AppwriteSAFE
Appwrite’s MCP server. Operating your backend has never been easier.
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
[](https://registry.modelcontextprotocol.io/?q=io.github.appwrite%2Fmcp)
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 Code
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.
Claude Desktop
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/"]
39cdaa9e5501OBSERVED · 2026-10-07Connect
Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control. Replace the environment placeholders with a token scoped to the least it needs.
claude mcp add mcp-server-appwrite --env APPWRITE_API_KEY=${APPWRITE_API_KEY} --env APPWRITE_OAUTH_ACCESS_TOKEN=${APPWRITE_OAUTH_ACCESS_TOKEN} --env APPWRITE_OAUTH_ORGANIZATION_ID=${APPWRITE_OAUTH_ORGANIZATION_ID} --env APPWRITE_OAUTH_PROJECT_ENDPOINT=${APPWRITE_OAUTH_PROJECT_ENDPOINT} -- uvx mcp-server-appwrite{
"mcpServers": {
"mcp-server-appwrite": {
"command": "uvx",
"args": [
"mcp-server-appwrite"
],
"env": {
"APPWRITE_API_KEY": "${APPWRITE_API_KEY}",
"APPWRITE_OAUTH_ACCESS_TOKEN": "${APPWRITE_OAUTH_ACCESS_TOKEN}",
"APPWRITE_OAUTH_ORGANIZATION_ID": "${APPWRITE_OAUTH_ORGANIZATION_ID}",
"APPWRITE_OAUTH_PROJECT_ENDPOINT": "${APPWRITE_OAUTH_PROJECT_ENDPOINT}"
}
}
}
}Exposed tools (5)
4 read · 1 write · 0 destructive.
| Tool | Risk | Description |
|---|---|---|
appwrite_search_docs | read | Search the Appwrite documentation. |
example_get | read | Get an example. |
storage_get_file_download | read | Download a file. |
storage_update_bucket | write | Update a bucket. |
users_list | read | List users. |
Trust audit
SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | PASS |
| L1 | Static analysis of the code | WARN |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | PASS |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- none-observed
- Network
- declared (5 observation(s))
- Shell
- declared (1 observation(s))
- Dependencies
- pinned
- Secrets in source
- none-found
Findings (9)
module = importlib.import_module(f"appwrite_console.services.{name}")for ip in ("127.0.0.1", "169.254.169.254", "10.0.0.1"):"APPWRITE_ENDPOINT": "http://127.0.0.1:1/v1",
"transaction": "http://10.140.28.8:8000/mcp",
"transaction": "http://10.140.28.8:8000/mcp",
"APPWRITE_ENDPOINT": "http://127.0.0.1:1/v1",
data = base64.b64decode(content)
curl -LsSf https://astral.sh/uv/install.sh | sh
src/mcp_server_appwrite/data/docs_index.npz
Gates applied: no_behavioural_pass.
39cdaa9e5501full audit observations/trust-audit/mcp-server/appwrite__appwrite-1.json · Report an issue / request a re-scanAudit history
Every audit this server has had. A grade with a past is a grade somebody is still checking.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-07 | 39cdaa9e5501 | SAFE | B | 89 | first audit |
Questions
What is the Appwrite MCP server?
Appwrite’s MCP server. Operating your backend has never been easier.
What tools does Appwrite expose?
5 in total: 4 read-only, 1 that write, and 0 that can delete or overwrite. Every one is listed on this page with its risk.
Is Appwrite safe to connect to an agent?
The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean server reads B.
What credentials does Appwrite need?
It reads APPWRITE_API_KEY, APPWRITE_OAUTH_ACCESS_TOKEN, APPWRITE_OAUTH_ORGANIZATION_ID, APPWRITE_OAUTH_PROJECT_ENDPOINT, APPWRITE_OAUTH_PROJECT_ID, MCP_OAUTH_SCOPES and OPENAI_API_KEY from the environment. Give it a token scoped to the least it needs — an agent that can be talked into calling a tool can be talked into calling it with your credentials.
How does Appwrite run?
It speaks stdio and streamable-http, so it runs as a local process your client starts. It is published on PyPI as mcp-server-appwrite.
How current is this page?
The grade is for one exact copy of the source (39cdaa9e5501), read on 2026-10-07. The repository is watched and re-audited when it changes.