Provides a template for deploying custom MCP tools as stateless servers on Appwrite Functions, supporting environment variables and bearer authentication.
Click on "Install 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 Template add 10 and 20"
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.
Stateless MCP server on Appwrite Functions — JSON-RPC over HTTPS, stdlib only. No SSE, no ASGI stack.
Edit functions/mcp/src/app.py, push with the Appwrite CLI, point your client at the function domain.
claude mcp add --transport http appwrite-mcp-demo https://mcp-example.sgp.appwrite.runOr in Cursor / Claude Desktop mcp.json:
{
"mcpServers": {
"appwrite-mcp-demo": {
"url": "https://mcp-example.sgp.appwrite.run"
}
}
}Demo tools: echo, add.
Related MCP server: Stream MCP
# 1. Point the CLI at your project (global Cloud endpoint — not regional)
appwrite client --endpoint https://cloud.appwrite.io/v1 --project-id <your-project>
# 2. Edit appwrite.config.json → set projectId to yours
# 3. Push
cp functions/mcp/.env.example functions/mcp/.env
appwrite push functions --with-variables
# 4. Domain
appwrite proxy list-rules
# or: appwrite proxy create-function-rule --domain <name>.<region>.appwrite.run --function-id mcp-example
# 5. Smoke-test
./scripts/smoke.sh https://<your-domain>Then add the domain the same way as the demo:
claude mcp add --transport http my-mcp https://<your-domain># functions/mcp/src/app.py
from mcp_lite import MCPServer
server = MCPServer(name="my-mcp", version="0.1.0")
@server.tool(description="Do something useful.")
def my_tool(query: str) -> str:
return f"got: {query}"Type hints become the tool inputSchema. Add a context parameter to read the Appwrite request (headers, dynamic API key). More patterns in examples/.
Do not name the tools module server.py — Open Runtimes already ships a top-level server module.
uv sync
uv run python scripts/dev.py # http://127.0.0.1:8787
./scripts/smoke.sh http://127.0.0.1:8787
uv run pytest -qMode | Env | Client header |
Open (default) |
| none |
Bearer |
|
|
30s hard timeout on domain executions — keep tools under ~25s (MCP_TOOL_TIMEOUT)
No SSE — one JSON response per request (Streamable HTTP JSON mode)
Stateless — no sessions, no progress streaming, no sampling
See docs/design.md and docs/clients.md.
This server cannot be installed
Unclaimed servers have limited discoverability.
If you are the server author, to access and configure the admin panel.
MCP (Model Context Protocol) server for Appwrite
MCP server for AI agents to plan, verify, and deploy Cloudflare-native apps.
Remote MCP server for RunComfy Serverless API (ComfyUI): deployments and async inference.
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/ChiragAgg5k/appwrite-mcp-template'
If you have feedback or need assistance with the MCP directory API, please join our Discord server