20 Best PostgreSQL MCP Servers, Compared (October 2026)
The short answer
For most developers installing a PostgreSQL MCP server this afternoon, DBHub (bytebase/dbhub) is the sensible default: it connects to PostgreSQL alongside MySQL, SQLite and DuckDB, exposes execute_sql and search_objects with guardrails such as read-only mode, gained 153 stars per 30 days, and had a commit 6 days ago with 87 commits on its default branch in the last 12 weeks. If your actual problem is a slow query rather than general access, reach for Postgres MCP (crystaldba/postgres-mcp), which exposes 9 tools for explain plans, index tuning, health checks and SQL execution and carries a tool description grade of A. If you need documentation rather than a live connection, pg-aiguide serves semantic search over version-aware PostgreSQL, TimescaleDB and PostGIS documentation, and had a commit 2 days ago.
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
- 1pg-aiguide : Agents writing PostgreSQL schema and SQL: its documented MCP server serves semantic search over version-aware PostgreSQL, TimescaleDB, and PostGIS documentation.
- 2Postgres MCP : Diagnosing slow PostgreSQL queries and index health: it exposes explain-plan, index-tuning, health-check, and SQL execution tools.
- 3pgEdge Postgres MCP Server : Internal, trusted developer workflows needing natural-language SQL against PostgreSQL 14+: it enables SQL queries through MCP-compatible clients and includes a natural-language agent.。
- 4butterbase : Teams running a self-hosted Butterbase backend that want agents to manage its Postgres, RLS, auth, storage, functions, realtime, KV, AI gateway, and RAG through /mcp.
- 5DBHub : Read-only diagnostics or local development across PostgreSQL and other databases: it exposes execute_sql and search_objects with guardrails such as read-only mode.
Which one, for your situation
| Your situation | What to use |
|---|---|
| I need something general to install this afternoon | DBHub covers PostgreSQL and other databases, exposes execute_sql and search_objects with guardrails such as read-only mode, and had a commit 6 days ago with 87 commits on its default branch in the last 12 weeks. |
| My queries are slow and my indexes need work | Postgres MCP (crystaldba/postgres-mcp) exposes 9 tools aimed at explain plans, index tuning, health checks and SQL execution, with a tool description grade of A. |
| I want PostgreSQL docs while writing schema and SQL | pg-aiguide performs semantic search over version-aware PostgreSQL, TimescaleDB and PostGIS documentation and had a commit 2 days ago, with 16 commits on its default branch in the last 12 weeks. |
| I have to watch locks, WAL, replication and bloat | MCP PostgreSQL Operations exposes 34 read-only tools for locks, WAL, replication, bloat, vacuum and query statistics, with a tool description grade of A. |
| I want to explore an unfamiliar schema before writing joins | whodb-cli exposes table, column, schema and ERD metadata tools plus a native EXPLAIN tool, and had a commit 0 days ago with 546 commits on its default branch in the last 12 weeks. |
| I already run a self-hosted Butterbase backend | butterbase runs an MCP server at /mcp on a self-hosted instance or over stdio, letting agents manage its Postgres, RLS, auth, storage, functions, realtime, KV, AI gateway and RAG. |
Top MCP servers for PostgreSQL
| Best for | Profile | ||||||
|---|---|---|---|---|---|---|---|
| 1 | Agents writing PostgreSQL schema and SQL: its documented MCP server serves semantic search over version-aware PostgreSQL, TimescaleDB, and PostGIS documentation. | Community favourite | 1,847 | +17 | 2 days ago | 82.9 | |
| 2 | Diagnosing slow PostgreSQL queries and index health: it exposes explain-plan, index-tuning, health-check, and SQL execution tools. | Community favourite | 3,340 | +114 | 43 days ago | 81.9 | |
| 3 | Internal, trusted developer workflows needing natural-language SQL against PostgreSQL 14+: it enables SQL queries through MCP-compatible clients and includes a natural-language agent.。 | Steady | 230 | +12 | 11 days ago | 74.2 | |
| 4 | Teams running a self-hosted Butterbase backend that want agents to manage its Postgres, RLS, auth, storage, functions, realtime, KV, AI gateway, and RAG through /mcp. | Community favourite | 3,672 | +443 | yesterday | 70.4 | |
| 5 | Read-only diagnostics or local development across PostgreSQL and other databases: it exposes execute_sql and search_objects with guardrails such as read-only mode. | Community favourite | 3,556 | +153 | 6 days ago | 69.7 | |
| 6 | New Prisma 8 PostgreSQL projects that want agent-assisted schema and query changes: the README documents `npx prisma skills sync` and installed SKILL.md workflows. | Community favourite | 47,677 | +104 | today | 67.7 | |
| 7 | Read-only analysis and monitoring of a PostgreSQL database: it exposes schema, query, and monitoring tools, and starts in readonly mode by default. | Abandoned but popular | 200 | +3 | 96 days ago | 66.3 | |
| 8 | Production PostgreSQL monitoring and maintenance triage: it exposes 34 read-only tools for locks, WAL, replication, bloat, vacuum, and query statistics. | Steady | 160 | -1 | 14 days ago | 62.7 | |
| 9 | Teams already using the VS Code extension: it runs an MCP server over their existing database connections, exposing schemas and query execution to editor agents. | Community favourite | 351 | +14 | 4 days ago | 59.1 | |
| 10 | PostgreSQL alongside other databases through one MCP server: DBX enables natural language queries and database management, with desktop, Docker, CLI, and AI assistant interfaces. | Community favourite | 20,736 | +3,839 | today | 57.5 | |
| 11 | Development against AWS infrastructure with PostgreSQL: it exposes 22 MCP tools for infra snapshots, table schemas, and CREATE INDEX suggestions. | Steady | 22 | +4 | 5 days ago | 56.8 | |
| 12 | For PostgreSQL schema and SQL exploration from an MCP-compatible IDE or CLI: the README documents a prebuilt postgres mode with generic tools. | Community favourite | 16,492 | +251 | 2 days ago | 54.9 | |
| 13 | Exploring and reading an unfamiliar PostgreSQL database: it exposes query, list_schemas, list_tables, and describe_table, with writes off by default. | Community favourite | 23 | +6 | 11 days ago | 54.2 | |
| 14 | Natural-language querying across PostgreSQL, MySQL, and Redis from Claude Desktop or other MCP clients: it documents MCP and HTTP interfaces plus a default read-only mode. | Abandoned but popular | 936 | +20 | 194 days ago | 52.8 | |
| 15 | Exploring an unfamiliar PostgreSQL schema before writing joins: it exposes table, column, schema, and ERD metadata tools plus a native EXPLAIN tool. | Community favourite | 5,030 | +17 | today | 52.5 | |
| 16 | Querying a PostgreSQL database from an agent with writes blocked by default: the query tool runs SQL, and DANGEROUSLY_ALLOW_WRITE_OPS must be set to allow writes. | Abandoned but popular | 180 | 0 | 328 days ago | 51.5 | |
| 17 | PostgreSQL administration and observability through MCP: README documents Code Mode in a V8 isolate, connection pooling, and OAuth 2.1. | Steady | 12 | 0 | 6 days ago | 51.0 | |
| 18 | AI agents needing governed natural-language access to PostgreSQL: GraphJin documents GraphQL and MCP interfaces, schema discovery, and SQL compilation. | Community favourite | 3,173 | +22 | 12 days ago | 49.7 | |
| 19 | Shipping an AI-generated app to Tencent CloudBase: it exposes MCP tools to query and change data, manage functions and hosting, and deploy from chat. | Community favourite | 1,126 | +47 | today | 49.7 | |
| 20 | Teams self-hosting a markdown wiki who want agents to search, read, and write pages: tela ships a built-in MCP server exposing 41 tools. | Emerging | 69 | +15 | today | 49.3 |
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 PostgreSQL (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: Agents writing PostgreSQL schema and SQL: its documented MCP server serves semantic search over version-aware PostgreSQL, TimescaleDB, and PostGIS documentation.
pg-aiguide ships a public MCP server at a TigerData-hosted URL for semantic search across the PostgreSQL, TimescaleDB, and PostGIS manuals, alongside installable Agent Skills and a Claude Code plugin carrying curated Postgres guidance. The MCP route is a remote hosted endpoint rather than a local process, and the extension documentation begins with TimescaleDB, so teams outside that ecosystem should confirm coverage before adopting it.
GitHub stars1,847Stars / 30 days+17npm / typical week56PyPI / typical weekno attributed packageTools exposednever inspectedLast commit2 days agoCommits / 12 weeks16Maintenance gradeATool descriptionsNot gradedScore 82.9: show every number behind it
- Adoption84 / 100 · weight 40%
- GitHub stars82
- npm downloads19downloads show none of the weekday rhythm human traffic has; halved
- Used through Glamanot measurednot used through Glama in the last 30 days
- Maintenance97 / 100 · weight 24%
- Last commit touching this server100
- Repository maintenance grade100
- Commit cadence85
- Momentum57 / 100 · weight 14%
- Stars gained, relative to size38
- Stars gained, absolute51
- npm download trend100
- 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
- 82.9
- × relevance: the keyword is dedicated here
- 1.00
- × continuity: actively changing
- 1.00
- × evidence: widely adopted
- 1.00
- Composite score
- 82.9
Best for: Diagnosing slow PostgreSQL queries and index health: it exposes explain-plan, index-tuning, health-check, and SQL execution tools.
Postgres MCP Pro exposes nine tools for listing schemas and objects, showing object details, explaining query plans, analyzing workload and query indexes, checking database health, reporting top queries, and executing SQL, and it supports both stdio and SSE transports. It assumes database credentials plus either Docker or Python 3.12 or higher, and its configurable access mode allows read-only operation, though the slow-query tool depends on the pg_stat_statements extension.
GitHub stars3,340Stars / 30 days+114npm / typical weekShips no npm packagePyPI / typical weekno attributed packageTools exposed9Last commit43 days agoCommits / 12 weeks1Maintenance gradeDTool descriptionsAScore 81.9: show every number behind it
- Adoption88 / 100 · weight 40%
- GitHub stars88
- 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
- Momentum78 / 100 · weight 14%
- Stars gained, relative to size75
- Stars gained, absolute83
- npm download trendnot measuredno download history for the selected registry
- 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
- 81.9
- × relevance: the keyword is dedicated here
- 1.00
- × continuity: actively changing
- 1.00
- × evidence: widely adopted
- 1.00
- Composite score
- 81.9
Best for: Internal, trusted developer workflows needing natural-language SQL against PostgreSQL 14+: it enables SQL queries through MCP-compatible clients and includes a natural-language agent.。
The pgEdge Postgres MCP Server enables SQL queries against PostgreSQL databases through MCP-compatible clients and documents interfaces including a web client, Go chat client, Claude Desktop, and Cursor, plus a natural language agent for forming SQL queries. Before choosing it, note that it provides LLMs with read access to the entire database schema and data and is not intended for public-facing applications, so it should be used only in internal or trusted-user environments.
GitHub stars230Stars / 30 days+12npm / typical weekShips no npm packagePyPI / typical weekno attributed packageTools exposednever inspectedLast commit11 days agoCommits / 12 weeks91Maintenance gradeATool descriptionsNot gradedScore 74.2: show every number behind it
- Adoption59 / 100 · weight 40%
- GitHub stars59
- 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 size74
- Stars gained, absolute45
- npm download trendnot measuredno download history for the selected registry
- Tool quality≈68 / 100 · weight 13%
- Tool description quality≈68tool descriptions not yet scored
- Built and inspected by Glamanot measurednever built and inspected by Glama
- Trust100 / 100 · weight 9%
- License100
- Published by the vendor it integrates100
- Weighted mean of the five
- 74.2
- × relevance: the keyword is dedicated here
- 1.00
- × continuity: actively changing
- 1.00
- × evidence: widely adopted
- 1.00
- Composite score
- 74.2
Best for: Teams running a self-hosted Butterbase backend that want agents to manage its Postgres, RLS, auth, storage, functions, realtime, KV, AI gateway, and RAG through /mcp.
Butterbase documents a built-in MCP server at /mcp for HTTP on self-hosted instances and via stdio with @butterbase/mcp, exposing its Postgres, RLS, auth, storage, serverless TypeScript functions, durable objects, realtime, KV, AI gateway, and RAG capabilities. Before choosing it, note that the HTTP /mcp interface assumes a self-hosted Butterbase instance, and the stdio route depends on @butterbase/mcp, which is not published.
GitHub stars3,672Stars / 30 days+443npm / typical weekShips no npm packagePyPI / typical weekno attributed packageTools exposednever inspectedLast commityesterdayCommits / 12 weeks185Maintenance gradeBTool descriptionsNot gradedScore 70.4: show every number behind it
- Adoption89 / 100 · weight 40%
- GitHub stars89
- npm downloadsnot measuredno npm package
- 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
- Momentum100 / 100 · weight 14%
- Stars gained, relative to size100
- Stars gained, absolute100
- npm download trendnot measuredno download history for the selected registry
- Tool quality≈68 / 100 · weight 13%
- Tool description quality≈68tool descriptions not yet scored
- Built and inspected by Glamanot measurednever built and inspected by Glama
- Trust100 / 100 · weight 9%
- License100
- Published by the vendor it integrates100
- Weighted mean of the five
- 90.3
- × relevance: the keyword is declared here
- 0.78
- × continuity: actively changing
- 1.00
- × evidence: widely adopted
- 1.00
- Composite score
- 70.4
Best for: Read-only diagnostics or local development across PostgreSQL and other databases: it exposes execute_sql and search_objects with guardrails such as read-only mode.
DBHub is an MCP server that connects MCP-compatible clients to PostgreSQL and other databases, documenting execute_sql for SQL execution and search_objects for schema exploration, with opt-in explain_sql, health_check, and custom tools. Before adopting it, know that it is configured through command-line options or a TOML file, and its README directs users needing approval flow, access control, data masking, or audit logging to a separate Bytebase offering.
GitHub stars3,556Stars / 30 days+153npm / typical weekdownloads not countedPyPI / typical weekno attributed packageTools exposednever inspectedLast commit6 days agoCommits / 12 weeks87Maintenance gradeATool descriptionsNot gradedScore 69.7: 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
- Momentum86 / 100 · weight 14%
- Stars gained, relative to size85
- Stars gained, absolute88
- npm download trendnot measuredno download history for the selected registry
- Tool quality≈68 / 100 · weight 13%
- Tool description quality≈68tool descriptions not yet scored
- Built and inspected by Glamanot measurednever built and inspected by Glama
- Trust100 / 100 · weight 9%
- License100
- Published by the vendor it integratesnot measurednot published by the vendor it integrates
- Weighted mean of the five
- 89.4
- × relevance: the keyword is declared here
- 0.78
- × continuity: actively changing
- 1.00
- × evidence: widely adopted
- 1.00
- Composite score
- 69.7
Best for: New Prisma 8 PostgreSQL projects that want agent-assisted schema and query changes: the README documents `npx prisma skills sync` and installed SKILL.md workflows.
The server is listed for Prisma Postgres databases, while its README documents Prisma 8 ORM setup on Node.js 24 or newer through
npm create prisma,npx prisma orm init, andnpx prisma skills sync. Before choosing it, note that its tool list has never been inspected, so the exposed tools are unknown.GitHub stars47,677Stars / 30 days+104npm / typical weekdownloads not countedPyPI / typical weekno attributed packageTools exposednever inspectedLast committodayCommits / 12 weeks405Maintenance gradeBTool descriptionsNot gradedScore 67.7: 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
- Momentum44 / 100 · weight 14%
- Stars gained, relative to size19
- Stars gained, absolute82
- npm download trendnot measuredno download history for the selected registry
- Tool quality≈68 / 100 · weight 13%
- Tool description quality≈68tool descriptions not yet scored
- Built and inspected by Glamanot measurednever built and inspected by Glama
- Trust100 / 100 · weight 9%
- License100
- Published by the vendor it integrates100
- Weighted mean of the five
- 86.8
- × relevance: the keyword is declared here
- 0.78
- × continuity: actively changing
- 1.00
- × evidence: widely adopted
- 1.00
- Composite score
- 67.7
Best for: Read-only analysis and monitoring of a PostgreSQL database: it exposes schema, query, and monitoring tools, and starts in readonly mode by default.
PostgreSQL MCP Server is an npm-installable MCP server exposing 18 tools for PostgreSQL schema, function, trigger, index, constraint, RLS, user, query, mutation, comment, import/export, copy, and monitoring operations. It starts in readonly mode by default, so mutations, DDL, role administration, filesystem import/export, and arbitrary SQL require explicit security-mode flags.
GitHub stars200Stars / 30 days+3npm / typical week1.9KPyPI / typical weekno attributed packageTools exposed18Last commit96 days agoCommits / 12 weeks0Maintenance gradeDTool descriptionsBScore 66.3: show every number behind it
- Adoption79 / 100 · weight 40%
- GitHub stars58
- npm downloads70
- 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
- Momentum29 / 100 · weight 14%
- Stars gained, relative to size37
- Stars gained, absolute24
- npm download trend20
- 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
- 66.3
- × relevance: the keyword is dedicated here
- 1.00
- × continuity: actively changing
- 1.00
- × evidence: widely adopted
- 1.00
- Composite score
- 66.3
Best for: Production PostgreSQL monitoring and maintenance triage: it exposes 34 read-only tools for locks, WAL, replication, bloat, vacuum, and query statistics.
MCP PostgreSQL Operations is an MCP server that exposes 34 read-only tools for PostgreSQL monitoring and operations, including locks, WAL, replication, server and database metadata, schemas, table relationships, connections, query statistics, sizes, configuration, index usage, vacuum and autovacuum activity, bloat, database statistics, background writer, I/O, functions, and standby conflicts. Before choosing it, note that advanced query analysis is enhanced by installing the pg_stat_statements extension, with pg_stat_monitor optional, while most other features work without them.
GitHub stars160Stars / 30 days-1npm / typical weekShips no npm packagePyPI / typical weekno attributed packageTools exposed34Last commit14 days agoCommits / 12 weeks9Maintenance gradeBTool descriptionsAScore 62.7: show every number behind it
- Adoption55 / 100 · weight 40%
- GitHub stars55
- npm downloadsnot measuredno npm package
- Used through Glamanot measurednot used through Glama in the last 30 days
- Maintenance88 / 100 · weight 24%
- Last commit touching this server100
- Repository maintenance grade80
- Commit cadence65
- Momentum0 / 100 · weight 14%
- Stars gained, relative to size0
- Stars gained, absolute0
- npm download trendnot measuredno download history for the selected registry
- Tool quality81 / 100 · weight 13%
- Tool description quality73
- 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
- 62.7
- × relevance: the keyword is dedicated here
- 1.00
- × continuity: actively changing
- 1.00
- × evidence: widely adopted
- 1.00
- Composite score
- 62.7
Best for: Teams already using the VS Code extension: it runs an MCP server over their existing database connections, exposing schemas and query execution to editor agents.
DBCode is a VS Code extension that runs an MCP server giving agents access to connected databases, their schemas, and query execution. Its exposed tool set is not documented in the repository, and it requires the extension installed with database connections already configured, since agents use those connections under per-connection AI permissions.
GitHub stars351Stars / 30 days+14npm / typical weekdownloads not countedPyPI / typical weekno attributed packageTools exposednever inspectedLast commit4 days agoCommits / 12 weeks70Maintenance gradeATool descriptionsNot gradedScore 59.1: 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
- Momentum61 / 100 · weight 14%
- Stars gained, relative to size70
- Stars gained, absolute48
- npm download trendnot measuredno download history for the selected registry
- Tool quality≈68 / 100 · weight 13%
- Tool description quality≈68tool descriptions not yet scored
- Built and inspected by Glamanot measurednever built and inspected by Glama
- Trust100 / 100 · weight 9%
- License100
- Published by the vendor it integratesnot measurednot published by the vendor it integrates
- Weighted mean of the five
- 75.8
- × relevance: the keyword is declared here
- 0.78
- × continuity: actively changing
- 1.00
- × evidence: widely adopted
- 1.00
- Composite score
- 59.1
Best for: PostgreSQL alongside other databases through one MCP server: DBX enables natural language queries and database management, with desktop, Docker, CLI, and AI assistant interfaces.
The dbx npm package provides an MCP server for DBX, a database manager available as Desktop, Docker, CLI, built-in AI assistant, and MCP Server, enabling natural language queries and database management through MCP. Its tool list has not been inspected, so the specific database operations it exposes cannot be confirmed before installation.
GitHub stars20,736Stars / 30 days+3,839npm / typical weekdownloads not countedPyPI / typical weekno attributed packageTools exposednever inspectedLast committodayCommits / 12 weeks4,437Maintenance gradeATool descriptionsNot gradedScore 57.5: show every number behind it
- Adoption100 / 100 · weight 40%
- GitHub stars100
- npm downloadsnot measurednpm publishes dbx from samt/node-dbx
- Used through Glamanot measurednot used through Glama in the last 30 days
- Maintenance100 / 100 · weight 24%
- Last commit touching this server100
- Repository maintenance grade100
- Commit cadence100
- Momentum100 / 100 · weight 14%
- Stars gained, relative to size100
- Stars gained, absolute100
- npm download trendnot measuredno download history for the selected registry
- Tool quality≈68 / 100 · weight 13%
- Tool description quality≈68tool descriptions not yet scored
- Built and inspected by Glamanot measurednever built and inspected by Glama
- Trust100 / 100 · weight 9%
- License100
- Published by the vendor it integratesnot measurednot published by the vendor it integrates
- Weighted mean of the five
- 95.8
- × relevance: the keyword is tagged here
- 0.60
- × continuity: actively changing
- 1.00
- × evidence: widely adopted
- 1.00
- Composite score
- 57.5
Best for: Development against AWS infrastructure with PostgreSQL: it exposes 22 MCP tools for infra snapshots, table schemas, and CREATE INDEX suggestions.
Infrawise statically analyzes a codebase and connected cloud services, then exposes 22 MCP tools through Claude Code, Cursor, or VS Code, among them get_infra_overview, get_table_schema, postgres_index_suggestions, get_queue_details, and get_log_errors. Its tools are read-and-suggest only (get_, analyze_, suggest_ prefixes), so it returns schemas, findings, and index DDL rather than executing queries, and the README requires Node.js 22 or later plus an AWS profile selected on first run.
GitHub stars22Stars / 30 days+4npm / typical week336PyPI / typical weekno attributed packageTools exposed22Last commit5 days agoCommits / 12 weeks221Maintenance gradeATool descriptionsAScore 56.8: show every number behind it
- Adoption59 / 100 · weight 40%
- GitHub stars34
- npm downloads54
- 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
- Momentum37 / 100 · weight 14%
- Stars gained, relative to size64
- Stars gained, absolute29
- npm download trend0
- Tool quality85 / 100 · weight 13%
- Tool description quality77
- 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
- 72.8
- × relevance: the keyword is declared here
- 0.78
- × continuity: actively changing
- 1.00
- × evidence: widely adopted
- 1.00
- Composite score
- 56.8
Best for: For PostgreSQL schema and SQL exploration from an MCP-compatible IDE or CLI: the README documents a prebuilt postgres mode with generic tools.
MCP Toolbox for Databases is an MCP server that the README documents as connecting MCP clients to databases through prebuilt generic tools (for example, list_tables and execute_sql) and through a custom tools framework for predefined queries and semantic search. Before choosing it, note that the prebuilt PostgreSQL setup assumes an MCP client configuration and environment variables for the database connection.
GitHub stars16,492Stars / 30 days+251npm / typical weekShips no npm packagePyPI / typical weekno attributed packageTools exposednever inspectedLast commit2 days agoCommits / 12 weeks247Maintenance gradeATool descriptionsNot gradedScore 54.9: show every number behind it
- Adoption100 / 100 · weight 40%
- GitHub stars100
- npm downloadsnot measuredno npm package
- Used through Glamanot measurednot used through Glama in the last 30 days
- Maintenance100 / 100 · weight 24%
- Last commit touching this server100
- Repository maintenance grade100
- Commit cadence100
- Momentum69 / 100 · weight 14%
- Stars gained, relative to size50
- Stars gained, absolute97
- npm download trendnot measuredno download history for the selected registry
- Tool quality≈68 / 100 · weight 13%
- Tool description quality≈68tool descriptions not yet scored
- Built and inspected by Glamanot measurednever built and inspected by Glama
- Trust100 / 100 · weight 9%
- License100
- Published by the vendor it integratesnot measurednot published by the vendor it integrates
- Weighted mean of the five
- 91.5
- × relevance: the keyword is tagged here
- 0.60
- × continuity: actively changing
- 1.00
- × evidence: widely adopted
- 1.00
- Composite score
- 54.9
Best for: Exploring and reading an unfamiliar PostgreSQL database: it exposes query, list_schemas, list_tables, and describe_table, with writes off by default.
MCP PostgreSQL Server connects over stdio to a PostgreSQL database and exposes five tools: query, execute, list_schemas, list_tables, and describe_table. It requires Node.js 20 or newer, and it is read-only by default, with execute refusing writes unless PG_ALLOW_WRITE is set to true.
GitHub stars23Stars / 30 days+6npm / typical week714PyPI / typical weekno attributed packageTools exposed5Last commit11 days agoCommits / 12 weeks16Maintenance gradeBTool descriptionsAScore 54.2: show every number behind it
- Adoption65 / 100 · weight 40%
- GitHub stars35
- npm downloads60downloads capped: not corroborated by repository audience
- Used through Glamanot measurednot used through Glama in the last 30 days
- Maintenance92 / 100 · weight 24%
- Last commit touching this server100
- Repository maintenance grade80
- Commit cadence85
- Momentum57 / 100 · weight 14%
- Stars gained, relative to size79
- Stars gained, absolute35
- npm download trend46
- Tool quality96 / 100 · weight 13%
- Tool description quality88
- 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
- 77.4
- × relevance: the keyword is dedicated here
- 1.00
- × continuity: actively changing
- 1.00
- × evidence: small audience
- 0.70
- Composite score
- 54.2
Best for: Natural-language querying across PostgreSQL, MySQL, and Redis from Claude Desktop or other MCP clients: it documents MCP and HTTP interfaces plus a default read-only mode.
Universal DB MCP documents MCP stdio, MCP SSE, MCP Streamable HTTP, and REST API interfaces for querying and analyzing MySQL, PostgreSQL, Redis, and other databases listed in its README. The dependency worth noting is Node.js 20 or newer.
GitHub stars936Stars / 30 days+20npm / typical week112PyPI / typical weekno attributed packageTools exposednever inspectedLast commit194 days agoCommits / 12 weeks0Maintenance gradeDTool descriptionsNot gradedScore 52.8: show every number behind it
- Adoption81 / 100 · weight 40%
- GitHub stars74
- npm downloads44
- 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
- Momentum47 / 100 · weight 14%
- Stars gained, relative to size56
- Stars gained, absolute53
- npm download trend24
- 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
- 67.7
- × relevance: the keyword is declared here
- 0.78
- × continuity: actively changing
- 1.00
- × evidence: widely adopted
- 1.00
- Composite score
- 52.8
Best for: Exploring an unfamiliar PostgreSQL schema before writing joins: it exposes table, column, schema, and ERD metadata tools plus a native EXPLAIN tool.
The MCP server is part of WhoDB CLI and exposes 12 tools: connection, schema, table, and column listings, ERD and starter-query metadata, audit and schema-diff checks, EXPLAIN, and query execution, with pending writes listed by whodb_pending and executed by whodb_confirm. Setup goes through the CLI README linked from the main repository, since no npm or PyPI package is published.
GitHub stars5,030Stars / 30 days+17npm / typical weekShips no npm packagePyPI / typical weekno attributed packageTools exposed12Last committodayCommits / 12 weeks546Maintenance gradeATool descriptionsAScore 52.5: 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
- Momentum34 / 100 · weight 14%
- Stars gained, relative to size24
- Stars gained, absolute51
- 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
- 87.5
- × relevance: the keyword is tagged here
- 0.60
- × continuity: actively changing
- 1.00
- × evidence: widely adopted
- 1.00
- Composite score
- 52.5
Best for: Querying a PostgreSQL database from an agent with writes blocked by default: the query tool runs SQL, and DANGEROUSLY_ALLOW_WRITE_OPS must be set to allow writes.
Postgres MCP Server exposes a query tool that executes SQL, plus resources for listing tables and returning a table's schema and sample data, and it runs over stdio by default or HTTP at /mcp. Choosing it means supplying a DATABASE_URL connection string, since write operations stay disabled unless DANGEROUSLY_ALLOW_WRITE_OPS is enabled.
GitHub stars180Stars / 30 days0npm / typical week182PyPI / typical weekno attributed packageTools exposednever inspectedLast commit328 days agoCommits / 12 weeks0Maintenance gradeDTool descriptionsNot gradedScore 51.5: show every number behind it
- Adoption64 / 100 · weight 40%
- GitHub stars56
- npm downloads48
- Used through Glamanot measurednot used through Glama in the last 30 days
- Maintenance32 / 100 · weight 24%
- Last commit touching this server42dated from the last commit on the default branch, re-read from GitHub at publication; github.com shows a push 39 days ago, which counts every ref; the stored date would have published 39 days ago
- Repository maintenance grade30
- Commit cadence5
- Momentum5 / 100 · weight 14%
- Stars gained, relative to size0
- Stars gained, absolute0
- npm download trend18
- 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
- 51.5
- × relevance: the keyword is dedicated here
- 1.00
- × continuity: actively changing
- 1.00
- × evidence: widely adopted
- 1.00
- Composite score
- 51.5
Best for: PostgreSQL administration and observability through MCP: README documents Code Mode in a V8 isolate, connection pooling, and OAuth 2.1.
The README documents a PostgreSQL MCP server that binds the Model Context Protocol to a PostgreSQL sandbox and includes Code Mode through a V8 isolate, schema introspection, migration tracking, connection pooling, HTTP/SSE transport, OAuth 2.1 authentication, and extension support for citext, ltree, pgcrypto, pg_cron, pg_stat_kcache, pgvector, PostGIS, and HypoPG. Installation is documented through the npm package @neverinfamous/postgres-mcp and Docker, and no PyPI package is attributed.
GitHub stars12Stars / 30 days0npm / typical week74PyPI / typical weekno attributed packageTools exposednever inspectedLast commit6 days agoCommits / 12 weeks14Maintenance gradeATool descriptionsNot gradedScore 51.0: show every number behind it
- Adoption44 / 100 · weight 40%
- GitHub stars28
- npm downloads40
- Used through Glamanot measurednot used through Glama in the last 30 days
- Maintenance97 / 100 · weight 24%
- Last commit touching this server100
- Repository maintenance grade100
- Commit cadence85
- Momentum10 / 100 · weight 14%
- Stars gained, relative to size0
- Stars gained, absolute0
- npm download trend38
- 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
- 60.0
- × relevance: the keyword is dedicated here
- 1.00
- × continuity: actively changing
- 1.00
- × evidence: modest but real audience
- 0.85
- Composite score
- 51.0
Best for: AI agents needing governed natural-language access to PostgreSQL: GraphJin documents GraphQL and MCP interfaces, schema discovery, and SQL compilation.
GraphJin exposes GraphQL and MCP interfaces so AI agents can discover schema, compile SQL, and query PostgreSQL alongside other sources. Before choosing it, note that its built-in agent mode requires a model API key in ./.env (OPENAI_API_KEY, ANTHROPIC_API_KEY, or GOOGLE_APIKEY).
GitHub stars3,173Stars / 30 days+22npm / typical week452PyPI / typical weekno attributed packageTools exposednever inspectedLast commit12 days agoCommits / 12 weeks513Maintenance gradeATool descriptionsNot gradedScore 49.7: show every number behind it
- Adoption92 / 100 · weight 40%
- GitHub stars88
- npm downloads28downloads show none of the weekday rhythm human traffic has; halved
- Used through Glamanot measurednot used through Glama in the last 30 days
- Maintenance100 / 100 · weight 24%
- Last commit touching this server100
- Repository maintenance grade100
- Commit cadence100
- Momentum31 / 100 · weight 14%
- Stars gained, relative to size33
- 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 integrates100
- Weighted mean of the five
- 82.8
- × relevance: the keyword is tagged here
- 0.60
- × continuity: actively changing
- 1.00
- × evidence: widely adopted
- 1.00
- Composite score
- 49.7
Best for: Shipping an AI-generated app to Tencent CloudBase: it exposes MCP tools to query and change data, manage functions and hosting, and deploy from chat.
CloudBase MCP is the MCP component of the CloudBase AI Toolkit, connecting AI IDEs such as Cursor, Claude Code, Codex and CodeBuddy to Tencent CloudBase so the assistant can log in, query and change data, manage functions and hosting, read logs, and call Cloud APIs from the conversation. It requires a CloudBase environment of the user's own and targets Tencent CloudBase rather than a standalone PostgreSQL instance: PostgreSQL appears in the documented surface as a Cloud API service that callCloudApi can open, and as a PostgreSQL access-pattern skill.
GitHub stars1,126Stars / 30 days+47npm / typical weekShips no npm packagePyPI / typical weekno attributed packageTools exposednever inspectedLast committodayCommits / 12 weeks775Maintenance gradeATool descriptionsNot gradedScore 49.7: show every number behind it
- Adoption76 / 100 · weight 40%
- GitHub stars76
- 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
- Momentum75 / 100 · weight 14%
- Stars gained, relative to size80
- Stars gained, absolute68
- npm download trendnot measuredno download history for the selected registry
- Tool quality≈68 / 100 · weight 13%
- Tool description quality≈68tool descriptions not yet scored
- Built and inspected by Glamanot measurednever built and inspected by Glama
- Trust100 / 100 · weight 9%
- License100
- Published by the vendor it integrates100
- Weighted mean of the five
- 82.8
- × relevance: the keyword is tagged here
- 0.60
- × continuity: actively changing
- 1.00
- × evidence: widely adopted
- 1.00
- Composite score
- 49.7
Best for: Teams self-hosting a markdown wiki who want agents to search, read, and write pages: tela ships a built-in MCP server exposing 41 tools.
tela is a self-hostable markdown wiki with a built-in MCP server at /api/mcp whose 41 tools let agents search, read, write, and organize pages, spaces, comments, attachments, shares, decks, sheets, and Atlas documentation runs. It does not expose SQL query or schema tools: the tools operate on tela wiki content rather than arbitrary SQL.
GitHub stars69Stars / 30 days+15npm / typical weekShips no npm packagePyPI / typical weekno attributed packageTools exposed41Last committodayCommits / 12 weeks227Maintenance gradeATool descriptionsAScore 49.3: show every number behind it
- Adoption46 / 100 · weight 40%
- GitHub stars46
- 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
- Momentum79 / 100 · weight 14%
- Stars gained, relative to size100
- Stars gained, absolute49
- npm download trendnot measuredno download history for the selected registry
- 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
- 74.4
- × relevance: the keyword is declared here
- 0.78
- × continuity: actively changing
- 1.00
- × evidence: modest but real audience
- 0.85
- Composite score
- 49.3
Questions people ask
DBHub or Postgres MCP for query tuning?
They aim at different work. DBHub is a universal database MCP server for MySQL, PostgreSQL, SQLite, DuckDB and more, and its guardrails such as read-only mode suit diagnostics and local development; it had a commit 6 days ago and 87 commits on its default branch in the last 12 weeks. Postgres MCP (crystaldba/postgres-mcp) is pointed squarely at explain plans, index tuning, health checks and SQL execution through 9 tools with a tool description grade of A, which makes it the better fit when the goal is making a slow query faster. Be aware that Postgres MCP had 1 commit on its default branch in the last 12 weeks.
Does pg-aiguide connect to my database?
No. pg-aiguide performs semantic search across PostgreSQL, TimescaleDB and PostGIS documentation so an assistant writes better SQL, and it does not execute queries against your database. It gained 17 stars per 30 days and had a commit 2 days ago, with 16 commits on its default branch in the last 12 weeks; its npm package @tigerdata/pg-aiguide had 56 downloads in a typical week. Pair it with a server that actually connects, such as DBHub or MCP PostgreSQL Server.
Which of these can I point at production?
Several are built for read-only use. MCP PostgreSQL Operations exposes 34 read-only tools for locks, WAL, replication, bloat, vacuum and query statistics; DBHub documents guardrails such as read-only mode; and PostgreSQL MCP Server (HenkDz/postgresql-mcp-server) starts in readonly mode by default. That last one is labelled Abandoned but popular, with 0 commits on its default branch in the last 12 weeks and a last commit 96 days ago, so treat it as a fixed snapshot rather than something being maintained.
Which of these are no longer maintained?
Three carry the Abandoned but popular label. PostgreSQL MCP Server (HenkDz/postgresql-mcp-server) had 0 commits on its default branch in the last 12 weeks and a last commit 96 days ago, Universal DB MCP had 0 commits in the last 12 weeks and a last commit 194 days ago, and Postgres MCP Server (ericzakariasson/pg-mcp-server) had 0 commits in the last 12 weeks and a last commit 328 days ago. None of the three has been archived by its owner.
What does Prisma MCP Server need before it will run?
It is aimed at new Prisma 8 PostgreSQL projects, and its README documents npx prisma skills sync plus installed SKILL.md workflows, so you need that setup rather than a bare connection string. It had a commit 0 days ago and 405 commits on its default branch in the last 12 weeks, which makes it one of the busier projects here. If you are not on Prisma, DBHub or Postgres MCP will get you further.