Netlify MCP Server
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| NETLIFY_ACCESS_TOKEN | Yes | Your Netlify personal access token |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Server capabilities have not been inspected yet.
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| createSiteFromGitHubC | Create a new Netlify site from a GitHub repository |
| listSitesB | List Netlify sites |
| getSiteC | Get details of a specific site |
| deleteSiteC | Delete a site |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 4 tools
Each tool has a clearly distinct purpose: createSiteFromGitHub creates sites from GitHub, deleteSite removes sites, getSite retrieves details, and listSites lists all sites. There is no overlap in functionality, making tool selection unambiguous.
Three tools follow a consistent verb_noun pattern (deleteSite, getSite, listSites), but createSiteFromGitHub deviates slightly by including 'FromGitHub' for specificity. This minor inconsistency does not hinder readability, as the naming remains intuitive and mostly uniform.
With only 4 tools, the server feels thin for managing Netlify sites, as it lacks operations like updating sites, managing deployments, or handling environment variables. While the core CRUD operations are covered, the scope is limited and may require workarounds for common workflows.
The tools cover basic CRUD operations (create, read, delete, list) for sites, but there are notable gaps such as updating site settings, managing deployments, or handling other Netlify resources like functions or forms. This incomplete surface could lead to agent failures for advanced tasks.