the weekday rhythm human traffic has; halved
      • Used through Glamanot measured
        not used through Glama in the last 30 days
    • Maintenance32 / 100 · weight 24%
      • Last commit touching this server42
      • Repository maintenance grade30
      • Commit cadence5
    • Momentum25 / 100 · weight 14%
      • Stars gained, relative to size0
      • Stars gained, absolute0
      • npm download trend100
    • Tool quality≈68 / 100 · weight 13%
      • Tool description quality≈68
        tool descriptions not yet scored
      • Built and inspected by Glamanot measured
        never built and inspected by Glama
    • Trust100 / 100 · weight 9%
      • License100
      • Published by the vendor it integratesnot measured
        not published by the vendor it integrates
    Weighted mean of the five
    48.6
    × relevance: the keyword is dedicated here
    1.00
    × continuity: actively changing
    1.00
    × evidence: modest but real audience
    0.85
    Composite score
    41.3

Questions people ask

How do I choose between DBHub and MySQL MCP Server (designcomputer/mysql_mcp_server)?

DBHub is the more active general database server: its last commit was 0 days ago and it had 70 commits in the last 12 weeks. MySQL MCP Server (designcomputer/mysql_mcp_server) is MySQL-specific and has a tool description grade of A. Choose DBHub if you want one server for multiple databases, and choose the MySQL-specific server if you want a purpose-built MySQL tool set.

What should I check before using MCP Server for MySQL (benborla/mcp-server-mysql)?

It runs mysql_query read-only by default, with writes behind opt-in flags, so decide whether you need write access before you connect an agent. Its last commit was 104 days ago, it had 0 commits in the last 12 weeks, and its profile is Abandoned but popular.

Does DBHub support MySQL only?

No, DBHub is a universal database MCP server connecting to MySQL, PostgreSQL, SQLite, DuckDB and etc. For MySQL work it exposes execute_sql and search_objects as its two tools.

Which server should I use for read-only MySQL access?

MySQL Database Access (dpflucas/mysql-mcp-server) is a direct read-only option: it exposes list_databases, list_tables, describe_table, and execute_query for SELECT, SHOW, DESCRIBE, and EXPLAIN only, with 4 tools and a tool description grade of A. MCP Server for MySQL (benborla/mcp-server-mysql) also runs mysql_query read-only by default, with writes behind opt-in flags, but its last commit was 104 days ago.

Can I use Faucet to write to MySQL?

Yes, Faucet exposes describe, query, insert, update and delete tools from one binary. It also provides API keys and per-table role-based access for governed CRUD access.

What does scherlok do with a MySQL database?

scherlok profiles MySQL tables, stores a baseline, and exposes watch/check/verify tools to detect anomalies and gate CI. It is read-only, with the connection resolved server-side, never via the model.

Other comparisons