drf-mcp-docs

drf-mcp-docs exposes Django REST Framework API documentation to AI coding agents via the Model Context Protocol (MCP). It provides MCP resources and tools to browse endpoints/schemas/auth methods and to generate frontend/client integration code snippets, using DRF schema generators (drf-spectacular, drf-yasg, or DRF built-in).

Evaluated Mar 30, 2026 (0d ago)
Homepage ↗ Repo ↗ DevTools python django django-rest-framework mcp ai-agents api-documentation openapi code-generation devtools
⚙ Agent Friendliness
62
/ 100
Can an agent use this?
🔒 Security
33
/ 100
Is it safe for agents?
⚡ Reliability
22
/ 100
Does it work consistently?

Score Breakdown

⚙ Agent Friendliness

MCP Quality
72
Documentation
75
Error Messages
0
Auth Simplicity
90
Rate Limits
10

🔒 Security

TLS Enforcement
40
Auth Strength
20
Scope Granularity
0
Dep. Hygiene
55
Secret Handling
60

The package is described as read-only documentation exposure, which reduces risk of direct data mutation. However, the README does not document authentication/authorization for MCP over streamable-http, rate limiting, or data redaction policies—so exposure could leak endpoint/schema/auth details. It likely relies on the MCP framework and DRF schema generation; dependency hygiene is unknown beyond declared dependencies.

⚡ Reliability

Uptime/SLA
0
Version Stability
25
Breaking Changes
35
Error Recovery
30
AF Security Reliability

Best When

You already generate OpenAPI/Swagger schema for your DRF API and want AI agents to consume that documentation to generate correct typed client code.

Avoid When

You cannot safely expose API documentation over stdio/HTTP to external parties, or you require strong guarantees about redacting sensitive schema/auth details.

Use Cases

  • Let an AI agent read DRF API structure and produce accurate frontend integration code (React/Vue/Angular or generic HTTP clients).
  • Enable agent-assisted development by searching endpoints and retrieving example requests/responses and schema types.
  • Document DRF authentication methods and required headers so generated clients can be correct.

Not For

  • Performing real API calls to mutate data (the service is documentation exposure and code generation).
  • Handling runtime API gateway authorization enforcement or serving application data beyond docs.
  • Production remote internet-facing deployment without appropriate network/auth controls (not specified in the README).

Interface

REST API
No
GraphQL
No
gRPC
No
MCP Server
Yes
SDK
No
Webhooks
No

Authentication

Methods: None specified (read-only docs).
OAuth: No Scopes: No

The README focuses on MCP transports (stdio and streamable-http) and states it exposes read-only documentation. It does not describe authentication/authorization controls for the MCP server (especially for the HTTP transport), so security depends on how you deploy and firewall it.

Pricing

Free tier: No
Requires CC: No

Open-source package (MIT). Costs depend on your infrastructure and any AI tooling you run.

Agent Metadata

Pagination
none
Idempotent
False
Retry Guidance
Not documented

Known Gotchas

  • HTTP transport may require external network hardening; README does not document auth/rate limits for the MCP endpoint.
  • The quality of generated examples/types depends on the underlying DRF schema adapter (spectacular/yasg/built-in).
  • If your API schema excludes paths/prefixes, tools/resources will not reflect excluded endpoints.

Alternatives

Full Evaluation Report

Comprehensive deep-dive: security analysis, reliability audit, agent experience review, cost modeling, competitive positioning, and improvement roadmap for drf-mcp-docs.

AI-powered analysis · PDF + markdown · Delivered within 30 minutes

$99

Package Brief

Quick verdict, integration guide, cost projections, gotchas with workarounds, and alternatives comparison.

Delivered within 10 minutes

$3

Score Monitoring

Get alerted when this package's AF, security, or reliability scores change significantly. Stay ahead of regressions.

Continuous monitoring

$3/mo

Scores are editorial opinions as of 2026-03-30.

6533
Packages Evaluated
19870
Need Evaluation
586
Need Re-evaluation
Community Powered