Atlas / MCP servers / l33tdawg / Strapi

StrapiSAFE

mcp/l33tdawg/strapi

An MCP server for your Strapi CMS

Verdict
SAFE
Grade
B
Trust score
89 /100
Exposed tools
20 9r · 9w · 2d
Transport
stdio
License
MIT
Stars
25
01

Overview

From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.

An MCP server for Strapi CMS, providing access to content types and entries through the Model Context Protocol.

Overview

This MCP server integrates with any Strapi CMS instance to provide:

  • Access to Strapi content types as resources
  • Tools to create and update content types in Strapi
  • Tools to manage content entries (create, read, update, delete)
  • Support for Strapi in development mode
  • Robust error handling with clear diagnostics and troubleshooting guidance
  • Configuration validation to prevent common setup issues

Setup

Environment Variables

It's recommended to use a .env file in the project root to store your credentials.

  • STRAPI_URL: The URL of your Strapi instance (default: http://localhost:1337)
  • STRAPI_ADMIN_EMAIL: The email address for a Strapi admin user (Recommended for full functionality, especially schema access).
  • STRAPI_ADMIN_PASSWORD: The password for the Strapi admin user (Recommended).
  • STRAPI_API_TOKEN: (Optional Fallback) An API token. Can be used if admin credentials are not provided, but may have limited permissions.
  • STRAPI_DEV_MODE: Set to "true" to enable development mode features (defaults to false).

Example `.env` file:

STRAPI_URL=http://localhost:1337
[email protected]
STRAPI_ADMIN_PASSWORD=your_admin_password
# STRAPI_API_TOKEN=your_api_token_here # Optional

Important:

  • Add .env to your .gitignore file to avoid committing credentials
  • Avoid placeholder values like "strapi_token" - the server validates and rejects common placeholders

Installation

Install from npm (Recommended)

npm install strapi-mcp

Install from source (Development)

For the latest development features:

git clone https://github.com/l33tdawg/strapi-mcp.git
cd strapi-mcp
npm install
npm run build

Running

Recommended Method (using Cursor MCP Configuration):

For Cursor users

Read from source at commit 4697e7917d9fOBSERVED · 2026-10-09
02

Connect

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-code
claude mcp add strapi-mcp --env STRAPI_ADMIN_PASSWORD=${STRAPI_ADMIN_PASSWORD} --env STRAPI_API_TOKEN=${STRAPI_API_TOKEN} -- npx -y [email protected]
claude-desktop
{
  "mcpServers": {
    "strapi-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "[email protected]"
      ],
      "env": {
        "STRAPI_ADMIN_PASSWORD": "${STRAPI_ADMIN_PASSWORD}",
        "STRAPI_API_TOKEN": "${STRAPI_API_TOKEN}"
      }
    }
  }
}
03

Exposed tools (20)

9 read · 9 write · 2 destructive. Blast radius: 2 tools can delete or overwrite — an agent that can be talked into calling a tool can be talked into calling this one.

ToolRiskDescription
connect_relationreadConnects related entries to a relation field.
create_componentwriteCreate a new component
create_content_typewriteCreates a new content type (Admin privileges required).
create_entrywriteCreate a new entry for a content type
delete_content_typedestructiveDeletes a content type (Admin privileges required).
delete_entrydestructiveDeletes a specific entry.
disconnect_relationreadDisconnects related entries from a relation field.
get_component_schemareadGet the schema for a specific component
get_content_type_schemareadGet the schema (fields, types, relations) for a specific content type.
get_entriesreadGet entries for a specific content type with optional filtering, pagination, sorting, and population of relations
get_entryreadGet a specific entry by ID
list_componentsreadList all available components in Strapi
list_content_typesreadList all available content types in Strapi
publish_entrywritePublishes a specific entry.
unpublish_entryreadUnpublishes a specific entry.
update_componentwriteUpdate an existing component
update_content_typewriteUpdates a content type attributes (Admin privileges required).
update_entrywriteUpdate an existing entry
upload_mediawriteUpload a media file to the Strapi Media Library. Maximum size: ~750KB file (1MB base64). For larger files, use upload_media_from_path.
upload_media_from_pathwriteUpload a media file from a local file path. Avoids context window overflow issues. Maximum size: 10MB.
04

Trust audit

SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.

LayerWhat it checksResult
L0Provenance & inventoryPASS
L1Static analysis of the codePASS
L2Instruction surface (what it tells the agent)PASS
L3Class-specific surfaceWARN
L4Behavioural (sandbox)SKIPPED

What the source does

Filesystem
declared (1 observation(s))
Network
declared (5 observation(s))
Shell
none-observed
Dependencies
not all pinned
Secrets in source
none-found

Findings (5)

MEDIUMFilesystem / path · mcp.destructive_tools · CWE-22, CWE-59
delete_content_type, delete_entry
Why it matters. 2 tool(s) can delete or overwrite
Fix. prefer a read-only mode or scoped tokens; the page states the blast radius
LOWSupply chain · supply.unpinned · CWE-829, CWE-1357
package.json
axios, dotenv, form-data, @types/form-data, @types/node, canvas, dotenv-cli, typescript
Why it matters. 8 dependency range(s) float
Fix. pin exact versions or ship a lockfile
INFOPrompt injection · prompt.authority_framing · CWE-94, CWE-1427
README.md:373
4. Set a name, description, and token type (preferably "Full access")
INFOPrompt injection · prompt.authority_framing · CWE-94, CWE-1427
README.md:400
- Verify your API token has proper permissions (preferably "Full access")
INFOPrompt injection · prompt.authority_framing · CWE-94, CWE-1427
README.md:429
- If using API token, ensure it has "Full access" permissions

Gates applied: no_behavioural_pass.

Audited 2026-10-09 · audit v0.4.1 · source sha 4697e7917d9ffull audit observations/trust-audit/mcp-server/l33tdawg__strapi.json · Report an issue / request a re-scan
05

Audit history

Every audit this server has had. A grade with a past is a grade somebody is still checking.

DateSourceVerdictGradeScoreChange
2026-10-094697e7917d9fSAFEB89first audit
06

Questions

What is the Strapi MCP server?

An MCP server for your Strapi CMS

What tools does Strapi expose?

20 in total: 9 read-only, 9 that write, and 2 that can delete or overwrite (delete_content_type, delete_entry). Every one is listed on this page with its risk.

Is Strapi safe to connect to an agent?

The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean server reads B. Separately from the audit: 2 of its tools can destroy data, so scope the token you give it to what you actually need.

What credentials does Strapi need?

It reads STRAPI_ADMIN_PASSWORD and STRAPI_API_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 Strapi run?

It speaks stdio, so it runs as a local process your client starts. It is published on npm as strapi-mcp at 0.2.3.

How current is this page?

The grade is for one exact copy of the source (4697e7917d9f), read on 2026-10-09. The repository is watched and re-audited when it changes.

Advertisement