20 Best Security MCP Servers, Compared (November 2026)

The short answer

Which one, for your situation

Top MCP servers for Security

The ranking, with the evidence

• 1

  openosint

  Community favourite

  OpenOSINT/OpenOSINT ↗

  Best for: Analysts using an AI agent for passive OSINT on domains, IPs, emails, or usernames: it exposes 20 tools for breach, DNS/RDAP, reputation, dork, graph lookups.

  OpenOSINT exposes 20 MCP tools for breach, WHOIS/RDAP, DNS, IP reputation, Shodan, VirusTotal, Censys, GitHub, Pastebin, Google dork, search-footprint, FollowTheMoney graph, and multi-target investigation workflows, and it also documents a CLI and Claude Code skills. The MCP quickstart uses uvx and assumes uv, and several tools require third-party API keys such as HIBP, Shodan, and VirusTotal.

  Score 91.1: show every number behind it

  • Adoption91 / 100 · weight 40%
    • GitHub stars82
    • PyPI downloads61
    • 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
  • Momentum94 / 100 · weight 14%
    • Stars gained, relative to size100
    • Stars gained, absolute86
    • PyPI download trend91
  • 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

  91.1

  × relevance: the keyword is dedicated here

  1.00

  × continuity: actively changing

  1.00

  × evidence: widely adopted

  1.00

  Composite score

  91.1

• 2

  pentest-ai

  Community favourite

  0xSteph/pentest-ai ↗

  Best for: Authorized bug-bounty work with per-program scope and rate: it applies a program profile to every request and supports a dry run before sending.

  Pentest-AI is distributed as the PyPI package ptai and documents MCP, CLI, and CI/CD interfaces for AI-driven pentest investigations, with machine oracles deciding whether a finding is verified. Before choosing it, note that setup requires Python 3.10 to 3.14 plus a supported AI client or model provider.

  Score 86.4: show every number behind it

  • Adoption85 / 100 · weight 40%
    • GitHub stars81
    • PyPI downloads25
      PyPI downloads show no weekday rhythm; 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
  • Momentum75 / 100 · weight 14%
    • Stars gained, relative to size89
    • Stars gained, absolute79
    • PyPI download trend46
  • 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

  86.4

  × relevance: the keyword is dedicated here

  1.00

  × continuity: actively changing

  1.00

  × evidence: widely adopted

  1.00

  Composite score

  86.4

• 3

  mcp-shodan

  Community favourite

  w0h1v/mcp-shodan ↗

  Best for: Analyst triage of an IP, hostname, product, or CVE: it exposes 7 read-only tools for Shodan host lookups, device search, DNS, and CVEDB vulnerability queries.

  mcp-shodan exposes 7 tools for Shodan IP lookups, device searches, DNS lookups, CVE and CPE queries, and product vulnerability searches over stdio or HTTP streaming. It requires the user's own Shodan API key, and its HTTP streaming transport has no authentication, so it should stay on localhost or behind an authenticating reverse proxy.

  Score 78.4: show every number behind it

  • Adoption65 / 100 · weight 40%
    • GitHub stars57
    • npm downloads55
    • 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
  • Momentum73 / 100 · weight 14%
    • Stars gained, relative to size76
    • Stars gained, absolute44
    • 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 integratesnot measured
      not published by the vendor it integrates

  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

• 4

  CVE MCP Server

  Abandoned but popular

  mukul975/cve-mcp-server ↗

  Best for: Triaging a CVE with vulnerability and threat intelligence: it exposes a triage_cve orchestrator plus lookup, scan, risk-score and report tools.

  CVE MCP Server exposes 28 tools for querying vulnerability and threat intelligence sources, including NVD, EPSS, CISA KEV, OSV.dev, Shodan, VirusTotal and MITRE ATT&CK, plus a triage_cve orchestrator and risk-scoring and reporting tools. Several tools require third-party API keys: Shodan lookups need SHODAN_KEY, and repository secret scanning needs GITHUB_TOKEN.

  Score 75.1: 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
  • Maintenance52 / 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 35 days ago, which counts every ref; the stored date would have published 35 days ago
    • Repository maintenance grade55
    • Commit cadence5
  • Momentum95 / 100 · weight 14%
    • Stars gained, relative to size100
    • Stars gained, absolute89
    • 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

  75.1

  × relevance: the keyword is dedicated here

  1.00

  × continuity: actively changing

  1.00

  × evidence: widely adopted

  1.00

  Composite score

  75.1

• 5

  Security Detections MCP

  Community favourite

  MHaggis/Security-Detections-MCP ↗

  Best for: Security teams that keep detection rules in multiple repositories: the README documents local indexing plus a hosted endpoint for querying a unified rule database.

  The README documents a local npm package that indexes local detection repositories and a hosted Streamable HTTP endpoint for querying a unified detection-rule database. Local use requires Node.js and environment variables pointing to those repositories, while the hosted option requires an account token.

  Score 74.5: show every number behind it

  • Adoption75 / 100 · weight 40%
    • GitHub stars68
    • npm downloads50
    • Used through Glamanot measured
      not used through Glama in the last 30 days
  • Maintenance76 / 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 142 days ago
    • Repository maintenance grade80
    • Commit cadence5
  • Momentum60 / 100 · weight 14%
    • Stars gained, relative to size51
    • Stars gained, absolute42
    • 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

  74.5

  × relevance: the keyword is dedicated here

  1.00

  × continuity: actively changing

  1.00

  × evidence: widely adopted

  1.00

  Composite score

  74.5

• 6

  robin

  Community favourite

  apurvsinghgautam/robin ↗

  Best for: Dark web OSINT from an MCP-capable agent: it runs as an MCP server and uses the agent's own model to refine queries and filter results.

  Robin documents a Streamlit web interface and an MCP interface for dark web OSINT searches over Tor, with LLM-assisted query refinement, result filtering, and investigation summaries. Before choosing it, note that it requires Tor to be running and either an API key for a supported LLM provider or a reachable Ollama or custom OpenAI-compatible endpoint, and its README recommends Docker.

  Score 73.3: show every number behind it

  • Adoption97 / 100 · weight 40%
    • GitHub stars97
    • 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
  • Momentum95 / 100 · weight 14%
    • Stars gained, relative to size92
    • Stars gained, absolute100
    • npm download trendnot measured
      no download history for the selected registry
  • Tool quality≈68 / 100 · weight 13%
    • Tool description quality≈68
      tool descriptions not yet scored
    • Built and inspected by Glamanot measured
      never built and inspected by Glama
  • Trust100 / 100 · weight 9%
    • License100
    • Published by the vendor it integratesnot measured
      not published by the vendor it integrates

  Weighted mean of the five

  94.0

  × relevance: the keyword is declared here

  0.78

  × continuity: actively changing

  1.00

  × evidence: widely adopted

  1.00

  Composite score

  73.3

• 7

  mcp-skylos

  Community favourite

  duriantaco/skylos ↗

  Best for: Teams reviewing AI coding-agent pull requests in Python, TypeScript, or Go: it exposes security, secrets, dead-code, change-verification, and agent-guardrail tools.

  mcp-skylos exposes 17 MCP tools for code analysis, including dead-code, security, secrets, quality, architecture, remediation, change-validation, triage-learning, provenance, and agent-verification tools. It is installed from PyPI as skylos and runs locally by default, but Python has the deepest coverage while other supported languages receive narrower checks.

  Score 73.3: 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 size89
    • Stars gained, absolute68
    • PyPI download trend68
  • 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

  94.0

  × relevance: the keyword is declared here

  0.78

  × continuity: actively changing

  1.00

  × evidence: widely adopted

  1.00

  Composite score

  73.3

• 8

  Threat Intelligence MCP Server

  Community favourite

  marc-shade/world-intel-mcp ↗

  Best for: Security analysts triaging suspicious IPs or file hashes: it checks reputation via VirusTotal, AbuseIPDB, and Shodan and retrieves CISA KEV and ThreatFox IOCs.

  Threat Intelligence MCP Server exposes 11 tools for listing and fetching threat feeds, checking IP and hash reputation, retrieving CISA KEV entries and recent ThreatFox IOCs, checking bulk IPs or network scan results, and viewing or clearing cached threat data. Its reputation checks go through VirusTotal, AbuseIPDB, and Shodan, so that external-service dependency is worth confirming before installation.

  Score 67.9: show every number behind it

  • Adoption76 / 100 · weight 40%
    • GitHub stars76
    • 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
  • Momentum100 / 100 · weight 14%
    • Stars gained, relative to size100
    • Stars gained, absolute100
    • 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 integratesnot measured
      not published by the vendor it integrates

  Weighted mean of the five

  87.1

  × relevance: the keyword is declared here

  0.78

  × continuity: actively changing

  1.00

  × evidence: widely adopted

  1.00

  Composite score

  67.9

• 9

  agent-security-scanner-mcp

  Community favourite

  sinewaveai/agent-security-scanner-mcp ↗

  Best for: Before an agent trusts an AI-suggested dependency: check_package and scan_packages test import names against official registries to flag hallucinated packages.

  It exposes 22 tools across an MCP server and a CLI: file, project, and git-diff vulnerability scanning, prompt and pre-execution agent action screening returning BLOCK/WARN/LOG/ALLOW, MCP server source audits, package hallucination checks against registries, CycloneDX SBOM generation with OSV.dev CVE lookups, and SOC2, GDPR, and AIUC-1 compliance evaluation. It ships as an npm package invoked through npx, so adoption assumes a Node.js toolchain and an init step per client (claude-code, cursor, windsurf, cline, and others) followed by a client restart, and no PyPI package is attributed to it.

  Score 67.4: show every number behind it

  • Adoption69 / 100 · weight 40%
    • GitHub stars52
    • npm downloads61
    • Used through Glamanot measured
      not used through Glama in the last 30 days
  • Maintenance76 / 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 19 days ago, which counts every ref; the stored date would have published 19 days ago
    • Repository maintenance grade80
    • Commit cadence40
  • Momentum25 / 100 · weight 14%
    • Stars gained, relative to size27
    • Stars gained, absolute13
    • npm download trend35
  • Tool quality71 / 100 · weight 13%
    • Tool description quality63
    • 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

  67.4

  × relevance: the keyword is dedicated here

  1.00

  × continuity: actively changing

  1.00

  × evidence: widely adopted

  1.00

  Composite score

  67.4

• 10

  pipelock

  Community favourite

  pipelab-org/pipelock ↗

  Best for: Wrapping an existing MCP server you do not control: it proxies the connection and scans both directions for credential leaks, prompt injection, and tool description poisoning.

  Pipelock runs as an intermediary between agents and the network, inspecting mediated HTTP, WebSocket, MCP, and A2A traffic, and it can sit in front of a configured MCP upstream to scan messages in both directions for secret exfiltration, prompt injection, and poisoned tool descriptions. Reading the contents of CONNECT tunnels requires TLS interception, since plain CONNECT is only checked at the hostname and URL level, and with no npm or PyPI package published it must be installed from the Go source repository.

  Score 65.8: 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
  • Momentum91 / 100 · weight 14%
    • Stars gained, relative to size100
    • Stars gained, absolute77
    • 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

  84.4

  × relevance: the keyword is declared here

  0.78

  × continuity: actively changing

  1.00

  × evidence: widely adopted

  1.00

  Composite score

  65.8

• 11

  Beelzebub MCP Honeypot

  Community favourite

  beelzebub-labs/beelzebub ↗

  Best for: Testing AI agents for prompt injection: it exposes MCP bait tools that make suspicious invocations observable during controlled agent testing.

  Beelzebub runs decoy services over SSH, HTTP, TCP, TELNET and MCP from YAML configuration, and emits captured interaction evidence to logs, RabbitMQ or Beelzebub Platform. Its installer starts a bundle of example services that includes privileged ports and can enable host networking on Linux, so deployment assumes an isolated lab host with authorization for every configured listener.

  Score 64.3: show every number behind it

  • Adoption84 / 100 · weight 40%
    • GitHub stars84
    • 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
  • Momentum60 / 100 · weight 14%
    • Stars gained, relative to size56
    • Stars gained, absolute67
    • 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

  82.4

  × relevance: the keyword is declared here

  0.78

  × continuity: actively changing

  1.00

  × evidence: widely adopted

  1.00

  Composite score

  64.3

• 12

  REMnux MCP Server

  Community favourite

  REMnux/remnux-mcp-server ↗

  Best for: Analysts with an AI assistant on or connected to a REMnux system: it exposes run_tool, analyze_file, and suggest_tools to execute and plan malware analysis.

  The server exposes 12 tools for running commands on REMnux, getting file metadata and hashes, listing samples, extracting archives, uploading and downloading files, auto-analyzing files by type, suggesting tools, extracting IOCs, getting tool help, and checking installed tools. It requires Node.js 20 or later, plus Docker access for container mode or SSH access for VM mode, though the server and AI assistant can both run locally on a REMnux system without Docker or SSH.

  Score 64.1: show every number behind it

  • Adoption72 / 100 · weight 40%
    • GitHub stars54
    • npm downloads64
    • 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
  • Momentum70 / 100 · weight 14%
    • Stars gained, relative to size97
    • Stars gained, absolute49
    • npm download trend45
  • 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

  82.2

  × relevance: the keyword is declared here

  0.78

  × continuity: actively changing

  1.00

  × evidence: widely adopted

  1.00

  Composite score

  64.1

• 13

  mcpproxy-go

  Community favourite

  smart-mcp-proxy/mcpproxy-go ↗

  Best for: Routing multiple upstream MCP servers through one endpoint while needing new servers quarantined: its quarantine management withholds their tools until review and approval.

  It exposes nine tools covering tool discovery and calls, registry search, upstream server management, truncated-response cache reads, and quarantine security management. Quarantine is not a guarantee of safety: the project documents exceptions and says auto mode does not hold changes.

  Score 62.9: 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
  • Maintenance100 / 100 · weight 24%
    • Last commit touching this server100
    • Repository maintenance grade100
    • Commit cadence100
  • Momentum75 / 100 · weight 14%
    • Stars gained, relative to size87
    • Stars gained, absolute57
    • npm 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

  80.6

  × relevance: the keyword is declared here

  0.78

  × continuity: actively changing

  1.00

  × evidence: widely adopted

  1.00

  Composite score

  62.9

• 14

  MCP Manager

  Steady

  MCP-Manager/MCP-Security-Checklists ↗

  Best for: Teams planning MCP security controls: the repository provides checklists and guides for Docker sandboxing, OAuth troubleshooting, identity management, logging, and threat mitigation.

  The repository documents security checklists and guides for MCP deployment, authentication and authorization, logging and auditing, threat mitigation, and AI agent security, but it does not document exposed tools. No npm package is published, no PyPI package is attributed, and exposed tools were not measured, so installation and interface need verification.

  Score 62.1: show every number behind it

  • Adoption58 / 100 · weight 40%
    • GitHub stars58
    • npm downloadsnot measured
      no npm package
    • Used through Glamanot measured
      not used through Glama in the last 30 days
  • Maintenance71 / 100 · weight 24%
    • Last commit touching this server100
    • Repository maintenance grade30
    • Commit cadence40
  • Momentum32 / 100 · weight 14%
    • Stars gained, relative to size37
    • Stars gained, absolute24
    • 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

  62.1

  × relevance: the keyword is dedicated here

  1.00

  × continuity: actively changing

  1.00

  × evidence: widely adopted

  1.00

  Composite score

  62.1

• 15

  Metasploit MCP Server

  Abandoned but popular

  GH05TCREW/MetasploitMCP ↗

  Best for: Authorized Metasploit penetration testing with an AI assistant: README documents tools for listing exploits and payloads, running exploits and auxiliary/post modules, and managing sessions and handlers.

  Metasploit MCP Server bridges large language models to the Metasploit Framework through README-documented tools for module discovery, exploit and auxiliary or post module execution, payload generation, and session and handler management. It requires a running Metasploit Framework with msfrpcd and Python 3.10 or higher, so deployment starts with that RPC service.

  Score 61.9: 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
  • Maintenance32 / 100 · weight 24%
    • Last commit touching this server42
    • Repository maintenance grade30
    • Commit cadence5
  • Momentum55 / 100 · weight 14%
    • Stars gained, relative to size58
    • Stars gained, absolute51
    • npm download trendnot measured
      no download history for the selected registry
  • Tool quality≈68 / 100 · weight 13%
    • Tool description quality≈68
      tool descriptions not yet scored
    • Built and inspected by Glamanot measured
      never built and inspected by Glama
  • Trust100 / 100 · weight 9%
    • License100
    • Published by the vendor it integratesnot measured
      not published by the vendor it integrates

  Weighted mean of the five

  61.9

  × relevance: the keyword is dedicated here

  1.00

  × continuity: actively changing

  1.00

  × evidence: widely adopted

  1.00

  Composite score

  61.9

• 16

  UniFi MCP Server

  Community favourite

  enuno/unifi-mcp-server ↗

  Best for: AI agents managing UniFi sites through cloud APIs: it exposes 71 tools for sites, hosts, ISP metrics, SD-WAN, connector proxy, and integration API calls.

  The server exposes 71 MCP tools covering UniFi sites, hosts, ISP and SD-WAN metrics, Network and Protect connector proxy requests, and integration API resources. The cloud API modes cover sites and aggregate statistics but not per-device control or configuration, which requires local mode.

  Score 61.7: show every number behind it

  • Adoption67 / 100 · weight 40%
    • GitHub stars63
    • PyPI downloads26
      PyPI downloads show no weekday rhythm; 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
  • Momentum93 / 100 · weight 14%
    • Stars gained, relative to size100
    • Stars gained, absolute75
    • PyPI download trend100
  • Tool quality48 / 100 · weight 13%
    • Tool description quality40
    • 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

  79.1

  × relevance: the keyword is declared here

  0.78

  × continuity: actively changing

  1.00

  × evidence: widely adopted

  1.00

  Composite score

  61.7

• 17

  squirrelscan

  Community favourite

  squirrelscan/squirrelscan ↗

  Best for: Auditing a website's security headers and site integrity from a coding agent: it serves the audit over MCP and returns fix instructions an agent can apply.

  squirrelscan crawls a site and runs rule categories covering crawlability, SEO, performance, security, site integrity and agent experience, with results reachable through a CLI, a hosted or local MCP server, and an API, in output formats including console, JSON, HTML, Markdown and LLM. No package was found published to npm or PyPI at publication and its MCP tool list has not been inspected, so choosing it means installing the single-binary CLI it documents and discovering the exposed tools only after connecting.

  Score 61.4: show every number behind it

  • Adoption62 / 100 · weight 40%
    • GitHub stars62
    • 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
  • Momentum86 / 100 · weight 14%
    • Stars gained, relative to size100
    • Stars gained, absolute64
    • 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

  78.7

  × relevance: the keyword is declared here

  0.78

  × continuity: actively changing

  1.00

  × evidence: widely adopted

  1.00

  Composite score

  61.4

• 18

  FofaMap

  Community favourite

  asaotomo/FofaMap ↗

  Best for: Authorized FOFA asset mapping with an optional Nuclei handoff: it exposes query validation, account quota checks, search, and a plan-and-approve scan workflow.

  FofaMap wraps FOFA asset discovery in 31 MCP tools covering query syntax validation, field catalogues, account and quota checks, exact searches with cursors, favicon hash lookups, host aggregation, exports, recurring schedules, and a Nuclei plan, approval, and execute handoff. Before choosing it, note that ordinary queries require a FOFA API Key, active scanning stays blocked until a user approves an exact expiring plan, and the host aggregation tool is unavailable to registered accounts.

  Score 60.4: 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
  • Maintenance97 / 100 · weight 24%
    • Last commit touching this server100
    • Repository maintenance grade100
    • Commit cadence85
  • Momentum58 / 100 · weight 14%
    • Stars gained, relative to size61
    • Stars gained, absolute53
    • 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

  77.4

  × relevance: the keyword is declared here

  0.78

  × continuity: actively changing

  1.00

  × evidence: widely adopted

  1.00

  Composite score

  60.4

• 19

  Lighthouse MCP

  Community favourite

  danielsogl/lighthouse-mcp-server ↗

  Best for: Security reviews of live websites that also need Lighthouse performance or SEO context: it exposes a get_security_audit tool checking HTTPS and CSP.

  Lighthouse MCP exposes 11 tools for running Google Lighthouse audits on websites and retrieving performance, accessibility, SEO, Core Web Vitals, resource, mobile-versus-desktop, performance-budget, and security results. Before choosing it, note that it requires Node.js 22.0.0 or newer and a Chrome/Chromium browser, with Chrome managed automatically by Lighthouse.

  Score 60.1: show every number behind it

  • Adoption75 / 100 · weight 40%
    • GitHub stars47
    • npm downloads68
    • 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
  • Momentum48 / 100 · weight 14%
    • Stars gained, relative to size50
    • Stars gained, absolute26
    • npm download trend72
  • Tool quality66 / 100 · weight 13%
    • Tool description quality57
    • 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

  77.1

  × relevance: the keyword is declared here

  0.78

  × continuity: actively changing

  1.00

  × evidence: widely adopted

  1.00

  Composite score

  60.1

• 20

  Node9-Proxy

  Community favourite

  node9-ai/node9-proxy ↗

  Best for: Running autonomous agents with access to Slack, GitHub, or databases: it gates tool calls locally, holds destructive actions for review, and keeps an audit record.

  Node9-Proxy checks an AI agent's tool calls before they run and documents an MCP server, launched over stdio with npx -y node9-ai mcp-server, that lets an agent read status, posture, audit record, and policy and explain decisions. It requires Node.js 22+ and can run with local protection only; dashboard login is optional and adds nothing to enforcement.

  Score 59.2: 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
  • Momentum61 / 100 · weight 14%
    • Stars gained, relative to size55
    • Stars gained, absolute36
    • 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

  75.9

  × relevance: the keyword is declared here

  0.78

  × continuity: actively changing

  1.00

  × evidence: widely adopted

  1.00

  Composite score

  59.2

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 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 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