Appwrite MCP Template
Enables deploying stateless MCP servers on Appwrite Functions, supporting custom tools with JSON-RPC over HTTPS.
README
Appwrite Hosted MCP Template
Stateless MCP server on Appwrite Functions — official Python SDK (mcp==2.0.0), JSON-RPC over HTTPS. No SSE sessions.
Edit functions/mcp/src/app.py, push with the Appwrite CLI, point your client at the function domain.

Try the demo
claude mcp add --transport http appwrite-mcp-demo https://mcp-example.sgp.appwrite.run
Or in Cursor / Claude Desktop mcp.json:
{
"mcpServers": {
"appwrite-mcp-demo": {
"url": "https://mcp-example.sgp.appwrite.run"
}
}
}
Demo tools: echo, add.
Deploy your own
# 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>
Write a tool
# functions/mcp/src/app.py
from mcp.server.mcpserver 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 (and return annotations become outputSchema). Add a ctx: Context parameter to read inbound HTTP headers (including Appwrite's dynamic API key):
from mcp.server.mcpserver import Context
@server.tool(description="...")
def whoami(ctx: Context) -> dict:
return {"api_key": (ctx.headers or {}).get("x-appwrite-key")}
More patterns in examples/.
Do not name the tools module server.py — Open Runtimes already ships a top-level server module.
Local development
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 -q
Auth
| Mode | Env | Client header |
|---|---|---|
| Open (default) | MCP_AUTH_MODE=none |
none |
| Bearer | MCP_AUTH_MODE=bearer + MCP_AUTH_TOKEN=... |
Authorization: Bearer ... |
Limits
- 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.
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.