20 Best GitHub MCP Servers, Compared (November 2026)

The short answer

Which one, for your situation

Top MCP servers for GitHub

The ranking, with the evidence

• 1

  GitHub MCP Server

  Community favourite

  github/github-mcp-server ↗

  Best for: Connecting an assistant to GitHub for repository, issue, and pull request work: the README documents a hosted remote MCP endpoint with OAuth or PAT authentication.

  The README documents a remote HTTP MCP endpoint hosted by GitHub at https://api.githubcopilot.com/mcp/ and a local version, with GitHub access for reading repositories and code, managing issues and pull requests, analyzing code, and automating workflows. Before choosing it, remote use requires a compatible MCP host with remote server support and any applicable policies enabled; each host application must configure a GitHub App or OAuth App to support remote access via OAuth.

  Score 91.8: show every number behind it

  • Adoption100 / 100 · weight 40%
    • GitHub stars100
    • npm downloadsnot measured
      no npm package
    • Used through Glamanot measured
      not used through Glama in the last 30 days
  • Maintenance95 / 100 · weight 24%
    • Last commit touching this server100
    • Repository maintenance grade80
    • Commit cadence100
  • Momentum80 / 100 · weight 14%
    • Stars gained, relative to size67
    • Stars gained, absolute100
    • npm download trendnot measured
      no download history for the selected registry
  • Tool quality≈68 / 100 · weight 13%
    • Tool description quality≈68
      tool descriptions not yet scored
    • Built and inspected by Glamanot measured
      never built and inspected by Glama
  • Trust100 / 100 · weight 9%
    • License100
    • Published by the vendor it integrates100

  Weighted mean of the five

  91.8

  × relevance: the keyword is dedicated here

  1.00

  × continuity: actively changing

  1.00

  × evidence: widely adopted

  1.00

  Composite score

  91.8

• 2

  github-codemunch-mcp

  Community favourite

  jgravelle/jcodemunch-mcp ↗

  Best for: Exploring a GitHub repository without reading whole files: it indexes the repo and retrieves specific functions, classes, or methods by symbol using tree-sitter AST parsing.

  The server provides seven tools to index a GitHub repository with tree-sitter parsing into local storage, list indexed repositories, inspect file trees and outlines, search symbols, and fetch source for one or more symbols. Its tree, outline, search, and retrieval tools rely on a local index created by index_repo, so a repository must be indexed first.

  Score 84.4: show every number behind it

  • Adoption100 / 100 · weight 40%
    • GitHub stars86
    • PyPI downloads87
    • 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 size67
    • Stars gained, absolute77
    • PyPI download trend88
  • Tool quality76 / 100 · weight 13%
    • Tool description quality68
    • Built and inspected by Glama100
  • Trust0 / 100 · weight 9%
    • License0
    • Published by the vendor it integratesnot measured
      not published by the vendor it integrates

  Weighted mean of the five

  84.4

  × relevance: the keyword is dedicated here

  1.00

  × continuity: actively changing

  1.00

  × evidence: widely adopted

  1.00

  Composite score

  84.4

• 3

  Octocode MCP

  Community favourite▲ 1

  bgauryy/octocode ↗

  Best for: Researching why code exists across local and GitHub repositories: it provides pull-request search plus local ripgrep, filesystem, and LSP navigation tools.

  Octocode MCP exposes thirteen tools for local and GitHub code research, including ripgrep search, repository and pull-request search, file and directory reads, LSP navigation, and npm/PyPI package lookup, and its README documents a CLI exposing the same tools. It assumes Node.js 20.12+ and an npx launch; GitHub authentication is optional but unlocks private repositories and higher API rate limits.

  Score 62.7: show every number behind it

  • Adoption85 / 100 · weight 40%
    • GitHub stars75
    • npm downloads70
    • Used through Glamanot measured
      not used through Glama in the last 30 days
  • Maintenance70 / 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 2 days ago, which counts every ref; the stored date would have published 2 days ago
    • Repository maintenance grade55
    • Commit cadence40
  • Momentum54 / 100 · weight 14%
    • Stars gained, relative to size37
    • Stars gained, absolute41
    • npm download trend100
  • 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

  80.4

  × relevance: the keyword is declared here

  0.78

  × continuity: actively changing

  1.00

  × evidence: widely adopted

  1.00

  Composite score

  62.7

• 4

  new-term-radar

  Community favourite▲ 1

  zhuyansen/new-term-radar ↗

  Best for: Watching X, Hugging Face, GitHub and sitemaps for newly emerging AI names before keyword tools list them: it produces a daily report.

  new-term-radar is a Python MCP server, CLI and set of Agent Skills that scans X, Hugging Face, GitHub, sitemaps and new sites for emerging AI model, product and repository names, then builds a keyword table with search volume, Google Trends and page-one competition. It requires an AIsa key for the X and new-site signals and a configured list of sitemaps, while the keyed signals can incur per-run or per-query costs.

  Score 60.2: show every number behind it

  • Adoption91 / 100 · weight 40%
    • GitHub stars83
    • PyPI downloads54
    • 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
  • Momentum≈0 / 100 · weight 14%
    • Stars gained, relative to sizenot measured
      no snapshot history yet
    • Stars gained, absolutenot measured
      no snapshot history yet
    • 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

  77.2

  × relevance: the keyword is declared here

  0.78

  × continuity: actively changing

  1.00

  × evidence: widely adopted

  1.00

  Composite score

  60.2

• 5

  mcp-github-project-manager

  Steady▼ 2

  kunwarVivek/mcp-github-project-manager ↗

  Best for: Teams running multiple AI coding agents on GitHub Projects V2: it provides agent checkout, heartbeats, review, and token budgets through compound tools.

  It exposes 21 compound tools that route through an action field to manage GitHub Projects V2, issues, pull requests, milestones, sprints, labels, releases, branches, workflows, and agent work, with AI generation, analysis, and planning actions. Before installing, note that it requires Node.js >= 22.12.0 and a GitHub credential with repo, project, and write:org scopes when using a PAT (or a GitHub CLI or OAuth login).

  Score 58.4: show every number behind it

  • Adoption53 / 100 · weight 40%
    • GitHub stars51
    • npm downloads18
      downloads show none of the weekday rhythm human traffic has; halved
    • 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
  • Momentum58 / 100 · weight 14%
    • Stars gained, relative to size53
    • Stars gained, absolute29
    • npm download trend100
  • Tool quality58 / 100 · weight 13%
    • Tool description quality50
    • 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

  68.7

  × relevance: the keyword is dedicated here

  1.00

  × continuity: actively changing

  1.00

  × evidence: modest but real audience

  0.85

  Composite score

  58.4

• 6

  idea-reality-mcp

  Community favourite

  mnemox-ai/idea-reality-mcp ↗

  Best for: Before starting a new project: it exposes one idea_check tool that scans GitHub, Hacker News, npm, PyPI and Stack Overflow for existing competitors.

  It exposes a single tool, idea_check, which takes an idea in plain English and returns a 0-100 reality score with competitor and trend data drawn from GitHub, Hacker News, npm, PyPI and Stack Overflow. It is a pre-build check of a product idea, so it does not review code or an existing repository, and setup assumes a local uvx runtime or the hosted REST endpoint.

  Score 58.4: show every number behind it

  • Adoption76 / 100 · weight 40%
    • GitHub stars73
    • PyPI downloads20
      PyPI downloads show no weekday rhythm; halved
    • 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
  • Momentum47 / 100 · weight 14%
    • Stars gained, relative to size40
    • Stars gained, absolute41
    • PyPI download trend67
  • Tool quality93 / 100 · weight 13%
    • Tool description quality85
    • 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

  74.9

  × relevance: the keyword is declared here

  0.78

  × continuity: actively changing

  1.00

  × evidence: widely adopted

  1.00

  Composite score

  58.4

• 7

  Article Writer MCP

  Community favouriteNew

  Cappybara12/mcp-use ↗

  Best for: Trying a content pipeline without live services: it runs topic research, drafting, style checks and GitHub PR staging in demo mode on bundled sample data.

  Article Writer MCP is a Python ArticlePipelineService fronted by a Graftcode Gateway, whose /mcp HTTP endpoint gives MCP clients the same methods a React dashboard reaches over WebSocket: pending topics, topic sources, drafts, style checks, next-article suggestions, article writing and GitHub PR staging. Nothing is published to npm or PyPI, so it has to be run from the repository, and the GitHub staging method raises an error in the default demo mode, which otherwise serves bundled sample data.

  Score 58.3: show every number behind it

  • Adoption75 / 100 · weight 40%
    • GitHub stars75
    • 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
  • Momentum100 / 100 · weight 14%
    • Stars gained, relative to size100
    • Stars gained, absolute100
    • npm download trendnot measured
      no download history for the selected registry
  • Tool quality≈68 / 100 · weight 13%
    • Tool description quality≈68
      tool descriptions not yet scored
    • Built and inspected by Glamanot measured
      never built and inspected by Glama
  • Trust0 / 100 · weight 9%
    • License0
    • Published by the vendor it integratesnot measured
      not published by the vendor it integrates

  Weighted mean of the five

  74.7

  × relevance: the keyword is declared here

  0.78

  × continuity: actively changing

  1.00

  × evidence: widely adopted

  1.00

  Composite score

  58.3

• 8

  GitMCP

  Abandoned but popular▲ 1

  idosal/git-mcp ↗

  Best for: AI-assisted Git, GitHub, or Gitea repository work: it exposes commit, push, pull, branch, merge, repository creation, release, and backup tools.

  GitMCP is documented as a remote MCP server that turns GitHub repositories or GitHub Pages sites into gitmcp.io documentation endpoints, and its published tool list includes 32 tools for Git operations, GitHub and Gitea repository management, authentication, configuration, releases, backups, and health checks. Before choosing it, note that the README's connection examples require client-specific MCP configuration, with Claude Desktop depending on npx mcp-remote.

  Score 56.7: show every number behind it

  • Adoption98 / 100 · weight 40%
    • GitHub stars98
    • npm downloadsnot measured
      npm names no repository for git-mcp, so its downloads cannot be attributed
    • 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
  • Momentum47 / 100 · weight 14%
    • Stars gained, relative to size32
    • Stars gained, absolute69
    • npm download trendnot measured
      no download history for the selected registry
  • Tool quality53 / 100 · weight 13%
    • Tool description quality45
    • Built and inspected by Glama100
  • Trust100 / 100 · weight 9%
    • License100
    • Published by the vendor it integratesnot measured
      not published by the vendor it integrates

  Weighted mean of the five

  72.7

  × relevance: the keyword is declared here

  0.78

  × continuity: actively changing

  1.00

  × evidence: widely adopted

  1.00

  Composite score

  56.7

• 9

  mcp-skylos

  Community favourite▲ 2

  duriantaco/skylos ↗

  Best for: Merging AI-generated Python changes: it exposes dead-code, security, quality, secrets, architecture, and change-review tools that return file, line, and severity findings for agents to fix.

  mcp-skylos exposes 17 MCP tools that run static analysis for dead code, security and secrets, quality, architecture, health scoring, remediation planning, change validation, and agent provenance. Python has the deepest coverage; Go dead-code and security checks require the native skylos-go engine.

  Score 56.3: show every number behind it

  • Adoption100 / 100 · weight 40%
    • GitHub stars74
    • PyPI downloads90
    • 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
  • Momentum77 / 100 · weight 14%
    • Stars gained, relative to size97
    • Stars gained, absolute71
    • PyPI download trend48
  • Tool quality78 / 100 · weight 13%
    • Tool description quality70
    • 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

  93.8

  × relevance: the keyword is tagged here

  0.60

  × continuity: actively changing

  1.00

  × evidence: widely adopted

  1.00

  Composite score

  56.3

• 10

  jscpd

  Community favourite▼ 2

  kucherenko/jscpd ↗

  Best for: Catching copy-paste duplication before a commit: it exposes a check_duplication tool that tests a snippet or file against the already scanned project.

  The jscpd MCP server runs over stdio via jscpd --mcp and exposes five tools: check_duplication and check_current_directory test a snippet or rescan the project, get_file_clones and get_statistics read the results of the last scan, and compare_folders compares two folders function by function, including across languages. Every clone answer is relative to the paths the server was started with and the most recent scan, so the project has to be scanned first and rescanned with check_current_directory after files are created, edited or deleted.

  Score 56.0: show every number behind it

  • Adoption95 / 100 · weight 40%
    • GitHub stars95
    • 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
  • Momentum72 / 100 · weight 14%
    • Stars gained, relative to size61
    • Stars gained, absolute88
    • npm download trendnot measured
      no download history for the selected registry
  • Tool quality93 / 100 · weight 13%
    • Tool description quality85
    • Built and inspected by Glama100
  • Trust100 / 100 · weight 9%
    • License100
    • Published by the vendor it integrates100

  Weighted mean of the five

  93.3

  × relevance: the keyword is tagged here

  0.60

  × continuity: actively changing

  1.00

  × evidence: widely adopted

  1.00

  Composite score

  56.0

• 11

  Kindly Web Search MCP Server

  Community favourite▼ 4

  Shelpuk-AI-Technology-Consulting/kindly-web-search-mcp-server ↗

  Best for: Debugging an unfamiliar library or API error: its web_search and get_content tools return StackOverflow answers, GitHub Issue comments, and arXiv content in one call.

  Kindly Web Search MCP Server documents a web_search tool that returns each result with a title, link, snippet and Markdown page_content, plus a get_content tool that renders a URL into Markdown. It requires a third-party search provider (Serper, SerpBase, Tavily, SearXNG, Sofya, You.com or Serply), ships no npm package and no attribution on PyPI, and its README positions it as one of three MCP servers plus a skill installed together.

  Score 55.5: show every number behind it

  • Adoption65 / 100 · weight 40%
    • GitHub stars65
    • 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
  • Momentum33 / 100 · weight 14%
    • Stars gained, relative to size35
    • 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

  71.2

  × relevance: the keyword is declared here

  0.78

  × continuity: actively changing

  1.00

  × evidence: widely adopted

  1.00

  Composite score

  55.5

• 12

  GitHub Stars MCP Server

  Steady▼ 2

  miantiao-me/github-stars ↗

  Best for: Semantic search over your own GitHub stars: it indexes starred repositories and README content through Cloudflare AutoRAG and exposes a search_github_stars tool.

  The README documents a single search_github_stars tool that takes a natural language query and returns matching starred repositories with relevant README content, reached over Streamable HTTP on a Cloudflare Worker. Choosing it means running your own Cloudflare deployment, since it depends on an R2 bucket, an AutoRAG instance and a bearer MCP_API_KEY, with starred repository data refreshed by a weekly GitHub Action.

  Score 54.3: show every number behind it

  • Adoption52 / 100 · weight 40%
    • GitHub stars52
    • npm downloadsnot measured
      npm names no repository for mcp-github-stars, so its downloads cannot be attributed
    • 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
  • Momentum24 / 100 · weight 14%
    • Stars gained, relative to size29
    • Stars gained, absolute15
    • 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

  63.9

  × relevance: the keyword is dedicated here

  1.00

  × continuity: actively changing

  1.00

  × evidence: modest but real audience

  0.85

  Composite score

  54.3

• 13

  Skill Seekers

  Community favourite▼ 1

  yusufkaraaslan/Skill_Seekers ↗

  Best for: Preparing a documentation site or GitHub repo as an AI skill for Claude Code: it exposes scraping, config, packaging, and upload tools for that workflow.

  Skill Seekers exposes 40 MCP tools for generating and validating scrape configs, scraping documentation, GitHub repositories, PDFs, videos, and local codebases into skills, packaging and uploading those skills, and exporting them to vector databases. Before choosing it, note that the MCP server is an optional extra installed with pip install skill-seekers[mcp] and that the project requires Python 3.10+.

  Score 52.9: show every number behind it

  • Adoption100 / 100 · weight 40%
    • GitHub stars100
    • PyPI downloads30
      PyPI downloads show no weekday rhythm; halved
    • 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
  • Momentum60 / 100 · weight 14%
    • Stars gained, relative to size44
    • Stars gained, absolute91
    • PyPI download trend53
  • 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

  88.2

  × relevance: the keyword is tagged here

  0.60

  × continuity: actively changing

  1.00

  × evidence: widely adopted

  1.00

  Composite score

  52.9

• 14

  pipelock

  Community favourite

  pipelab-org/pipelock ↗

  Best for: Deployments that must route MCP servers and agent egress through a proxy: it scans mediated traffic for credential leaks, prompt injection, and tool description poisoning.

  Pipelock is a security proxy that mediates HTTP, WebSocket, MCP, and A2A traffic and scans it for secret exfiltration, prompt injection, SSRF, tool poisoning, and risky tool-call chains. It requires traffic to be routed through the proxy or MCP wrapper, and plain CONNECT without TLS interception is scanned only at the hostname and URL level.

  Score 50.6: show every number behind it

  • Adoption75 / 100 · weight 40%
    • GitHub stars75
    • 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
  • Momentum90 / 100 · weight 14%
    • Stars gained, relative to size100
    • Stars gained, absolute76
    • 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

  84.3

  × relevance: the keyword is tagged here

  0.60

  × continuity: actively changing

  1.00

  × evidence: widely adopted

  1.00

  Composite score

  50.6

• 15

  MisakaNet

  Community favourite▼ 2

  Ikalus1988/MisakaNet ↗

  Best for: Debugging a recurring install or build error: it searches a public failure-lesson index by error text and fetches the matching lesson instead of debugging from scratch.

  MisakaNet exposes 11 tools that search and retrieve evidence-graded failure lessons from a public index, submit new intakes or lessons, record when a lesson was reused, and check risk before high-risk operations. Reading needs no account, but the write tools such as writing a lesson or recording a lesson's use require registering an agent for a node_id and token.

  Score 50.1: show every number behind it

  • Adoption73 / 100 · weight 40%
    • GitHub stars69
    • npm downloads29
      downloads show none of the weekday rhythm human traffic has; halved
    • 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
  • Momentum74 / 100 · weight 14%
    • Stars gained, relative to size97
    • Stars gained, absolute64
    • npm download trend45
  • Tool quality93 / 100 · weight 13%
    • Tool description quality85
    • 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

  83.5

  × relevance: the keyword is tagged here

  0.60

  × continuity: actively changing

  1.00

  × evidence: widely adopted

  1.00

  Composite score

  50.1

• 16

  OpenCollab MCP

  Emerging

  prakhar1605/Opencollab-mcp ↗

  Best for: Matching a GitHub profile to beginner-friendly issues: it analyzes the user's skills and returns 'good first issue' candidates with availability checks.

  Its 22 tools read the GitHub API for profile analysis, first-issue discovery, repository health and contribution-readiness scoring, issue availability checks, and PR-plan context. It assumes a GitHub personal access token (classic, public_repo scope) supplied as GITHUB_TOKEN through uvx, pip, or Docker, and it returns data only: the README states the AI client does the drafting.

  Score 47.5: show every number behind it

  • Adoption45 / 100 · weight 40%
    • GitHub stars41
    • PyPI downloads24
    • 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
  • Momentum82 / 100 · weight 14%
    • Stars gained, relative to size100
    • Stars gained, absolute54
    • PyPI 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 integratesnot measured
      not published by the vendor it integrates

  Weighted mean of the five

  71.6

  × relevance: the keyword is declared here

  0.78

  × continuity: actively changing

  1.00

  × evidence: modest but real audience

  0.85

  Composite score

  47.5

• 17

  Node9-Proxy

  Community favouriteNew

  node9-ai/node9-proxy ↗

  Best for: Teams running multiple coding agents: it provides a policy gate that checks every tool call and holds destructive git, SQL, and shell actions for review.

  Node9-Proxy runs as a stdio MCP server that lets an agent read status, posture, audit record, and policy and explain any decision, while its gate checks tool calls before execution. Before choosing it, note that it requires Node.js 22+ and its documented MCP launch command is npx -y node9-ai mcp-server over stdio; local protection needs no account.

  Score 45.9: show every number behind it

  • Adoption64 / 100 · weight 40%
    • GitHub stars59
    • npm downloads35
      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
  • Momentum65 / 100 · weight 14%
    • Stars gained, relative to size62
    • Stars gained, absolute40
    • 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

  76.5

  × relevance: the keyword is tagged here

  0.60

  × continuity: actively changing

  1.00

  × evidence: widely adopted

  1.00

  Composite score

  45.9

• 18

  Sugar

  Steady▲ 2

  roboticforce/sugar ↗

  Best for: Agents that lose project context between sessions: it exposes store_learning and search_memories over MCP, backed by local SQLite per project and globally.

  Sugar runs two MCP servers, sugar mcp memory and an optional sugar mcp tasks, whose documented tools include store_learning and search_memories for writing and retrieving per-project and global memories held in local SQLite databases. Choosing it means installing the sugarai PyPI package and running sugar init per project, since memory lives in .sugar/memory.db on the machine rather than in a hosted store.

  Score 44.6: show every number behind it

  • Adoption53 / 100 · weight 40%
    • GitHub stars50
    • PyPI downloads21
      PyPI downloads show no weekday rhythm; halved
    • 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
  • Momentum39 / 100 · weight 14%
    • Stars gained, relative to size40
    • Stars gained, absolute21
    • PyPI download trend58
  • 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

  67.3

  × relevance: the keyword is declared here

  0.78

  × continuity: actively changing

  1.00

  × evidence: modest but real audience

  0.85

  Composite score

  44.6

• 19

  mcp-omnisearch

  Community favourite▼ 1

  spences10/mcp-omnisearch ↗

  Best for: GitHub tasks that also need Tavily, Brave, Kagi, Exa, Linkup, or Firecrawl: its search and execute tools call configured native provider functions.

  It exposes two tools, search and execute; search discovers configured provider functions, and execute runs JavaScript against them in a QuickJS sandbox. It requires Node.js 22.19+ and API keys for the providers in use, and providers without keys are skipped.

  Score 43.7: show every number behind it

  • Adoption64 / 100 · weight 40%
    • GitHub stars64
    • npm downloadsnot measured
      npm names no repository for mcp-omnisearch, 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
  • Momentum27 / 100 · weight 14%
    • Stars gained, relative to size30
    • Stars gained, absolute23
    • 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 integratesnot measured
      not published by the vendor it integrates

  Weighted mean of the five

  72.8

  × relevance: the keyword is tagged here

  0.60

  × continuity: actively changing

  1.00

  × evidence: widely adopted

  1.00

  Composite score

  43.7

• 20

  mcp-github-trending

  Dormant▼ 1

  hetaoBackend/mcp-github-trending ↗

  Best for: Monitoring GitHub trending repositories and developers by language and time period: it exposes two tools for those filters.

  It exposes two tools for GitHub trending repositories and developers, with optional programming-language and daily/weekly/monthly filters plus spoken-language filtering for repositories. Before choosing it, note that the README lists Python 3.12 as a prerequisite and documents a PyPI installation, while the publication measurements attribute no PyPI package.

  Score 43.3: 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
  • Maintenance46 / 100 · weight 24%
    • Last commit touching this server68
    • Repository maintenance grade30
    • Commit cadence5
  • Momentum34 / 100 · weight 14%
    • Stars gained, relative to size43
    • Stars gained, absolute21
    • npm download trendnot measured
      no download history for the selected registry
  • Tool quality63 / 100 · weight 13%
    • Tool description quality55
    • Built and inspected by Glama100
  • Trust100 / 100 · weight 9%
    • License100
    • Published by the vendor it integratesnot measured
      not published by the vendor it integrates

  Weighted mean of the five

  50.9

  × relevance: the keyword is dedicated here

  1.00

  × continuity: actively changing

  1.00

  × evidence: modest but real audience

  0.85

  Composite score

  43.3

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 Slack 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 CMS 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