About Django Admin MCP
django-admin-mcp is a Django app that exposes ModelAdmin classes to MCP clients through a single mixin. It reuses Django's permissions, validation and change history, so it suits Django projects that want agents to work with data under existing access rules.
Key features
- 01Generates CRUD tools from existing ModelAdmin classes
- 02Reuses Django permission checks and full_clean validation
- 03Registered admin actions become callable tools
- 04Writes recorded in Django LogEntry history
- 05Hides sensitive fields with mcp_fields settings
- 06Tokens scoped to their linked user's permissions
Use cases
- 01Letting an agent query and update Django admin records
- 02Running existing bulk admin actions such as publishing or CSV export
- 03Giving agents an auditable entry point for data changes
MCP support
The package serves an MCP endpoint over HTTP with tools for model CRUD, admin actions, relationship traversal and history, plus read-only resources at models:// and data:// URIs.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
uvx django-admin-mcphostHostname of your Django deployment that mounts django_admin_mcp.urls (e.g. admin.example.com)Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.
Tools
Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.
Details
From the project READMEdjango-admin-mcp
Add a mixin to your ModelAdmin and MCP clients get CRUD, admin actions and relationship traversal, inside Django's existing permissions. Only Django and Pydantic as dependencies.
One mixin, the request's path through the admin, a token, a conversation with the agent, then getting started. 50 seconds · 1080p · 60 fps · original soundtrack. Watch the film.
Why not just give the agent database access?
A database connection hands the agent raw tables. The Django admin is where your project already encodes who may touch what, how records are validated, and what the sanctioned bulk operations are. This package puts the agent behind that layer instead of around it:
- Permissions — every call goes through
ModelAdmin.has_*_permission(). A token can only do what its linked user can do, and starts with no access until you grant it. - Validation — writes run
full_clean()and yoursave_model()/save_related()hooks, so the agent cannot save a record the admin form would reject. - Audit history — every create, update, delete and action is written to Django's
LogEntryunder the token's user. You can see what the agent changed, and the agent can read the history too. - Admin actions — "publish", "refund", "export CSV" and your other registered actions become tools, including two-step confirmation flows. The agent uses the operations you designed rather than inventing SQL.
- Scoped exposure —
mcp_fields/mcp_exclude_fieldskeep password hashes and secrets out of the agent's view;get_queryset()still limits which rows it can see.
How it compares
A generic Django MCP server or a hand-rolled FastMCP wrapper asks you to define tools, schemas and permission checks yourself, one function at a time. This package reads the ModelAdmin classes you already maintain and generates the tools from them, so field choices, querysets, validation, actions and permissions stay in one place and the agent inherits every change you make to the admin. It also ships as a plain Django app with no MCP SDK or extra HTTP stack.
Installation
pip install django-admin-mcp
# settings.py
INSTALLED_APPS = [
'django_admin_mcp',
# ...
]
# urls.py
urlpatterns = [
path('mcp/', include('django_admin_mcp.urls')),
# ...
]
python manage.py migrate django_admin_mcp
Quick start
1. Expose a model. Set mcp_expose = True to generate tools for it. Models with the mixin but without the flag are discoverable through find_models only.
from django.contrib import admin
from django_admin_mcp import MCPAdminMixin
from .models import Article, Author
@admin.register(Article)
class ArticleAdmin(MCPAdminMixin, admin.ModelAdmin):
mcp_expose = True # list_article, get_article, create_article, ...
mcp_exclude_fields = ['internal_notes']
list_display = ['title', 'author', 'published']
@admin.register(Author)
class AuthorAdmin(MCPAdminMixin, admin.ModelAdmin):
pass # discoverable, no direct tools
2. Create a token in the admin at /admin/django_admin_mcp/mcptoken/. Grant it exactly the permissions and groups the agent needs. The linked user caps what the token can do and is the identity its changes are logged under.
3. Point your MCP client at it, for example in a .mcp.json for Claude Code:
{
"mcpServers": {
"django-admin": {
"type": "http",
"url": "http://localhost:8000/mcp/",
"headers": { "Authorization": "Bearer YOUR_TOKEN" }
}
}
}
4. Ask the agent.
User: Show me the latest 10 articles
Agent: [calls list_article with limit=10]
User: Mark articles 1, 2 and 3 as published
Agent: [calls action_article with action="mark_as_published", ids=[1, 2, 3]]
User: What changed on article 42?
Agent: [calls history_article with id=42]
Tools
For each exposed model (here Article) the server generates:
| Tool | Does |
|---|---|
list_article, get_article | Read with pagination and filtering (needs view) |
create_article, update_article, delete_article | Write single records (needs add / change / delete) |
bulk_article | Create, update or delete many records at once |
actions_article, action_article | List and run registered admin actions, including file-returning exports |
describe_article | Field definitions, types and constraints |
related_article | Follow foreign keys and reverse relations |
history_article | Django admin change history |
autocomplete_article | Search suggestions for foreign-key fields |
Plus find_models to discover everything exposed, MCP prompts for common workflows, and read-only resources at models:// and data:// URIs. The endpoint speaks JSON-RPC 2.0 over HTTP with GET /mcp/health/ for health checks. Full reference in the docs.
Security in brief
- Tokens look like
mcp_<key>.<secret>; only a salted hash of the secret is stored. - Each token carries its own permissions and groups, intersected with its user's permissions. Deactivating the user disables its tokens.
- Expiry is configurable; revoke a token by deactivating or deleting it in the admin.
- Sensitive values are redacted from log messages, and large action downloads are capped by
MCP_ACTION_MAX_FILE_BYTES(default 5 MiB).
See Permissions and Token Management for details.
Requirements
Python 3.10 to 3.14, Django 3.2 to 6.0, Pydantic 2. Tested against every Django release in that range.
Support the project
If this saved you time, a star on GitHub helps others find it. Issues and PRs are welcome; see the contributing guide.
License
MIT
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.
