Skip to main content
Glama
deenesjakoruzh
MCERQUA

Netlify MCP Server

by MCERQUA
OverviewSchemaSourceRelated ServersDiscussionsAdmin
JavaScript
Remote

Netlify MCP 서버

Netlify 사이트를 관리하기 위한 모델 컨텍스트 프로토콜(MCP) 서버입니다. 이 서버는 MCP를 통해 Netlify API와 원활하게 통합되어 MCP 지원 환경에서 직접 사이트를 생성, 관리 및 배포할 수 있도록 지원합니다.

특징

  • GitHub 저장소에서 새 사이트 만들기

  • 기존 Netlify 사이트 나열

  • 자세한 사이트 정보를 얻으세요

  • 사이트 삭제

Related MCP server: Express MCP Server

설치

  1. 이 저장소를 복제하세요:

지엑스피1

  1. 종속성 설치:

npm install

  1. 프로젝트를 빌드하세요:

npm run build

구성

Netlify 액세스 토큰 받기

  1. https://app.netlify.com/signup 에서 Netlify 계정을 만드세요

  2. 사용자 설정 > 애플리케이션 > 개인 액세스 토큰으로 이동하세요.

  3. "새로운 액세스 토큰"을 클릭하세요

  4. 이름을 지정합니다(예: "MCP 통합")

  5. 생성된 토큰을 복사하세요

MCP 설정

  1. 프로젝트 루트에 .env 파일을 만듭니다.

NETLIFY_ACCESS_TOKEN=your_token_here

  1. MCP 설정 구성에 서버를 추가합니다.

{
  "mcpServers": {
    "netlify": {
      "command": "node",
      "args": ["path/to/netlify-mcp/build/index.js"],
      "env": {
        "NETLIFY_ACCESS_TOKEN": "your_token_here"
      },
      "disabled": false,
      "autoApprove": []
    }
  }
}

사용 가능한 도구

GitHub에서 사이트 생성

GitHub 저장소에서 새로운 Netlify 사이트를 만듭니다.

interface CreateSiteFromGitHubArgs {
  name: string;          // Name for the new site
  repo: string;          // GitHub repository (format: owner/repo)
  branch: string;        // Branch to deploy from
  buildCommand: string;  // Build command to run
  publishDir: string;    // Directory containing the built files
}

리스트사이트

귀하가 접근할 수 있는 모든 Netlify 사이트를 나열하세요.

interface ListSitesArgs {
  filter?: 'all' | 'owner' | 'guest';  // Optional filter for sites
}

getSite

특정 사이트에 대한 자세한 정보를 얻으세요.

interface GetSiteArgs {
  siteId: string;  // ID of the site to retrieve
}

사이트 삭제

Netlify 사이트를 삭제합니다.

interface DeleteSiteArgs {
  siteId: string;  // ID of the site to delete
}

선적 서류 비치

자세한 내용은 다음을 참조하세요.

기여하다

기여를 환영합니다! 풀 리퀘스트를 제출해 주세요.

특허

이 프로젝트는 MIT 라이선스에 따라 라이선스가 부여되었습니다. 자세한 내용은 라이선스 파일을 참조하세요.

Available Tools

4 tools
createSiteFromGitHubC

Create a new Netlify site from a GitHub repository

ParametersJSON Schema
NameRequiredDescriptionDefault
nameYesName for the new site (will be used as subdomain)
repoYesGitHub repository in format owner/repo
branchNoBranch to deploy from (default: main)main
buildCommandYesBuild command to run (e.g., npm run build)
publishDirYesDirectory containing the built files to publish (e.g., dist, build)
envVarsNoEnvironment variables for the build process

TDQS

C2.9/5.0
Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries the full burden of behavioral disclosure. It states the tool creates a site but doesn't mention critical behaviors like whether this requires specific permissions, if it's idempotent, what happens on failure, or if there are rate limits. This leaves significant gaps for an agent to understand the tool's operational characteristics.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, clear sentence that directly states the tool's purpose without any unnecessary words. It's perfectly front-loaded and wastes no space, making it highly efficient for an agent to parse.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a creation tool with 6 parameters, no annotations, and no output schema, the description is insufficient. It doesn't explain what the tool returns upon success or failure, doesn't mention authentication requirements, and provides no context about the Netlify platform or GitHub integration. The agent would need to guess about many operational aspects.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The schema description coverage is 100%, so all parameters are documented in the schema. The description doesn't add any additional parameter semantics beyond what's already in the schema, such as explaining relationships between parameters or providing examples. This meets the baseline expectation when schema coverage is complete.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the action ('Create') and resource ('new Netlify site from a GitHub repository'), making the purpose immediately understandable. However, it doesn't explicitly differentiate from sibling tools like 'deleteSite' or 'getSite' beyond the obvious action difference, which is why it doesn't reach a perfect score.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides no guidance on when to use this tool versus alternatives like 'listSites' or 'getSite', nor does it mention prerequisites such as GitHub authentication or Netlify account setup. It simply states what the tool does without contextual usage information.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

deleteSiteC

Delete a site

ParametersJSON Schema
NameRequiredDescriptionDefault
siteIdYesID or name of the site to delete

TDQS

C2.9/5.0
Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries the full burden of behavioral disclosure. 'Delete a site' implies a destructive, irreversible mutation, but it doesn't specify permissions required, whether deletion is permanent, what happens to associated resources, or error conditions. This is a significant gap for a destructive operation with zero annotation coverage.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description 'Delete a site' is extremely concise—a single three-word phrase that front-loads the core action. There is zero wasted language, making it efficient and immediately clear, though this conciseness comes at the cost of completeness in other dimensions.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given this is a destructive mutation tool with no annotations and no output schema, the description is insufficiently complete. It doesn't explain what 'delete' entails behaviorally, what the response might contain, or error handling. For a tool that permanently removes resources, more context is needed to guide safe and effective use.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema has 100% description coverage, with the 'siteId' parameter fully documented as 'ID or name of the site to delete'. The description adds no additional parameter information beyond what the schema provides, so it meets the baseline of 3 where the schema does the heavy lifting.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description 'Delete a site' clearly states the verb (delete) and resource (site), making the tool's function immediately understandable. It doesn't explicitly differentiate from sibling tools like 'getSite' or 'listSites', but the action 'delete' inherently distinguishes it from those read-only operations.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides no guidance on when to use this tool versus alternatives. It doesn't mention prerequisites (e.g., needing an existing site), consequences of deletion, or when to choose other tools like 'createSiteFromGitHub' for creation instead. This leaves the agent without context for appropriate tool selection.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

getSiteC

Get details of a specific site

ParametersJSON Schema
NameRequiredDescriptionDefault
siteIdYesID or name of the site to retrieve

TDQS

C2.9/5.0
Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full burden of behavioral disclosure. It states 'Get details' which implies a read-only operation, but doesn't clarify aspects like whether it requires authentication, rate limits, error handling (e.g., for invalid site IDs), or what 'details' includes (e.g., fields returned). For a tool with zero annotation coverage, this leaves significant gaps in understanding its behavior.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, clear sentence with zero wasted words. It's front-loaded with the core purpose ('Get details of a specific site'), making it immediately understandable. Every word earns its place, and there's no unnecessary elaboration.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's simplicity (1 parameter, no output schema, no annotations), the description is incomplete. It doesn't explain what 'details' are returned, which is crucial since there's no output schema. For a read operation with no annotations, it should at least hint at the response structure or key fields to make it fully usable by an agent.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema has 100% description coverage, with the 'siteId' parameter clearly documented as 'ID or name of the site to retrieve'. The description doesn't add any meaning beyond this, as it doesn't elaborate on parameter usage or constraints. With high schema coverage, the baseline score of 3 is appropriate since the schema does the heavy lifting.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the action ('Get details') and resource ('specific site'), making the purpose immediately understandable. It doesn't explicitly differentiate from sibling tools like 'listSites' (which retrieves multiple sites vs. a single site), but the specificity of 'specific site' implies a single-item retrieval. This is clear but lacks explicit sibling differentiation.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides no guidance on when to use this tool versus alternatives. It doesn't mention when to use 'getSite' vs. 'listSites' (e.g., for a single known site vs. browsing all sites) or prerequisites like needing a site ID. There's no explicit or implied context for usage beyond the basic purpose.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

listSitesB

List Netlify sites

ParametersJSON Schema
NameRequiredDescriptionDefault
filterNoFilter sites by access typeall
pageNoPage number for pagination
perPageNoNumber of sites per page (max 100)

TDQS

B3.1/5.0
Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries full burden for behavioral disclosure. It states the action ('List') but doesn't mention whether this is a read-only operation, if it requires authentication, what the output format looks like, or any rate limits. For a listing tool with zero annotation coverage, this leaves significant behavioral gaps.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, efficient sentence that directly states the tool's purpose without unnecessary words. It's appropriately sized for a simple listing operation and front-loads the essential information.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a listing tool with three well-documented parameters but no annotations or output schema, the description is minimally complete. It identifies the resource but doesn't address behavioral aspects like pagination behavior, authentication needs, or output format, which could help the agent understand what to expect.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema has 100% description coverage, thoroughly documenting all three parameters with their purposes, enums, defaults, and constraints. The description adds no additional parameter information beyond what the schema already provides, which is adequate but not additive.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the verb ('List') and resource ('Netlify sites'), making the purpose immediately understandable. However, it doesn't distinguish this tool from its siblings like 'getSite', which might retrieve a specific site rather than listing multiple sites.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides no guidance on when to use this tool versus alternatives like 'getSite' or 'createSiteFromGitHub'. There's no mention of prerequisites, typical use cases, or comparisons to sibling tools, leaving the agent without contextual usage cues.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

  1. 4 tool updatesv1.0.0
    • ChangedcreateSiteFromGitHub7 fields changed
      • addedInput schema / properties / branch / default
        Added value: +"main"
      • changedInput schema / properties / branch / description
        Previous value: -"Branch to deploy from"New value: +"Branch to deploy from (default: main)"
      • changedInput schema / properties / buildCommand / description
        Previous value: -"Build command to run"New value: +"Build command to run (e.g., npm run build)"
      • addedInput schema / properties / envVars
        Added value: +{
+  "additionalProperties": {
+    "type": "string"
+  },
+  "description": "Environment variables for the build process",
+  "type": "object"
+}
      • changedInput schema / properties / name / description
        Previous value: -"Name for the new site"New value: +"Name for the new site (will be used as subdomain)"
      • changedInput schema / properties / publishDir / description
        Previous value: -"Directory containing the built files to publish"New value: +"Directory containing the built files to publish (e.g., dist, build)"
      • changedInput schema / required
        Previous value: -[
-  "name",
-  "repo",
-  "branch",
-  "buildCommand",
-  "publishDir"
-]New value: +[
+  "name",
+  "repo",
+  "buildCommand",
+  "publishDir"
+]
    • ChangeddeleteSite1 field changed
      • changedInput schema / properties / siteId / description
        Previous value: -"ID of the site to delete"New value: +"ID or name of the site to delete"
    • ChangedgetSite1 field changed
      • changedInput schema / properties / siteId / description
        Previous value: -"ID of the site to retrieve"New value: +"ID or name of the site to retrieve"
    • ChangedlistSites3 fields changed
      • addedInput schema / properties / filter / default
        Added value: +"all"
      • addedInput schema / properties / page
        Added value: +{
+  "default": 1,
+  "description": "Page number for pagination",
+  "type": "number"
+}
      • addedInput schema / properties / perPage
        Added value: +{
+  "default": 20,
+  "description": "Number of sites per page (max 100)",
+  "type": "number"
+}
  2. 4 tool updates
    • First observedcreateSiteFromGitHub
    • First observeddeleteSite
    • First observedgetSite
    • First observedlistSites
Deploy Server
Shareable, User-Owned Context BackendPeople, applications, and agents read, write, and coordinate together in one context lake. Reach it over MCP, a CLI, a Python SDK, or REST.fulcradynamics.comAd

TDQS

B3.2/5.0

Scored across 4 tools

Disambiguation5/5

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.

Naming Consistency4/5

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.

Tool Count3/5

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.

Completeness3/5

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.

Maintenance

ActivityInactive
ResponsivenessNo issues

Resources

Related MCP Connectors

Related MCP Servers

  • Express MCP Server

    depeshmandalia
    F
    license
    Not graded
    quality
    D
    maintenance
    A basic example of a serverless Model Context Protocol (MCP) implementation using Netlify Functions, allowing developers to run MCP services without managing traditional server infrastructure.
    -

  • MCP Express on Netlify

    khawjaahmad
    -
    license
    Not graded
    quality
    Not graded
    maintenance
    A basic example of deploying a serverless Model Context Protocol (MCP) server using Netlify Functions, allowing developers to quickly create and deploy MCP-compatible AI agent backends.
    -

Appeared in Searches