MCP & AI Agent Integration

Appwrite
automation.

28 AI agent actions for Appwrite — callable from any MCP-compatible runtime, Claude, Cursor, or Cerebral OS workflow. Use Appwrite to manage databases, trigger deployments, and automate developer workflows. Full governance, audit trail, and dry-run safety on every execution.

No credit card required
Live in production environments
<200ms median execution
Dry-run before production
Execution trace
live
28
actions
100%
governed
<200ms
latency
28
AI agent actions
15
Read operations
13
Write operations
4
High-risk actions (approval gated)
Developer Tools Appwrite is a Developer Tools integration — use it to automate database operations, deployments, and dev workflows from any AI agent or MCP-compatible runtime.
Actions

What you can do
with Appwrite.

Every action below is available as an MCP tool and a verb in Cerebral OS — callable from any AI agent, Claude, Cursor, Windsurf, or your own runtime via the BYOA API. All executions are governed, audited, and dry-run safe.

Get Bucket
appwrite:get_bucket
Fetch a single storage bucket by ID with configuration and permissions.
Read Low risk
Get Collection
appwrite:get_collection
Fetch a single collection by ID with attributes and indexes.
Read Low risk
Get Database
appwrite:get_database
Fetch a single database by ID with metadata and configuration.
Read Low risk
Get Document
appwrite:get_document
Fetch a single document by ID with all its data.
Read Low risk
Get File
appwrite:get_file
Fetch file metadata by ID including size, type, and upload information.
Read Low risk
Get Function
appwrite:get_function
Fetch a single function by ID with configuration and runtime information.
Read Low risk
Get User
appwrite:get_user
Fetch a single user by ID with profile information and preferences.
Read Low risk
List Buckets
appwrite:list_buckets
List all storage buckets in the project with optional search and pagination.
Read Low risk
List Collections
appwrite:list_collections
List all collections in a database with optional search and pagination.
Read Low risk
List Databases
appwrite:list_databases
List all databases in the project with optional search and pagination.
Read Low risk
List Documents
appwrite:list_documents
List documents in a collection with optional queries and pagination.
Read Low risk
List Executions
appwrite:list_executions
List function executions with status and results.
Read Low risk
List Files
appwrite:list_files
List all files in a storage bucket with optional search and pagination.
Read Low risk
List Functions
appwrite:list_functions
List all functions in the project with optional search and pagination.
Read Low risk
List Users
appwrite:list_users
List users with optional search and pagination.
Read Low risk
Create Bucket
appwrite:create_bucket
Create a new storage bucket for file uploads.
Write Medium risk
Create Collection
appwrite:create_collection
Create a new collection in a database.
Write Medium risk
Create Database
appwrite:create_database
Create a new database in the project.
Write Medium risk
Create Document
appwrite:create_document
Create a new document in a collection with custom data.
Write Medium risk
Create User
appwrite:create_user
Create a new user account with email and optional profile information.
Write Medium risk
Delete Database
appwrite:delete_database
Permanently delete a database and all its collections and documents.
Write High risk
Delete Document
appwrite:delete_document
Permanently delete a document from a collection.
Write High risk
Delete File
appwrite:delete_file
Permanently delete a file from storage.
Write High risk
Delete User
appwrite:delete_user
Permanently delete a user account and all associated data.
Write High risk
Execute Function
appwrite:execute_function
Execute a function with optional input data and get the result.
Write Medium risk
Update Database
appwrite:update_database
Update an existing database's name and settings.
Write Medium risk
Update Document
appwrite:update_document
Update an existing document with new data and/or permissions.
Write Medium risk
Update User
appwrite:update_user
Update an existing user's profile information.
Write Medium risk
MCP & Runtime API

Call Appwrite
from any AI agent.

Any AI agent — Claude, Cursor, LangChain, AutoGen, or your own — can call Appwrite actions through the Cerebral OS Runtime API. Governance, credentials, and audit trail fire automatically.

appwrite:get_bucket READ
# Call via Runtime API
curl
-X POST \
  "https://api.cerebralos.com/v1/runtime/actions/run"
  -H "X-API-Key: YOUR_KEY" \
  -d '{
    "verb": "appwrite:get_bucket",
    "args": {},
    "execution_id": "agent-001"
  }'
appwrite:create_bucket WRITE
# Dry-run first — no production risk
curl
-X POST \
  "https://api.cerebralos.com/v1/runtime/actions/run"
  -H "X-API-Key: YOUR_KEY" \
  -d '{
    "verb": "appwrite:create_bucket",
    "args": {},
    "execution_id": "agent-001",
    "metadata": {"dryRun": true}
  }'
Get your Runtime API key at app.cerebralos.com/signup — 1,000 free executions, no credit card required.
AI agent examples

What your AI agent
can do with Appwrite.

Real patterns your AI agent can execute via MCP or the Runtime API. Every action governed, dry-run safe, and fully audited.

Trigger
AI agent needs Appwrite data
Call appwrite:get_bucket via MCP or Runtime API
AI processes result and takes next action
Full execution logged to audit trail automatically
Trigger
Workflow needs to write to Appwrite
Dry-run validates appwrite:create_bucket before execution
Approval gate fires if risk level is high
Action executes with full governance — logged, audited, reversible
Trigger
Event in Appwrite
Process with AI agent
Take governed action
Log to audit trail
How it works

Every Appwrite action
governed end-to-end.

Cerebral OS isn't a connector. It's the execution layer that sits in front of Appwrite — adding governance, dry-run safety, and a full audit trail to every operation.

Governance first
Every verb carries a risk classification. High-risk writes require explicit approval gates before they execute in production.
Dry-run safe
Simulate any Appwrite action before it touches production. See exactly what would happen before a single real call is made.
Immutable audit trail
Every Appwrite action is logged — what ran, what changed, who approved it, when it happened. Full history on every verb, forever.
Connect with

Appwrite works best
alongside these.

Build multi-step workflows that connect Appwrite to the rest of your stack. All governed. All audited.

Appwrite integration

Start free.
No credit card required.

Start free with 1,000 runs — no credit card required. Connect Appwrite in minutes, dry-run every action before it touches production, full audit trail on everything.

Start free — 1,000 runs Browse all integrations →