StrapiSAFE
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
A Model Context Protocol server for interacting with Strapi CMS. This server enables AI assistants to interact with your Strapi instance through a standardized interface, supporting content types and REST API operations.
⚠️ IMPORTANT DISCLAIMER: This software has been developed with the assistance of AI technology. It is provided as-is and should NOT be used in production environments without thorough testing and validation. The code may contain errors, security vulnerabilities, or unexpected behavior. Use at your own risk for research, learning, or development purposes only.
Changelog
Version 2.6.0 - Enhanced Validation & Debugging Update
- 🔧 Implemented structured error handling with McpError and ErrorCode
- ✅ Added comprehensive Zod validation for runtime type safety
- 📊 Integrated comprehensive logging system with request tracking
- 🐛 Added debug mode configuration with environment variables
- 🧹 Removed unused prompt handlers for cleaner codebase
- ⬆️ Updated all dependencies to latest versions
- 📖 Added DEBUGGING.md guide for development workflow
- 🛡️ Enhanced security with better input validation
- 🚀 Improved developer experience with detailed error messages
For complete version history, see CHANGELOG.md.
Features
- 🔍 Schema introspection
- 🔄 REST API support with validation
- 📸 Media upload handling
- 🔐 JWT authentication
- 📝 Content type management
- 🖼️ Image processing with format conversion
- 🌐 Multiple server support
- ✅ Automatic schema validation
- 🔒 Write protection policy
- 📚 Integrated documentation
- 🔄 Version compatibility management
Installation
You can use this server directly with npx in your Claude Desktop configuration:
{
"mcpServers": {
"strapi": {
"command": "npx",
"args": ["-y",560721330050OBSERVED · 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.
claude mcp add strapi-mcp-server -- npx -y @bschauer/[email protected]
{
"mcpServers": {
"strapi-mcp-server": {
"command": "npx",
"args": [
"-y",
"@bschauer/[email protected]"
]
}
}
}Exposed tools (3)
1 read · 2 write · 0 destructive.
| Tool | Risk | Description |
|---|---|---|
strapi_get_components | read | Get all components from Strapi with pagination support. Returns both component data and pagination metadata (page, pageSize, total, pageCount). |
strapi_rest | write | Execute REST API requests against Strapi endpoints. IMPORTANT: All write operations (POST, PUT, DELETE) require explicit user authorization via the userAuthorized parameter. ## Reading Data params: { populate: [ |
strapi_upload_media | write | Upload media to Strapi |
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.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | PASS |
| L1 | Static analysis of the code | PASS |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | PASS |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- none-observed
- Network
- declared (4 observation(s))
- Shell
- none-observed
- Dependencies
- not all pinned
- Secrets in source
- none-found
Findings (2)
.node-version
@modelcontextprotocol/sdk, @types/node-fetch, @types/qs, form-data, node-fetch, qs, sharp, zod
Gates applied: no_behavioural_pass.
560721330050full audit observations/trust-audit/mcp-server/misterboe__strapi-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 | 560721330050 | SAFE | B | 89 | first audit |
Questions
What tools does Strapi expose?
3 in total: 1 read-only, 2 that write, and 0 that can delete or overwrite. 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.
What credentials does Strapi need?
No credential environment variables were found in its source, so it appears to need none.
How does Strapi run?
It speaks stdio, so it runs as a local process your client starts. It is published on npm as @bschauer/strapi-mcp-server at 2.9.0.
How current is this page?
The grade is for one exact copy of the source (560721330050), read on 2026-10-07. The repository is watched and re-audited when it changes.