20 Best MongoDB MCP Servers, Compared (November 2026)

The short answer

Which one, for your situation

Top MCP servers for MongoDB

The ranking, with the evidence

• 1

  MongoDB MCP Server

  Community favourite

  mongodb-js/mongodb-mcp-server ↗

  Best for: Managing MongoDB Atlas from an AI assistant: it exposes Atlas cluster, project, access-list, alert, and performance-advisor tools alongside database operations.

  MongoDB MCP Server runs queries and aggregations, describes collection schemas and indexes, and manages Atlas resources such as clusters, database users, projects, and alerts across 28 exposed tools. Setup goes through an interactive npx script or bundled agent plugins, and the Atlas plugin route connects to a MongoDB-hosted server over OAuth rather than running the server locally.

  Score 90.2: show every number behind it

  • Adoption100 / 100 · weight 40%
    • GitHub stars77
    • npm downloads100
    • 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
  • Momentum65 / 100 · weight 14%
    • Stars gained, relative to size53
    • Stars gained, absolute54
    • npm download trend98
  • Tool quality63 / 100 · weight 13%
    • Tool description quality55
    • Built and inspected by Glama100
  • Trust100 / 100 · weight 9%
    • License100
    • Published by the vendor it integrates100

  Weighted mean of the five

  90.2

  × relevance: the keyword is dedicated here

  1.00

  × continuity: actively changing

  1.00

  × evidence: widely adopted

  1.00

  Composite score

  90.2

• 2

  MongoDB

  Abandoned but popular

  kiliczsh/mcp-mongo-server ↗

  Best for: Read-only MongoDB exploration from an MCP client: the server exposes 8 tools and has a read-only mode that blocks writes.

  It provides an MCP server for MongoDB that exposes 8 tools (query, aggregate, update, serverInfo, insert, createIndex, count, and listCollections) over stdio or an HTTP endpoint. Before choosing it, note that it requires Node.js 20 or newer.

  Score 66.9: show every number behind it

  • Adoption69 / 100 · weight 40%
    • GitHub stars61
    • npm downloads50
    • Used through Glamanot measured
      not used through Glama in the last 30 days
  • Maintenance69 / 100 · weight 24%
    • Last commit touching this server88
    • Repository maintenance grade80
    • Commit cadence5
  • Momentum35 / 100 · weight 14%
    • Stars gained, relative to size33
    • Stars gained, absolute24
    • npm download trend51
  • 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

  66.9

  × relevance: the keyword is dedicated here

  1.00

  × continuity: actively changing

  1.00

  × evidence: widely adopted

  1.00

  Composite score

  66.9

• 3

  ArcadeDB Multi-Model DBMS

  Community favourite

  ArcadeData/arcadedb ↗

  Best for: ArcadeDB users needing MCP access to inspect schemas, run read-only queries, execute write commands, and profile queries: it exposes ten tools for those operations.

  It exposes ten tools for ArcadeDB operations: list databases, read schemas, run read-only queries, execute write commands, check server status, profile queries, and read or update server settings. The tools operate on an authenticated ArcadeDB server, and none of its exposed tools targets MongoDB specifically.

  Score 66.2: show every number behind it

  • Adoption77 / 100 · weight 40%
    • GitHub stars77
    • 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
  • Momentum75 / 100 · weight 14%
    • Stars gained, relative to size79
    • Stars gained, absolute69
    • npm download trendnot measured
      no 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 integrates100

  Weighted mean of the five

  84.9

  × relevance: the keyword is declared here

  0.78

  × continuity: actively changing

  1.00

  × evidence: widely adopted

  1.00

  Composite score

  66.2

• 4

  DBCode

  Community favourite

  dbcodeio/public ↗

  Best for: Managing MongoDB from VS Code while giving an AI agent access: DBCode runs an MCP server over existing connections with schema access and query execution.

  DBCode is a VS Code extension that can run an MCP server, exposing existing database connections, database schemas, and query execution to AI agents. The dependency to plan for is that it runs as a VS Code extension, and agents use the connections configured there with AI permissions set per connection.

  Score 57.5: 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
  • Maintenance100 / 100 · weight 24%
    • Last commit touching this server100
    • Repository maintenance grade100
    • Commit cadence100
  • Momentum48 / 100 · weight 14%
    • Stars gained, relative to size53
    • Stars gained, absolute40
    • npm download trendnot measured
      no download history for the selected registry
  • Tool quality≈65 / 100 · weight 13%
    • Tool description quality≈65
      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

  73.7

  × relevance: the keyword is declared here

  0.78

  × continuity: actively changing

  1.00

  × evidence: widely adopted

  1.00

  Composite score

  57.5

• 5

  dbx

  Community favourite

  t8y2/dbx ↗

  Best for: DBX users who need MCP access to DBX-managed databases: the README documents an MCP Server interface.

  dbx provides an MCP interface to the DBX database manager, which the README documents alongside desktop, Docker, CLI, and built-in AI assistant interfaces. Its MCP tool list has not been measured, so the exact database operations exposed through MCP are not established.

  Score 57.3: 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
  • 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 measured
      no download history for the selected registry
  • Tool quality≈65 / 100 · weight 13%
    • Tool description quality≈65
      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

  95.5

  × relevance: the keyword is tagged here

  0.60

  × continuity: actively changing

  1.00

  × evidence: widely adopted

  1.00

  Composite score

  57.3

• 6

  MCP Toolbox for Databases

  Community favourite

  googleapis/mcp-toolbox ↗

  Best for: Querying a supported cloud database from an IDE or CLI: the --prebuilt flag loads generic tools like list_tables and execute_sql, configured by environment variables.

  MCP Toolbox for Databases is an MCP server that connects clients such as Gemini CLI, Claude Code, or Codex to databases, exposing prebuilt generic tools (for example list_tables and execute_sql) when started with a --prebuilt=<database> flag, plus a framework for defining custom query tools for production agents. Coverage depends on which prebuilt configuration is selected (the README lists Google Cloud databases including AlloyDB, BigQuery, Cloud SQL, Spanner, and Firestore), and any query beyond those sets has to be authored as a custom tool with connection details supplied through environment variables.

  Score 54.3: 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
  • Maintenance100 / 100 · weight 24%
    • Last commit touching this server100
    • Repository maintenance grade100
    • Commit cadence100
  • Momentum64 / 100 · weight 14%
    • Stars gained, relative to size45
    • Stars gained, absolute93
    • npm download trendnot measured
      no download history for the selected registry
  • Tool quality≈65 / 100 · weight 13%
    • Tool description quality≈65
      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

  90.5

  × relevance: the keyword is tagged here

  0.60

  × continuity: actively changing

  1.00

  × evidence: widely adopted

  1.00

  Composite score

  54.3

• 7

  GraphJin

  Community favourite

  dosco/graphjin ↗

  Best for: AI agents querying MongoDB alongside other databases under policy controls: GraphJin exposes a governed MCP surface with catalog discovery, query validation, and audited execution.

  GraphJin documents GraphQL and MCP interfaces, including an /api/v1/agent endpoint and MCP tools for catalog discovery, query help, security and runtime checks, watches, and an ask_graphjin_agent tool that runs a discovery loop against configured systems. Its built-in agent requires a model API key from OpenAI, Anthropic, or Google.

  Score 50.5: show every number behind it

  • Adoption92 / 100 · weight 40%
    • GitHub stars88
    • npm downloads27
      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
  • Momentum43 / 100 · weight 14%
    • Stars gained, relative to size39
    • Stars gained, absolute60
    • npm download trend30
  • Tool quality≈65 / 100 · weight 13%
    • Tool description quality≈65
      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

  84.2

  × relevance: the keyword is tagged here

  0.60

  × continuity: actively changing

  1.00

  × evidence: widely adopted

  1.00

  Composite score

  50.5

• 8

  Prisma MCP Server

  Community favourite

  prisma/orm ↗

  Best for: New Prisma 8 projects using MongoDB: the documented `npm create prisma` scaffolder wires Prisma 8 in with MongoDB as the chosen database.

  The server's tool list is unknown, while the repository documents Prisma 8 as a TypeScript ORM with the npm create prisma scaffolder, the npx prisma orm init setup command, and agent skill files for supported editor runtimes. Before choosing it, note the README lists Node.js 24 or newer and a package manager as prerequisites.

  Score 48.2: 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≈65 / 100 · weight 13%
    • Tool description quality≈65
      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

  80.3

  × relevance: the keyword is tagged here

  0.60

  × continuity: actively changing

  1.00

  × evidence: widely adopted

  1.00

  Composite score

  48.2

• 9

  mcp-server-db

  Steady

  Nam088/mcp-db-server ↗

  Best for: Running MongoDB alongside Postgres, Redis, Elasticsearch, MySQL, or LDAP in one session: it routes multiple connections and documents MongoDB aggregation, distinct, index, and explain support.

  mcp-server-db is an MCP server that exposes 100 tools for querying and managing Postgres, Redis, Elasticsearch, MySQL, MongoDB, and LDAP, with connections configured through environment variables or a YAML file. Its MongoDB driver is optional, so a local install using --no-optional requires installing mongodb separately.

  Score 35.8: show every number behind it

  • Adoption48 / 100 · weight 40%
    • GitHub stars48
    • npm downloadsnot measured
      npm publishes mcp-server-db from Nam088/mcp-database-server-v2
    • Used through Glamanot measured
      not used through Glama in the last 30 days
  • Maintenance75 / 100 · weight 24%
    • Last commit touching this server88
    • Repository maintenance grade55
    • Commit cadence65
  • Momentum0 / 100 · weight 14%
    • Stars gained, relative to size0
    • Stars gained, absolute0
    • 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 integratesnot measured
      not published by the vendor it integrates

  Weighted mean of the five

  54.0

  × relevance: the keyword is declared here

  0.78

  × continuity: actively changing

  1.00

  × evidence: modest but real audience

  0.85

  Composite score

  35.8

• 10

  infrawise

  Steady

  Sidd27/infrawise ↗

  Best for: Diagnosing AWS infrastructure with MongoDB collections: it exposes suggest_mongo_index plus schema and service tools across DynamoDB, Lambda, SQS, and other AWS services.

  Infrawise exposes 22 MCP tools that scan AWS services and connected databases, including MongoDB schema inspection and suggest_mongo_index, alongside DynamoDB, Lambda, SQS, and other service checks. Before choosing it for MongoDB work, note that it requires Node.js 22 or later and its MongoDB tools cover schema inspection and index-command suggestions within a broader AWS infrastructure analysis scope.

  Score 34.2: show every number behind it

  • Adoption38 / 100 · weight 40%
    • GitHub stars34
    • npm downloads24
      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
  • Momentum25 / 100 · weight 14%
    • Stars gained, relative to size0
    • Stars gained, absolute0
    • npm download trend100
  • 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

  62.6

  × relevance: the keyword is declared here

  0.78

  × continuity: actively changing

  1.00

  × evidence: small audience

  0.70

  Composite score

  34.2

• 11

  mq-bridge

  Steady

  marcomq/mq-bridge ↗

  Best for: Bridging Kafka to MongoDB via MCP: route tools start copy jobs from inline JSON endpoints while rows stay out of model context.

  mq-bridge exposes 11 MCP tools for publishing messages and starting, monitoring, and stopping copy routes between brokers, databases, files, and HTTP endpoints, with endpoints supplied inline as JSON. It is scoped to data movement rather than MongoDB query or administration, and route_messages reads are destructive and only capture routes started with capture_last.

  Score 33.2: show every number behind it

  • Adoption40 / 100 · weight 40%
    • GitHub stars35
    • npm downloadsnot measured
      no npm package
    • Used through Glama30
  • Maintenance100 / 100 · weight 24%
    • Last commit touching this server100
    • Repository maintenance grade100
    • Commit cadence100
  • Momentum≈0 / 100 · weight 14%
    • Stars gained, relative to sizenot measured
      no snapshot history yet
    • Stars gained, absolutenot measured
      no snapshot history yet
    • npm download trendnot measured
      no 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 measured
      not published by the vendor it integrates

  Weighted mean of the five

  60.8

  × relevance: the keyword is declared here

  0.78

  × continuity: actively changing

  1.00

  × evidence: small audience

  0.70

  Composite score

  33.2

• 12

  askdb

  Dormant

  mgorabbani/askdb ↗

  Best for: AI access to production MongoDB or PostgreSQL data with hidden fields omitted: it clones data into a Docker sandbox and strips hidden fields from responses.

  The README documents a self-hosted MCP Streamable HTTP endpoint for MongoDB and PostgreSQL with tools for listing databases, inspecting collection schemas, and running find, aggregate, count, distinct, and sample-documents queries. It depends on Docker: AskDB clones production data into an isolated Docker container that the AI queries instead of the original.

  Score 32.2: show every number behind it

  • Adoption47 / 100 · weight 40%
    • GitHub stars47
    • npm downloadsnot measured
      no npm package
    • Used through Glamanot measured
      not used through Glama in the last 30 days
  • Maintenance52 / 100 · weight 24%
    • Last commit touching this server68
    • Repository maintenance grade55
    • Commit cadence5
  • 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≈65 / 100 · weight 13%
    • Tool description quality≈65
      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 declared here

  0.78

  × continuity: actively changing

  1.00

  × evidence: modest but real audience

  0.85

  Composite score

  32.2

• 13

  Datris MCP Server

  Steady

  datris/datris-platform-oss ↗

  Best for: Agents that must acquire, validate, and land data into MongoDB alongside other stores: it brokers credentials through Vault and gates each action with per-agent policy.

  Datris documents one MCP endpoint that carries an acquire, validate, land, and observe loop across MongoDB, Postgres, Kafka, S3/MinIO, and several vector stores, with AI-generated taps, plain-English validation rules, and natural-language SQL. It is a self-hosted Docker stack rather than a drop-in connector: the installer expects an AI provider key from Anthropic, OpenAI, Grok, Azure OpenAI, or Bedrock and brings up about ten containers, with a reduced-memory path configured through .env settings.

  Score 30.5: show every number behind it

  • Adoption29 / 100 · weight 40%
    • GitHub stars29
    • 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
  • Momentum29 / 100 · weight 14%
    • Stars gained, relative to size38
    • Stars gained, absolute16
    • npm download trendnot measured
      no download history for the selected registry
  • Tool quality≈65 / 100 · weight 13%
    • Tool description quality≈65
      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

  55.9

  × relevance: the keyword is declared here

  0.78

  × continuity: actively changing

  1.00

  × evidence: small audience

  0.70

  Composite score

  30.5

• 14

  MongoDB Lens

  Abandoned but popular

  furey/mongodb-lens ↗

  Best for: Teams managing live MongoDB deployments from an LLM client: the README documents tools for aggregation pipelines, schema inference and comparison, index creation, and query pattern analysis.

  MongoDB Lens is a local MCP server that connects to a MongoDB URI and documents tools for running queries and aggregation pipelines, inferring and comparing collection schemas, creating indexes, managing connection aliases and database users, and dropping collections, databases, or indexes. It assumes a MongoDB connection URI at startup (with a tool to return to that original URI), and its destructive tools such as delete-document, drop-collection, and drop-database require confirmation before they execute.

  Score 29.5: show every number behind it

  • Adoption64 / 100 · weight 40%
    • GitHub stars58
    • npm downloads37
    • Used through Glamanot measured
      not used through Glama in the last 30 days
  • Maintenance25 / 100 · weight 24%
    • Last commit touching this server18
    • Repository maintenance grade55
    • Commit cadence5
  • Momentum2 / 100 · weight 14%
    • Stars gained, relative to size0
    • Stars gained, absolute0
    • npm download trend10
  • Tool quality≈65 / 100 · weight 13%
    • Tool description quality≈65
      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

  49.2

  × relevance: the keyword is dedicated here

  1.00

  × continuity: no change in over a year

  0.60

  × evidence: widely adopted

  1.00

  Composite score

  29.5

• 15

  Memory MCP

  Steady

  JamesANZ/memory-mcp ↗

  Best for: Keeping LLM conversation memory across sessions on your own MongoDB instance: it exposes save, get, add and clear memory tools plus tag-based context archiving.

  The server documents memory tools (save-memories, get-memories, add-memories, clear-memories) alongside context caching tools such as archive-context, retrieve-context, score-relevance, and search-context-by-tags, storing everything in MongoDB. It assumes a running MongoDB instance and a MONGODB_URI connection string (defaulting to mongodb://localhost:27017), and the published npm package requires Node.js 18 or newer.

  Score 28.2: show every number behind it

  • Adoption36 / 100 · weight 40%
    • GitHub stars35
    • 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
  • Maintenance64 / 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 331 days ago
    • Repository maintenance grade30
    • Commit cadence5
  • Momentum33 / 100 · weight 14%
    • Stars gained, relative to size37
    • Stars gained, absolute16
    • npm download trend44
  • Tool quality≈65 / 100 · weight 13%
    • Tool description quality≈65
      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

  51.6

  × relevance: the keyword is declared here

  0.78

  × continuity: actively changing

  1.00

  × evidence: small audience

  0.70

  Composite score

  28.2

• 16

  FastMCP Todo Server

  Steady

  MadnessEngineering/Omnispindle ↗

  Best for: AI agents coordinating multi-project development work: it exposes FastMCP tools for todo, knowledge, session, quest, and semantic search workflows.

  Omnispindle is a Python FastMCP server that documents tools for todo management, knowledge capture, Inventorium session tracking, quests, context bundles, and semantic search, plus stdio and HTTP entry points. Before choosing it, note that it stores requests in MongoDB and its API-mode configuration uses Auth0 login, which opens a browser on the first tool call.

  Score 27.7: show every number behind it

  • Adoption26 / 100 · weight 40%
    • GitHub stars26
    • 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
  • 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≈65 / 100 · weight 13%
    • Tool description quality≈65
      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

  50.7

  × relevance: the keyword is declared here

  0.78

  × continuity: actively changing

  1.00

  × evidence: small audience

  0.70

  Composite score

  27.7

• 17

  MongoDB

  Abandoned but popular

  QuantGeekDev/mongo-mcp ↗

  Best for: Teams running a local MongoDB sandbox who want Claude to read and write documents: it ships find, insert, update and delete operations plus index management.

  It connects to a MongoDB instance through a connection URI supplied on the command line, and its README documents tools for listing collections, querying documents, inserting, updating and deleting single documents, and creating, dropping and listing indexes. Setup requires a full connection URI (including the authSource parameter) and Node.js 18 or later, and since those write tools are included, the credentials it is given need write access to the target database.

  Score 27.3: show every number behind it

  • Adoption59 / 100 · weight 40%
    • GitHub stars56
    • npm downloads16
      downloads show none of the weekday rhythm human traffic has; halved
    • Used through Glamanot measured
      not used through Glama in the last 30 days
  • Maintenance18 / 100 · weight 24%
    • Last commit touching this server18
    • Repository maintenance grade30
    • Commit cadence5
  • Momentum2 / 100 · weight 14%
    • Stars gained, relative to size0
    • Stars gained, absolute0
    • npm download trend7
  • Tool quality≈65 / 100 · weight 13%
    • Tool description quality≈65
      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

  45.5

  × relevance: the keyword is dedicated here

  1.00

  × continuity: no change in over a year

  0.60

  × evidence: widely adopted

  1.00

  Composite score

  27.3

• 18

  hydra-etl

  Steady

  bejaouibechir/Hydra ↗

  Best for: AI-assisted authoring of declarative YAML ETL pipelines using MongoDB, CSV, Parquet, PostgreSQL, MySQL, or API connectors: it validates job manifests before execution.

  The server exposes tools for listing and describing Hydra ETL operations and connectors, reading, validating, and writing job manifests, reading and writing workflow manifests, previewing data files, finding examples, and running jobs or workflows when explicitly requested. It is distributed as the hydra-etl PyPI package and has no npm package, so installation assumes Python.

  Score 26.7: show every number behind it

  • Adoption45 / 100 · weight 40%
    • GitHub stars17
    • PyPI downloads42
      PyPI downloads capped: not corroborated by repository audience
    • 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
  • Momentum0 / 100 · weight 14%
    • Stars gained, relative to size0
    • Stars gained, absolute0
    • PyPI download trendnot measured
      no download history for the selected registry
  • 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

  62.2

  × relevance: the keyword is declared here

  0.78

  × continuity: actively changing

  1.00

  × evidence: no meaningful evidence of adoption

  0.55

  Composite score

  26.7

• 19

  Alibaba Cloud DMS MCP Server

  Dormant

  aliyun/alibabacloud-dms-mcp-server ↗

  Best for: Cross-engine querying across MongoDB and other supported databases: 16 tools cover instance, database, and table metadata, SQL execution, and change-order approval.

  It is an MCP server for Alibaba Cloud DMS that exposes 16 tools for instance and database discovery, table metadata, SQL execution, change-order approval, and SQL generation, fixing, and optimization across supported database engines. Adding an instance requires a username and password and is limited to Aliyun instances.

  Score 26.2: show every number behind it

  • Adoption44 / 100 · weight 40%
    • GitHub stars44
    • npm downloadsnot measured
      no npm package
    • Used through Glamanot measured
      not used through Glama in the last 30 days
  • Maintenance63 / 100 · weight 24%
    • Last commit touching this server88
    • Repository maintenance grade55
    • Commit cadence5
  • Momentum0 / 100 · weight 14%
    • Stars gained, relative to size0
    • Stars gained, absolute0
    • npm download trendnot measured
      no 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 integrates100

  Weighted mean of the five

  51.4

  × relevance: the keyword is tagged here

  0.60

  × continuity: actively changing

  1.00

  × evidence: modest but real audience

  0.85

  Composite score

  26.2

• 20

  db-mcp-server

  Dormant

  stucchi/db-mcp-server ↗

  Best for: Querying an existing MongoDB database from an MCP client without Docker: it accepts DB_TYPE=mongodb with DB_URL and exposes query, describe, list_collections, and aggregate tools.

  db-mcp-server runs one MCP instance per database configured by environment variables and, for MongoDB, documents query, describe, list_collections, aggregate, and status tools. For MongoDB, DB_URL and DB_DATABASE are required, and SSH tunneling is not supported.

  Score 26.2: show every number behind it

  • Adoption37 / 100 · weight 40%
    • GitHub stars12
    • PyPI downloads35
    • 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
  • Momentum18 / 100 · weight 14%
    • Stars gained, relative to size0
    • Stars gained, absolute0
    • PyPI download trend72
  • Tool quality83 / 100 · weight 13%
    • Tool description quality75
    • 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

  48.0

  × relevance: the keyword is declared here

  0.78

  × continuity: actively changing

  1.00

  × evidence: small audience

  0.70

  Composite score

  26.2

Questions people ask

Other comparisons

• Best Figma MCP servers
• Best Obsidian MCP servers
• Best YouTube MCP servers
• Best Jira MCP servers
• Best PostgreSQL MCP servers
• Best MySQL MCP servers
• Best GitHub MCP servers
• Best Notion MCP servers
• Best Linear MCP servers
• Best Discord MCP servers
• Best CRM MCP servers
• Best Payments MCP servers
• Best Ecommerce MCP servers
• Best Social Media MCP servers
• Best Browser Automation MCP servers
• Best Email MCP servers
• Best PDF MCP servers
• Best Kubernetes MCP servers
• Best Docker MCP servers
• Best AWS MCP servers
• Best Spreadsheets MCP servers
• Best SEO MCP servers
• Best Web Search MCP servers
• Best Web Scraping MCP servers
• Best Vector Database MCP servers
• Best Code Execution MCP servers
• Best Calendar MCP servers
• Best Observability MCP servers
• Best Image Generation MCP servers
• Best Speech & Transcription MCP servers
• Best Maps MCP servers
• Best Travel MCP servers
• Best Stock Market MCP servers
• Best Web Analytics MCP servers
• Best Memory MCP servers
• Best Documentation MCP servers
• Best Security MCP servers