Appwrite MCP Server
OfficialConnect to Appwrite via MCP and manage Appwrite databases, collections, attributes, indexes, and documents through agent-callable tools.
Create, list, get, update, and delete databases.
Create, list, get, update, and delete collections, including permissions and document-level security settings.
Define and manage collection attributes: boolean, datetime, email, enum, float, integer, IP, relationship, string, and URL, with create/list/get/update/delete operations.
Create, list, get, and delete indexes.
Create, read, list, update, delete, bulk create/update/delete, and upsert documents; increment or decrement numeric document attributes.
Filter/paginate results using Appwrite query strings and search where supported.
Use the hosted server with browser OAuth, or run self-hosted over stdio with an API key; writes can include audit-log reasons, and Cloud environment IDs are supported.
Provides tools to manage Appwrite resources including databases, users, functions, teams, storage, messaging, locale, and avatars through the Appwrite API.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@Appwrite MCP Server list all users in my project"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Appwrite MCP server
A Model Context Protocol server for Appwrite. It exposes Appwrite's API — databases, users, functions, teams, storage, and more — as tools your MCP client can call.
Connect to the hosted server at https://mcp.appwrite.io/ and authenticate
through your browser. The first time you connect, your client opens an Appwrite
consent screen; approve the scopes and you're connected. There are no keys to
copy. The conventional https://mcp.appwrite.io/mcp URL is also supported and
connects to the same server.

Connect your client
Pick your client below. Each adds the hosted Appwrite Cloud server.
claude mcp add --transport http appwrite https://mcp.appwrite.io/Then, inside a Claude Code session, run /mcp, select appwrite, and follow
the browser prompt to authenticate.
Go to Settings → Connectors → Add custom connector and paste
https://mcp.appwrite.io/. Available on Pro and Max plans; on Team and
Enterprise plans only an organization Owner can add custom connectors.
If you don't see that option (free plan, or a Team/Enterprise member), bridge the remote server through stdio instead (requires Node.js). Go to Settings → Developer → Local MCP servers, click Edit Config, and add:
{
"mcpServers": {
"appwrite": {
"command": "npx",
"args": ["-y", "mcp-remote", "https://mcp.appwrite.io/"]
}
}
}Restart Claude Desktop; the server appears under Local MCP servers and a browser window opens to authenticate.

Edit ~/.cursor/mcp.json (global) or .cursor/mcp.json (project).
{
"mcpServers": {
"appwrite": {
"url": "https://mcp.appwrite.io/"
}
}
}Cursor prompts you to log in through the browser; the server then shows up under Settings → MCP with its tools enabled.

Edit .vscode/mcp.json (workspace) or your user configuration via the Command
Palette → MCP: Open User Configuration.
{
"servers": {
"appwrite": {
"type": "http",
"url": "https://mcp.appwrite.io/"
}
}
}Edit ~/.codex/config.toml.
[mcp_servers.appwrite]
url = "https://mcp.appwrite.io/"Then authenticate from the terminal:
codex mcp login appwriteIn the Codex GUI, you can instead add the server from the MCP settings —
set the URL to https://mcp.appwrite.io/ and leave the token and header
fields empty (authentication happens through the browser):

Edit opencode.json (project) or ~/.config/opencode/opencode.json (global).
{
"$schema": "https://opencode.ai/config.json",
"mcp": {
"appwrite": {
"type": "remote",
"url": "https://mcp.appwrite.io/",
"enabled": true
}
}
}Edit ~/.codeium/windsurf/mcp_config.json.
{
"mcpServers": {
"appwrite": {
"serverUrl": "https://mcp.appwrite.io/"
}
}
}gemini mcp add --transport http appwrite https://mcp.appwrite.io/Or edit ~/.gemini/settings.json (note the key is httpUrl, not url):
{
"mcpServers": {
"appwrite": {
"httpUrl": "https://mcp.appwrite.io/"
}
}
}Gemini CLI opens the browser OAuth flow automatically on first connect. To
re-authenticate, run /mcp auth appwrite inside a session.
Edit ~/.gemini/config/mcp_config.json (global) or .agents/mcp_config.json (project workspace).
{
"mcpServers": {
"appwrite": {
"serverUrl": "https://mcp.appwrite.io/"
}
}
}⚠️ Note: Antigravity strictly requires the
serverUrlkey for remote transport. Using legacy fields likeurlorhttpUrlwill cause tool registration to fail silently.
Antigravity opens the browser OAuth flow automatically on first connect. If you manually edit the JSON file, navigate to Settings → Customizations → Installed MCP Servers and click Refresh to reload the tool definitions.
copilot mcp add --transport http appwrite https://mcp.appwrite.io/Or run /mcp add inside a session, or edit ~/.copilot/mcp-config.json:
{
"mcpServers": {
"appwrite": {
"type": "http",
"url": "https://mcp.appwrite.io/"
}
}
}A browser window opens to authenticate on first connect. Check status with
/mcp.
Go to Settings → AI → MCP Servers → Add Server → Add Remote Server, or add
to your settings.json (zed: open settings):
{
"context_servers": {
"appwrite": {
"url": "https://mcp.appwrite.io/"
}
}
}Zed prompts you to authenticate through the browser on first connect.
Go to Settings → Agents → MCP servers → + Add, choose the URL-based
server type, and enter https://mcp.appwrite.io/.
Warp opens a browser window to authenticate on first connect.
JetBrains IDEs don't yet support OAuth for remote MCP servers, so bridge through stdio (requires Node.js). Go to Settings → Tools → AI Assistant → Model Context Protocol (MCP) → Add, switch to the JSON view, and paste:
{
"mcpServers": {
"appwrite": {
"command": "npx",
"args": ["-y", "mcp-remote", "https://mcp.appwrite.io/"]
}
}
}A browser window opens to authenticate on first connect.
Cline doesn't yet support OAuth for remote MCP servers, so bridge through stdio (requires Node.js). In the Cline panel, open the MCP Servers icon → Configure tab → Configure MCP Servers, and add:
{
"mcpServers": {
"appwrite": {
"command": "npx",
"args": ["-y", "mcp-remote", "https://mcp.appwrite.io/"]
}
}
}A browser window opens to authenticate on first connect.
Related MCP server: MCP Toolkit
Reasons and environments
Every write the agent makes carries a short reason (why it made the change).
Appwrite records it on the project's audit log, so you can review what your
agent changed, and why, in the project's Activity tab.
On Appwrite Cloud, the agent can act in a project's environments (for example
staging): appwrite_get_context lists them, and each call takes the
environment's ID as environment_id next to the project's project_id. See
Tool surface.
Self-hosted Appwrite
Running your own Appwrite instance? Run the MCP server locally over stdio and
authenticate with a project API key. See docs/self-hosted.md
for per-client setup.
Documentation
Tool surface — the tools exposed to the model and the internal Appwrite catalog.
How Cloud authentication works — the OAuth 2.1 flow.
Documentation search — the in-process
appwrite_search_docstool and how to rebuild its index.Events — MCP Events: webhook subscriptions to changes in your Appwrite project (in development, not available yet).
Self-hosted Appwrite — run the server locally with a project API key.
Local development — running, testing, and debugging the server locally.
AGENTS.md — full contributor guide and pre-PR checklist.
License
This MCP server is licensed under the MIT License. See the LICENSE file for details.
Available Tools
49 toolsdatabases_createC
Create a new Database.
Inputs: database_id (required), name (required), enabled.
databases_create_boolean_attributeC
Create a boolean attribute.
Inputs: database_id (required), collection_id (required), key (required), required (required), +2 more.
databases_create_collectionB
Create a new Collection. Before using this route, you should create a new database resource using either a server integration API or directly from your database console.
Inputs: database_id (required), collection_id (required), name (required), permissions, +2 more.
databases_create_datetime_attributeC
Create a date time attribute according to the ISO 8601 standard.
Inputs: database_id (required), collection_id (required), key (required), required (required), +2 more.
databases_create_documentB
Create a new Document. Before using this route, you should create a new collection resource using either a server integration API or directly from your database console.
Inputs: database_id (required), collection_id (required), document_id (required), data (required), +1 more.
databases_create_documentsC
WARNING: Experimental Feature - This endpoint is experimental and not yet officially supported. It may be subject to breaking changes or removal in future versions.
Inputs: database_id (required), collection_id (required), documents (required).
databases_create_email_attributeC
Create an email attribute.
Inputs: database_id (required), collection_id (required), key (required), required (required), +2 more.
databases_create_enum_attributeC
Create an enumeration attribute. The elements param acts as a white-list of accepted values for this attribute.
Inputs: database_id (required), collection_id (required), key (required), elements (required), +3 more.
databases_create_float_attributeC
Create a float attribute. Optionally, minimum and maximum values can be provided.
Inputs: database_id (required), collection_id (required), key (required), required (required), +4 more.
databases_create_indexC
Creates an index on the attributes listed. Your index should include all the attributes you will query in a single request.
Inputs: database_id (required), collection_id (required), key (required), type (required), +3 more.
databases_create_integer_attributeC
Create an integer attribute. Optionally, minimum and maximum values can be provided.
Inputs: database_id (required), collection_id (required), key (required), required (required), +4 more.
databases_create_ip_attributeC
Create IP address attribute.
Inputs: database_id (required), collection_id (required), key (required), required (required), +2 more.
databases_create_relationship_attributeC
Create relationship attribute. Learn more about relationship attributes.
Inputs: database_id (required), collection_id (required), related_collection_id (required), type (required), +4 more.
databases_create_string_attributeC
Create a string attribute.
Inputs: database_id (required), collection_id (required), key (required), size (required), +4 more.
databases_create_url_attributeC
Create a URL attribute.
Inputs: database_id (required), collection_id (required), key (required), required (required), +2 more.
databases_decrement_document_attributeC
Decrement a specific attribute of a document by a given value.
Inputs: database_id (required), collection_id (required), document_id (required), attribute (required), +2 more.
databases_deleteA
Delete a database by its unique ID. Only API keys with with databases.write scope can delete a database.
Inputs: database_id (required).
databases_delete_attributeC
Deletes an attribute.
Inputs: database_id (required), collection_id (required), key (required).
databases_delete_collectionA
Delete a collection by its unique ID. Only users with write permissions have access to delete this resource.
Inputs: database_id (required), collection_id (required).
databases_delete_documentC
Delete a document by its unique ID.
Inputs: database_id (required), collection_id (required), document_id (required).
databases_delete_documentsC
WARNING: Experimental Feature - This endpoint is experimental and not yet officially supported. It may be subject to breaking changes or removal in future versions.
Inputs: database_id (required), collection_id (required), queries.
databases_delete_indexC
Delete an index.
Inputs: database_id (required), collection_id (required), key (required).
databases_getB
Get a database by its unique ID. This endpoint response returns a JSON object with the database metadata.
Inputs: database_id (required).
databases_get_attributeC
Get attribute by ID.
Inputs: database_id (required), collection_id (required), key (required).
databases_get_collectionC
Get a collection by its unique ID. This endpoint response returns a JSON object with the collection metadata.
Inputs: database_id (required), collection_id (required).
databases_get_documentB
Get a document by its unique ID. This endpoint response returns a JSON object with the document data.
Inputs: database_id (required), collection_id (required), document_id (required), queries.
databases_get_indexC
Get index by ID.
Inputs: database_id (required), collection_id (required), key (required).
databases_increment_document_attributeC
Increment a specific attribute of a document by a given value.
Inputs: database_id (required), collection_id (required), document_id (required), attribute (required), +2 more.
databases_listB
Get a list of all databases from the current Appwrite project. You can use the search parameter to filter your results.
Inputs: queries, search.
databases_list_attributesC
List attributes in the collection.
Inputs: database_id (required), collection_id (required), queries.
databases_list_collectionsB
Get a list of all collections that belong to the provided databaseId. You can use the search parameter to filter your results.
Inputs: database_id (required), queries, search.
databases_list_documentsC
Get a list of all the user's documents in a given collection. You can use the query params to filter your results.
Inputs: database_id (required), collection_id (required), queries.
databases_list_indexesC
List indexes in the collection.
Inputs: database_id (required), collection_id (required), queries.
databases_updateC
Update a database by its unique ID.
Inputs: database_id (required), name (required), enabled.
databases_update_boolean_attributeB
Update a boolean attribute. Changing the default value will not update already existing documents.
Inputs: database_id (required), collection_id (required), key (required), required (required), +2 more.
databases_update_collectionC
Update a collection by its unique ID.
Inputs: database_id (required), collection_id (required), name (required), permissions, +2 more.
databases_update_datetime_attributeC
Update a date time attribute. Changing the default value will not update already existing documents.
Inputs: database_id (required), collection_id (required), key (required), required (required), +2 more.
databases_update_documentC
Update a document by its unique ID. Using the patch method you can pass only specific fields that will get updated.
Inputs: database_id (required), collection_id (required), document_id (required), data, +1 more.
databases_update_documentsD
WARNING: Experimental Feature - This endpoint is experimental and not yet officially supported. It may be subject to breaking changes or removal in future versions.
Inputs: database_id (required), collection_id (required), data, queries.
databases_update_email_attributeB
Update an email attribute. Changing the default value will not update already existing documents.
Inputs: database_id (required), collection_id (required), key (required), required (required), +2 more.
databases_update_enum_attributeB
Update an enum attribute. Changing the default value will not update already existing documents.
Inputs: database_id (required), collection_id (required), key (required), elements (required), +3 more.
databases_update_float_attributeC
Update a float attribute. Changing the default value will not update already existing documents.
Inputs: database_id (required), collection_id (required), key (required), required (required), +4 more.
databases_update_integer_attributeC
Update an integer attribute. Changing the default value will not update already existing documents.
Inputs: database_id (required), collection_id (required), key (required), required (required), +4 more.
databases_update_ip_attributeC
Update an ip attribute. Changing the default value will not update already existing documents.
Inputs: database_id (required), collection_id (required), key (required), required (required), +2 more.
databases_update_relationship_attributeC
Update relationship attribute. Learn more about relationship attributes.
Inputs: database_id (required), collection_id (required), key (required), on_delete, +1 more.
databases_update_string_attributeB
Update a string attribute. Changing the default value will not update already existing documents.
Inputs: database_id (required), collection_id (required), key (required), required (required), +3 more.
databases_update_url_attributeC
Update an url attribute. Changing the default value will not update already existing documents.
Inputs: database_id (required), collection_id (required), key (required), required (required), +2 more.
databases_upsert_documentD
WARNING: Experimental Feature - This endpoint is experimental and not yet officially supported. It may be subject to breaking changes or removal in future versions.
Inputs: database_id (required), collection_id (required), document_id (required), data (required), +1 more.
databases_upsert_documentsD
WARNING: Experimental Feature - This endpoint is experimental and not yet officially supported. It may be subject to breaking changes or removal in future versions.
Inputs: database_id (required), collection_id (required), documents (required).
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 49 tools
Tools are well-organized by resource type (databases, collections, documents, attributes) and action (create, get, list, update, delete), with clear distinctions. Some potential overlap exists between single and batch operations (e.g., create_document vs. create_documents), but descriptions clarify these as separate endpoints, and attribute types are clearly differentiated by data type.
Naming follows a highly consistent pattern throughout: all tools use snake_case with a 'databases_' prefix, followed by a verb (create, get, list, update, delete, increment, decrement) and a noun (database, collection, document, attribute, index). This predictability makes it easy for agents to understand and select tools based on naming conventions alone.
With 49 tools, the count is excessive for a single server, making it overwhelming for agents to navigate. While the tools cover a comprehensive database management domain, the sheer volume could lead to confusion and inefficiency, as many tools are highly specific (e.g., separate tools for each attribute type like boolean, email, string).
The tool set provides complete CRUD/lifecycle coverage for Appwrite databases, including resources (databases, collections, documents, attributes, indexes) and operations (create, read, update, delete, list, increment/decrement). It even includes experimental batch operations and relationship attributes, leaving no obvious gaps for database management tasks.
Maintenance
Related MCP Connectors
A comprehensive Model Context Protocol (MCP) server that enables AI assistants to interact with yo…
Model Context Protocol server for the Apideck Unified API. Connect any MCP-compatible agent framework to 100+ accounting systems, HRIS platforms, file storage providers, and more through one integration. More information https://www.apideck.com/mcp-server
A Model Context Protocol server for Wix AI tools
The Mercado Pago MCP Server implements the Model Context Protocol to provide AI agents and LLMs with access to Mercado Pago's APIs and tools within compatible development environments. It acts as an intermediary that translates Mercado Pago resources into executable functions (tools) that AI applications can invoke to perform actions and automate flows. The server simplifies integration, enables using documentation to implement or improve code, and optimizes operations through natural language interactions without manual implementations.
Related MCP Servers
- AlicenseNot gradedqualityAmaintenanceA Model Context Protocol server that enables AI assistants to interact with Coolify instances through natural language, allowing management of servers, applications, databases, and deployments.3,354 npm628MIT
- FlicenseNot gradedqualityDmaintenanceA comprehensive Model Context Protocol server implementation that enables AI assistants to interact with file systems, databases, GitHub repositories, web resources, and system tools while maintaining security and control.2-
- AlicenseNot gradedqualityDmaintenanceA Model Context Protocol server that allows AI tools to connect to and interact with your Directus API, enabling automated access to collections, items, and user data.27MIT
- AlicenseAqualityDmaintenanceA Model Context Protocol server providing tools for DB queries, API calls, file I/O, and text transformations, enabling AI agents like Claude to perform real-world actions.10MIT