ContentfulBLOCK
MCP (Model Context Protocol) server for the Contentful Management API
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
A Model Context Protocol (MCP) server that provides AI assistants with comprehensive tools to interact with Contentful APIs.
🚀 Example Use Cases
This MCP server provides a comprehensive set of tools for content management, allowing AI to help you create, edit, organize, and publish content directly within Contentful. Once configured, you can use natural language in your AI assistant of choice to manage and interact with your Contentful spaces, including:
- Content Creation: "Create a new blog post for our fall product launch"
- Content Management: "Update all product entries to include the new pricing structure"
- Asset Organization: "Upload and organize these marketing images by campaign"
- Workflow Automation: "Create an AI action that translates content to Spanish"
- Content Modeling: "Add a new field to the product content type for customer ratings"
📓 Table of Contents
- ⚙️ Getting Started
- Prerequisites
- Installation
- Environment Variables
- Protected environments
- Configuration
- 🛠️ Available Tools
- 🔍 Development
- Testing with MCP Inspector
- 📦 Releases
- 🤝 Contributing and development
- 📚 Documentation
- ❓ Help & Support
- 📄 License and Notices
- 🛡️ Code of Conduct
⚙️ Getting started
Prerequisites
- Node.js
- npm
- A Contentful account with a Space ID
- Contentful Management API personal access token
Installation
One-Click install
[![Install MCP Server](https:/
0a01c7cb003cOBSERVED · 2026-10-07Connect
Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control. Replace the environment placeholders with a token scoped to the least it needs.
claude mcp add mcp-tools --env CONTENTFUL_MANAGEMENT_ACCESS_TOKEN=${CONTENTFUL_MANAGEMENT_ACCESS_TOKEN} -- npx -y @contentful/[email protected]{
"mcpServers": {
"mcp-tools": {
"command": "npx",
"args": [
"-y",
"@contentful/[email protected]"
],
"env": {
"CONTENTFUL_MANAGEMENT_ACCESS_TOKEN": "${CONTENTFUL_MANAGEMENT_ACCESS_TOKEN}"
}
}
}
}Exposed tools (2)
2 read · 0 write · 0 destructive.
| Tool | Risk | Description |
|---|---|---|
Hero | read | A hero section |
Test | read | Test |
Trust audit
BLOCKgrade D · trust 69/100 Do not install this without reading the findings. The audit found something that could harm you or your machine.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | PASS |
| L1 | Static analysis of the code | FAIL |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | PASS |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- declared (2 observation(s))
- Network
- none-observed
- Shell
- declared (2 observation(s))
- Dependencies
- not all pinned
- Secrets in source
- none-found
Findings (14)
exec(
.bito.yaml
.prettierignore
.swcrc
import baseConfig from '../../eslint.config.mjs';
outputPath: '../../dist/packages/mcp-tools',
import { formatResponse } from '../../utils/formatters.js';import { VariableType } from '../../utils/ai-actions.js';import { createMockConfig } from '../../test-helpers/mockConfig.js';[](https://cursor.com/en/install-mcp?name=contentful-mcp&config=eyJjb21tYW5kIjoibnB4IC15IEBjb250ZW50ZnVsL21jcC1zZXJ2ZXIiLCJlbnYiO
[](https://cursor.com/en/install-mcp?name=contentful-mcp&config=eyJjb21tYW5kIjoibnB4IC15IEBjb250ZW50ZnVsL21jcC1zZXJ2ZXIiLCJlbnYiO
@anthropic-ai/dxt, @commitlint/cli, @commitlint/config-conventional, @swc-node/register, @swc/cli, @swc/core, @swc/helpers, @types/node
@modelcontextprotocol/sdk, dotenv, @types/node, eslint, prettier, rimraf, tsup, typescript
@contentful/rich-text-types, @modelcontextprotocol/sdk, contentful-export, contentful-import, fast-xml-parser, lodash-es, outdent, tsup
Gates applied: no_behavioural_pass.
0a01c7cb003cfull audit observations/trust-audit/mcp-server/contentful__contentful-1.json · Report an issue / request a re-scanAudit history
Every audit this server has had. A grade with a past is a grade somebody is still checking.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-07 | 0a01c7cb003c | BLOCK | D | 69 | first audit |
Questions
What is the Contentful MCP server?
MCP (Model Context Protocol) server for the Contentful Management API
What tools does Contentful expose?
2 in total: 2 read-only, 0 that write, and 0 that can delete or overwrite. Every one is listed on this page with its risk.
Is Contentful safe to connect to an agent?
No — not without reading the findings first. The audit graded it D (69/100) and found 1 critical or high issue in the source. Each one is listed on this page with the file and line it is on.
What credentials does Contentful need?
It reads CONTENTFUL_MANAGEMENT_ACCESS_TOKEN from the environment. Give it a token scoped to the least it needs — an agent that can be talked into calling a tool can be talked into calling it with your credentials.
How does Contentful run?
It speaks stdio, so it runs as a local process your client starts. It is published on npm as @contentful/mcp-tools at 0.12.38.
How current is this page?
The grade is for one exact copy of the source (0a01c7cb003c), read on 2026-10-07. The repository is watched and re-audited when it changes.