A
licenseA
qualityD
maintenanceLet Claude and Cursor manage your Railway infrastructure through natural language. Deploy, configure, and monitor - autonomously and safely.
38
422 npm
73
MIT
Lizard MCP
Officialby lizard-build
Related Servers
Alternatives to Lizard MCP
PlugLayer MCP Serverofficial
AlicenseCqualityBmaintenanceEnables deploying and managing infrastructure via natural language, including project/domain management, compute nodes, image deployment, and CI/CD integration.70MIT- AlicenseNot gradedqualityBmaintenanceEnables managing Sliplane deployments, projects, and application status through natural language, with OAuth or API key auth.MIT
Related Servers
hostman-mcp-serverofficial
AlicenseAqualityDmaintenanceEnables deploying applications to Hostman, creating VPCs, databases, and floating IPs, and managing VCS providers through natural language prompts.1210 npmMIT- AlicenseAqualityCmaintenanceEnables managing DigitalOcean cloud resources, including Droplets, databases, domains, and more, via natural language.12MIT
- AlicenseBqualityFmaintenanceEnables management of Komodo infrastructure including servers, stacks, deployments, builds, repositories, procedures, and system settings through natural language.54124 npm10GPL 3.0
- AlicenseNot gradedqualityNot gradedmaintenanceEnables AI assistants to manage cloud infrastructure through natural language by providing a unified interface to the Dokploy platform. Supports Docker containers, applications, databases, domains, monitoring, and deployment operations through conversational commands.23 npm1-
- AlicenseAqualityBmaintenanceEnables AI assistants to deploy and manage SnapDeploy containers and resources—including builds, logs, environment variables, databases, and custom domains—directly through natural language.15134 npmMIT
- AlicenseAqualityDmaintenanceEnables deployment and management of applications on the Citizen platform from git repositories or local files. It allows AI assistants to monitor deployment logs, handle authentication, and automatically fix build errors using intelligent error analysis.1112 npmMIT
TDQS
A3.6/5.0
Scored across 33 tools
Disambiguation4/5
Tool descriptions are strongly use-case-driven and most map to a distinct resource+operation pair (secrets_*, service_*, domain_*). The main ambiguity risk is between deploy_redeploy and git_checkout, and between config_apply and the narrower service_set/secrets_set, but the descriptions explicitly steer agents. Overall an agent can reliably pick the right tool.
Naming Consistency4/5
Most tools follow a consistent snake_case resource_action pattern (service_create, secrets_list, domain_delete, metrics_get). Deviations are minor: deploy_events and billing_summary are noun_noun, whoami is a command-style exception, and deploy_redeploy/deploy_restart read oddly. The majority is predictable enough.
Tool Count2/5
33 tools is a very large MCP surface, exceeding the 16–25 'heavy' band regardless of the broad platform scope. While few tools are redundant, the set would be hard for an agent to scan and could be consolidated (e.g. service_get_port/service_set_port, deploy_* operations, config_apply vs service_set). This count hurts usability.
Completeness4/5
Core lifecycles are well covered: services have list/show/create/rename/scale/delete, secrets have list/set/delete/refs, domains have attach/verify/delete, and deploy/logs/metrics/git are present. Gaps are minor: projects only have list/create (no update/delete) and there is no explicit domain list, but agents can work around these via service_show and the existing service operations.
Maintenance
ActivityMaintained
ResponsivenessNo issues