20 Best AWS MCP Servers, Compared (November 2026)

The short answer

Which one, for your situation

Top MCP servers for AWS

The ranking, with the evidence

• 1

  AWS Nova Canvas

  Abandoned but popular

  awslabs/mcp ↗

  Best for: Generating mockup, diagram, or UI design concept images from text prompts or hex color palettes: it exposes generate_image and generate_image_with_colors tools.

  AWS Nova Canvas exposes two tools: generate_image for text-prompt image generation and generate_image_with_colors for color-guided generation, with generated images saved to user-specified workspace directories. It requires an AWS account with Amazon Bedrock and Amazon Nova Canvas enabled, plus an AWS profile and region configured for access.

  Score 78.4: 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
  • Maintenance42 / 100 · weight 24%
    • Last commit touching this server42
      dated from the last commit on the default branch, re-read from GitHub at publication; github.com shows a push 0 days ago, which counts every ref
    • Repository maintenance gradenot measured
      repository is active but this server inside it is not
    • Commit cadencenot measured
      repository is active but this server inside it is not
  • Momentum64 / 100 · weight 14%
    • Stars gained, relative to size48
    • Stars gained, absolute87
    • 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

  78.4

  × relevance: the keyword is dedicated here

  1.00

  × continuity: actively changing

  1.00

  × evidence: widely adopted

  1.00

  Composite score

  78.4

• 2

  TerraVision

  Community favourite

  patrickchugh/terravision ↗

  Best for: Diagramming AWS infrastructure from Terraform code before deployment: it renders diagrams from the code alone, with no cloud account access required.

  TerraVision exposes seven MCP tools: render_graph draws a diagram from a plain JSON graph, generate_diagram writes one from Terraform code, generate_architecture_graph returns that architecture as structured data by actually running Terraform and resolving variables, and the rest serve a diagram guide, a self-contained interactive HTML page, and file open/read helpers. Agents must read diagram_guide before calling render_graph, and the Terraform-based tools assume Terraform can be executed on the machine where the server runs.

  Score 65.3: show every number behind it

  • Adoption81 / 100 · weight 40%
    • GitHub stars81
    • 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
  • Momentum50 / 100 · weight 14%
    • Stars gained, relative to size47
    • Stars gained, absolute56
    • 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

  83.7

  × relevance: the keyword is declared here

  0.78

  × continuity: actively changing

  1.00

  × evidence: widely adopted

  1.00

  Composite score

  65.3

• 3

  memora

  Community favourite

  agentic-box/memora ↗

  Best for: Agents that need shared memory across sessions: it stores memories in SQLite with semantic and hybrid search plus optional S3 or R2 cloud sync.

  Memora exposes 44 tools for creating, updating, tagging, linking and searching persistent memory entries, plus structured document storage, duplicate detection, and an HTML knowledge graph export. Its LLM-assisted features such as absorb, deduplication and supersession detection depend on a configured language model, and semantic search quality depends on whichever embedding backend is chosen.

  Score 61.4: show every number behind it

  • Adoption72 / 100 · weight 40%
    • GitHub stars72
    • 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
  • Momentum54 / 100 · weight 14%
    • Stars gained, relative to size56
    • Stars gained, absolute50
    • npm download trendnot measured
      no download history for the selected registry
  • 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

  78.7

  × relevance: the keyword is declared here

  0.78

  × continuity: actively changing

  1.00

  × evidence: widely adopted

  1.00

  Composite score

  61.4

• 4

  aws-athena-mcp

  Community favourite

  lishenxydlgzs/aws-athena-mcp ↗

  Best for: Analysts querying AWS Glue catalog data through Athena: it exposes five tools for running SQL, checking status, fetching results, and listing or running saved queries.

  It exposes five tools: run_query and run_saved_query execute Athena SQL, get_status checks execution state, get_result fetches completed results, and list_saved_queries lists saved queries. Choosing it requires AWS credentials with Athena and S3 permissions and an OUTPUT_S3_PATH pointing to an S3 bucket for query results.

  Score 60.9: show every number behind it

  • Adoption63 / 100 · weight 40%
    • GitHub stars41
    • npm downloads57
    • Used through Glamanot measured
      not used through Glama in the last 30 days
  • Maintenance70 / 100 · weight 24%
    • Last commit touching this server88
    • Repository maintenance grade55
    • Commit cadence40
  • Momentum3 / 100 · weight 14%
    • Stars gained, relative to size0
    • Stars gained, absolute0
    • npm download trend13
  • 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

  60.9

  × relevance: the keyword is dedicated here

  1.00

  × continuity: actively changing

  1.00

  × evidence: widely adopted

  1.00

  Composite score

  60.9

• 5

  Servonaut

  Community favourite

  zb-ss/servonaut ↗

  Best for: Mixed fleets of AWS EC2, Hetzner, OVH, and custom SSH hosts: commands run over SSH with automatic failover to AWS SSM, unified in 69 tools.

  Servonaut is a terminal app plus MCP server that exposes 69 tools for listing instances, running commands, getting logs, transferring files over SCP, querying CloudWatch and CloudTrail, banning IPs through WAF/security group configs, and working with S3 buckets across AWS, Hetzner, OVH, and custom SSH servers, with guard tiers and an audit trail. The hosted pieces (relay status and reconnect, calls to mcp.servonaut.dev, memory sync) assume a servonaut.dev login from servonaut login, while the README states it runs fully offline against the user's own credentials without an account.

  Score 58.2: show every number behind it

  • Adoption61 / 100 · weight 40%
    • GitHub stars38
    • PyPI downloads55
    • 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
  • Momentum60 / 100 · weight 14%
    • Stars gained, relative to size59
    • Stars gained, absolute27
    • PyPI download trend100
  • 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

  74.6

  × relevance: the keyword is declared here

  0.78

  × continuity: actively changing

  1.00

  × evidence: widely adopted

  1.00

  Composite score

  58.2

• 6

  IAM Policy Autopilot

  Community favourite

  awslabs/iam-policy-autopilot ↗

  Best for: Using an AI coding assistant to create IAM permissions for an AWS app: it analyzes local AWS SDK calls and generates baseline identity-based policies.

  IAM Policy Autopilot is an MCP server and command-line tool that analyzes local application code for AWS SDK calls in Python, Go, TypeScript, JavaScript, and Java, and can generate baseline AWS IAM identity-based policies, including from a Terraform plan file in JSON format. Before choosing it, note that it produces identity-based policies only and does not cover resource-based policies, RCPs, SCPs, or permission boundaries.

  Score 57.6: show every number behind it

  • Adoption68 / 100 · weight 40%
    • GitHub stars68
    • 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
  • Momentum50 / 100 · weight 14%
    • Stars gained, relative to size54
    • Stars gained, absolute44
    • 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

  73.8

  × relevance: the keyword is declared here

  0.78

  × continuity: actively changing

  1.00

  × evidence: widely adopted

  1.00

  Composite score

  57.6

• 7

  LocalStack MCP Server

  Steady

  localstack/localstack-mcp-server ↗

  Best for: Managing a local LocalStack AWS environment: it starts and stops LocalStack, deploys CDK or Terraform, and runs awslocal commands through exposed tools.

  The LocalStack MCP Server exposes seven tools for LocalStack lifecycle management, awslocal command execution, CDK or Terraform deployment and destruction, log and IAM policy analysis, chaos injection, and Cloud Pods state management. All tools require a LOCALSTACK_AUTH_TOKEN, and the server is currently an experimental public preview.

  Score 53.8: show every number behind it

  • Adoption57 / 100 · weight 40%
    • GitHub stars37
    • npm downloads51
    • Used through Glamanot measured
      not used through Glama in the last 30 days
  • Maintenance86 / 100 · weight 24%
    • Last commit touching this server100
    • Repository maintenance grade55
    • Commit cadence85
  • Momentum46 / 100 · weight 14%
    • Stars gained, relative to size37
    • Stars gained, absolute16
    • npm download trend100
  • Tool quality78 / 100 · weight 13%
    • Tool description quality70
    • Built and inspected by Glama100
  • Trust100 / 100 · weight 9%
    • License100
    • Published by the vendor it integrates100

  Weighted mean of the five

  69.0

  × relevance: the keyword is declared here

  0.78

  × continuity: actively changing

  1.00

  × evidence: widely adopted

  1.00

  Composite score

  53.8

• 8

  cloud-finops-mcp

  Steady

  OptimNow/cloud-finops-skills ↗

  Best for: Answering cloud cost questions from written FinOps guidance and waste runbooks: seven retrieval tools for references, playbooks and dated figures, with no cloud account access.

  cloud-finops-mcp exposes seven tools that list, search and fetch FinOps references and waste-pattern playbooks, plus a tool for current values of figures quoted in those references. It cannot see a user's cloud account, so resource-specific answers come as detection queries the user runs rather than live findings.

  Score 46.9: show every number behind it

  • Adoption46 / 100 · weight 40%
    • GitHub stars46
    • 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
  • Momentum46 / 100 · weight 14%
    • Stars gained, relative to size58
    • Stars gained, absolute29
    • npm download trendnot measured
      no download history for the selected registry
  • Tool quality100 / 100 · weight 13%
    • Tool description quality93
    • 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

  70.7

  × relevance: the keyword is declared here

  0.78

  × continuity: actively changing

  1.00

  × evidence: modest but real audience

  0.85

  Composite score

  46.9

• 9

  Backblaze B2 MCP Server

  Steady

  backblaze-labs/b2-mcp ↗

  Best for: Teams storing data in Backblaze B2 who want an AI client to manage buckets, keys, Object Lock, and S3-compatible object transfers through 40 tools.

  It exposes 40 tools: native Backblaze B2 control-plane calls for buckets, application keys, Object Lock, event notifications and Partner/Groups operations, 19 S3-compatible data-plane calls for upload, download, copy, multipart and presigned URLs, and four analytics tools over B2 usage reports and bounded live listings. Before choosing it, note that it requires a B2 application key (with a master key added for the Partner/Groups tools) and that it operates Backblaze B2 buckets through B2 and S3-compatible endpoints rather than managing AWS S3 storage.

  Score 46.5: show every number behind it

  • Adoption45 / 100 · weight 40%
    • GitHub stars42
    • npm downloads23
      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
  • Momentum60 / 100 · weight 14%
    • Stars gained, relative to size59
    • Stars gained, absolute29
    • npm download trend100
  • 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

  70.1

  × relevance: the keyword is declared here

  0.78

  × continuity: actively changing

  1.00

  × evidence: modest but real audience

  0.85

  Composite score

  46.5

• 10

  Dynoxide

  Steady

  nubo-db/dynoxide ↗

  Best for: DynamoDB-compatible local testing for coding agents: its MCP server exposes DynamoDB operations while the same engine runs as an HTTP server or embedded Rust library.

  Dynoxide is a DynamoDB-compatible emulator, backed by SQLite, that runs as an HTTP server or an MCP server and can also embed as a Rust library or compile to WebAssembly. It emulates DynamoDB rather than connecting to an existing AWS table, so the MCP server fits local or embedded workflows.

  Score 46.1: show every number behind it

  • Adoption50 / 100 · weight 40%
    • GitHub stars50
    • 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
  • Momentum55 / 100 · weight 14%
    • Stars gained, relative to size67
    • Stars gained, absolute36
    • 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

  69.5

  × relevance: the keyword is declared here

  0.78

  × continuity: actively changing

  1.00

  × evidence: modest but real audience

  0.85

  Composite score

  46.1

• 11

  AWS Athena MCP Server

  Steady

  ColeMurray/aws-athena-mcp ↗

  Best for: Exploratory SQL against AWS Athena from an MCP client: it documents query execution, schema discovery, and result retrieval.

  The README documents an MCP server that runs SQL queries against AWS Athena, discovers schemas, lists tables, and retrieves query results and status. Before use, it requires an S3 output location set through ATHENA_S3_OUTPUT_LOCATION and AWS credentials available to the process.

  Score 43.9: show every number behind it

  • Adoption43 / 100 · weight 40%
    • GitHub stars35
    • PyPI downloads38
    • Used through Glamanot measured
      not used through Glama in the last 30 days
  • Maintenance69 / 100 · weight 24%
    • Last commit touching this server88
      dated from the last commit on the default branch, re-read from GitHub at publication; github.com shows a push 3 days ago, which counts every ref; the stored date would have published 3 days ago
    • Repository maintenance grade30
    • Commit cadence65
  • Momentum0 / 100 · weight 14%
    • Stars gained, relative to size0
    • Stars gained, absolute0
    • PyPI 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

  51.6

  × relevance: the keyword is dedicated here

  1.00

  × continuity: actively changing

  1.00

  × evidence: modest but real audience

  0.85

  Composite score

  43.9

• 12

  mcp-v8

  Steady

  r33drichards/mcp-js ↗

  Best for: Multi-step agent scripting: it exposes a run_js tool that executes JavaScript and TypeScript in a sandboxed V8 isolate with persistent heap snapshots.

  mcp-v8 exposes a run_js tool that runs JavaScript or TypeScript inside a V8 isolate, and the README documents stdio, Streamable HTTP and SSE transports plus a REST sidecar at /api/exec for posting a script directly. Host capabilities including network fetch, filesystem access, subprocesses, WebAssembly and module imports are denied by default and are unlocked only through OPA/Rego policy files, so nothing outside the isolate is reachable until those policies are written.

  Score 43.2: show every number behind it

  • Adoption45 / 100 · weight 40%
    • GitHub stars45
    • 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
  • Momentum47 / 100 · weight 14%
    • Stars gained, relative to size58
    • Stars gained, absolute29
    • 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

  65.2

  × relevance: the keyword is declared here

  0.78

  × continuity: actively changing

  1.00

  × evidence: modest but real audience

  0.85

  Composite score

  43.2

• 13

  cloud-audit

  Steady

  gebalamariusz/cloud-audit ↗

  Best for: Auditing an AWS account read-only through an MCP client: it exposes seven tools for scans, findings, attack chains, remediation, health, checks, and agent blast radius.

  cloud-audit exposes seven MCP tools for a read-only AWS security scan, findings and attack-chain retrieval, CLI and Terraform remediation, health scoring, check listing, and agent blast-radius analysis. Real scans depend on AWS credentials, while list_checks and the demo path work without an AWS account.

  Score 43.0: show every number behind it

  • Adoption50 / 100 · weight 40%
    • GitHub stars47
    • PyPI downloads23
      PyPI downloads show no weekday rhythm; halved
    • Used through Glamanot measured
      not used through Glama in the last 30 days
  • Maintenance86 / 100 · weight 24%
    • Last commit touching this server88
      dated from the last commit on the default branch, re-read from GitHub at publication; github.com shows a push 22 days ago, which counts every ref; the stored date would have published 22 days ago
    • Repository maintenance grade100
    • Commit cadence65
  • Momentum28 / 100 · weight 14%
    • Stars gained, relative to size33
    • Stars gained, absolute16
    • PyPI download trend34
  • 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

• 14

  Log Analyzer with MCP

  Abandoned but popular

  awslabs/Log-Analyzer-with-MCP ↗

  Best for: When an AI assistant needs to browse, search, summarize, and correlate CloudWatch Logs: the README documents those workflows.

  The server provides an MCP interface for AI assistants to browse and search CloudWatch Log Groups, search logs with CloudWatch Logs Insights syntax, generate summaries, and correlate logs across AWS services. Before installing, it assumes uv/uvx is available along with an AWS account containing CloudWatch Logs and configured AWS credentials.

  Score 41.2: 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
  • Maintenance40 / 100 · weight 24%
    • Last commit touching this server68
      dated from the last commit on the default branch, re-read from GitHub at publication; github.com shows a push 92 days ago, which counts every ref; the stored date would have published 92 days ago
    • Repository maintenance grade5
    • Commit cadence5
  • Momentum23 / 100 · weight 14%
    • Stars gained, relative to size27
    • Stars gained, absolute16
    • 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

  52.8

  × relevance: the keyword is declared here

  0.78

  × continuity: actively changing

  1.00

  × evidence: widely adopted

  1.00

  Composite score

  41.2

• 15

  MCP OAuth2.1 with AWS Cognito Example

  Dormant

  empires-security/mcp-oauth2-aws-cognito ↗

  Best for: Building an MCP server authenticated through AWS Cognito: it implements OAuth 2.1 resource-server flows with dynamic client registration and client ID metadata documents.

  It is a Node.js and Express example MCP server that acts as an OAuth 2.1 resource server, serving protected resource metadata at /.well-known/oauth-protected-resource, discovering authorization server metadata dynamically, and shipping static, DCR and CIMD client samples. Nothing is published to npm or PyPI, so it runs from source, and its dynamic client registration path depends on API Gateway and Lambda endpoints because Cognito does not support that flow natively.

  Score 40.1: show every number behind it

  • Adoption46 / 100 · weight 40%
    • GitHub stars46
    • npm downloadsnot measured
      no npm package
    • 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
  • 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 integratesnot measured
      not published by the vendor it integrates

  Weighted mean of the five

  47.2

  × relevance: the keyword is dedicated here

  1.00

  × continuity: actively changing

  1.00

  × evidence: modest but real audience

  0.85

  Composite score

  40.1

• 16

  AWS SRA Verify MCP Server

  Steady

  awslabs/sra-verify-mcp ↗

  Best for: Assessing an AWS Organization against the Security Reference Architecture: it exposes discovery and run tools for SRA checks across management, audit, log-archive, and application accounts.

  The AWS SRA Verify MCP Server exposes tools to list supported services and checks, describe a check, and run a security check against AWS accounts. It assumes an AWS Organization with the SRA account structure and, for cross-account scans, an IAM role deployed to each assessed account.

  Score 39.8: show every number behind it

  • Adoption34 / 100 · weight 40%
    • GitHub stars15
    • PyPI downloads31
    • Used through Glamanot measured
      not used through Glama in the last 30 days
  • Maintenance97 / 100 · weight 24%
    • Last commit touching this server100
    • Repository maintenance grade100
    • Commit cadence85
  • 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 integrates100

  Weighted mean of the five

  56.9

  × relevance: the keyword is dedicated here

  1.00

  × continuity: actively changing

  1.00

  × evidence: small audience

  0.70

  Composite score

  39.8

• 17

  RAGStack-Lambda

  Steady

  HatmanStack/RAGStack-Lambda ↗

  Best for: Teams deploying an AWS knowledge base for documents and media: the README documents an MCP server for AI assistant integration, OCR, and transcription.

  RAGStack-Lambda deploys a serverless AWS pipeline that processes documents, images, video, and audio, extracts text with OCR or AWS Transcribe, and answers queries through Amazon Bedrock; its README documents a GraphQL API, a web component, and an MCP server. The documented setup requires an AWS account with admin access and a CloudFormation or source-based deployment, and it has no published npm package and no attributed PyPI package.

  Score 38.3: show every number behind it

  • Adoption35 / 100 · weight 40%
    • GitHub stars35
    • 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≈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

  54.7

  × relevance: the keyword is dedicated here

  1.00

  × continuity: actively changing

  1.00

  × evidence: small audience

  0.70

  Composite score

  38.3

• 18

  Sample S3 MCP Server

  Dormant

  aws-samples/sample-mcp-server-s3 ↗

  Best for: Loading PDF documents from S3 into an LLM's context: it exposes PDFs as resources and documents S3 listing and retrieval tools.

  The server documents ListBuckets, ListObjectsV2, and GetObject tools for S3 and exposes PDF documents as resources for loading into an LLM's context. It assumes AWS credentials with appropriate S3 permissions, and its resource support is limited to PDF documents.

  Score 37.7: show every number behind it

  • Adoption48 / 100 · weight 40%
    • GitHub stars48
    • npm downloadsnot measured
      no npm package
    • 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
  • 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 integratesnot measured
      not published by the vendor it integrates

  Weighted mean of the five

  44.4

  × relevance: the keyword is dedicated here

  1.00

  × continuity: actively changing

  1.00

  × evidence: modest but real audience

  0.85

  Composite score

  37.7

• 19

  aws-calculator-mcp

  Dormant

  Musheer360/aws-calculator-mcp ↗

  Best for: Estimating AWS costs without AWS credentials: it builds estimates in calculator.aws and returns a shareable link plus scraped costs.

  The README documents tools that search the AWS service catalog, fetch a service's configuration fields, create and update an estimate, export it to a calculator.aws link, and refresh it through headless Chrome to read the actual calculated costs. Node.js 18 or newer is required, and headless Chrome is a separate install needed for cost retrieval and report generation.

  Score 37.0: show every number behind it

  • Adoption40 / 100 · weight 40%
    • GitHub stars24
    • npm downloads36
    • 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
  • Momentum47 / 100 · weight 14%
    • Stars gained, relative to size39
    • Stars gained, absolute16
    • 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

  52.9

  × relevance: the keyword is dedicated here

  1.00

  × continuity: actively changing

  1.00

  × evidence: small audience

  0.70

  Composite score

  37.0

• 20

  MCP2Lambda

  Steady

  danilop/MCP2Lambda ↗

  Best for: Calling existing AWS Lambda functions from an MCP client without code changes: it exposes list and invoke tools for discovery and invocation.

  MCP2Lambda bridges an MCP client to AWS Lambda, exposing a tool to list available functions and a tool to invoke one with a JSON payload. It requires Python 3.12 or higher and configured AWS credentials, and by default only functions whose names start with mcp2lambda- are available.

  Score 36.9: show every number behind it

  • Adoption51 / 100 · weight 40%
    • GitHub stars51
    • npm downloadsnot measured
      no npm package
    • 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
  • 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

  55.7

  × relevance: the keyword is declared here

  0.78

  × continuity: actively changing

  1.00

  × evidence: modest but real audience

  0.85

  Composite score

  36.9

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 MongoDB 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 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