What it does

Reads content types and entries and can create drafts in a Contentful space. The content model access is the underrated part: an agent that knows your fields writes entries that validate instead of failing on save. Keep publish permission separate from write permission.

Install

Terminal

npx -y @contentful/mcp-server

Client configuration

Paste this into your MCP client config (Claude Desktop, Cursor, or any client that reads mcpServers), then restart the client.

mcp.json

{
  "mcpServers": {
    "contentful": {
      "command": "npx",
      "args": [
        "-y",
        "@contentful/mcp-server"
      ]
    }
  }
}

Use it for

Drafting entries and inspecting content models in a Contentful space

Skip it if

Publishing straight to production without an editorial step

When to use it

Reach for this when the task needs cms inside the agent loop. Skip it if a plain shell command or a one-off script is enough — every server you add costs context and adds a failure mode.

Other TypeScript servers

Filesystem — Gives an agent scoped read, write, and search access to directories you explicitly allow
Memory — A persistent knowledge graph stored in a local JSON file, exposed through entities, relations, and observations
Sequential Thinking — Gives the model a scratchpad for structured, revisable reasoning: numbered thoughts that can branch, revise, and conclude

Contentful MCP