appium-mcp-auth
Authentication and authorization plugin for appium-mcp, adding bearer API keys, OAuth JWT, session tokens, scope-based authorization, rate limiting, and per-session ownership when running over SSE/HTTP Stream.
README
appium-mcp-auth
Authentication & authorization for appium-mcp when hosted over SSE / HTTP Stream ā built entirely on the appium-mcp Plugin API (no core changes).
When you expose appium-mcp over SSE, anyone who can reach the port gets a full
Appium session and can drive real devices. appium-mcp-auth adds a security
layer as a drop-in plugin:
- š Bearer API keys (
ak_<id>_<secret>) ā hashed at rest, constant-time compared. For machines / CI. - šŖŖ OAuth JWT access tokens ā validated against the issuer JWKS (
iss/aud/exp). For humans / IDE clients. - š« Session tokens ā exchange an API key for a short-lived token via
auth_login. - š Scope-based authorization ā per-tool required scopes, admin-role bypass.
- š§āš¤āš§ Per-caller session ownership ā callers only see/drive the Appium sessions they created (multi-tenant isolation).
- š¦ Rate limiting & session quotas ā per subject.
How it works (read this first)
A plugin runs inside appium-mcp's beforeCall / afterCall hooks and cannot
read HTTP headers ā so the credential is passed as a tool argument
(default authToken). Authentication and authorization both happen in
beforeCall; a denied call is short-circuited before the tool runs.
tool call āāāŗ beforeCall(ctx)
1. authenticate ctx.args.authToken ā Identity (apiKey | sessionToken | oauth)
2. rate-limit per subject
3. authorize tool vs Identity.scopes (admin role bypasses)
4. ownership: any sessionId arg must be owned by the caller
5. session-creating tool? enforce per-subject session quota
allow ā tool runs | deny ā error result (tool never runs)
āāāŗ afterCall: bind new sessions to caller, release deleted ones
Implications (by design):
- Terminate TLS in front of the server ā the credential travels in the request body.
- No OAuth
.well-knowndiscovery endpoints (a plugin can't serve them); front with a gateway if your MCP client needs auto-negotiation. This package still validates JWTs. - Calls that omit
sessionIdhit Appium's global active session ā in multi-tenant mode, require an ownedsessionIdon every call.
Install
npm install @appclaw/appium-mcp-auth
That's it ā appium-mcp (which brings fastmcp and zod) and jose for JWT
validation come along automatically as regular dependencies. The plugin
resolves the exact fastmcp/zod copies that appium-mcp uses at runtime, so
there is no peer-dependency juggling.
Requires Node.js ā„ 20.
Implement it in your project
There are two ways to use it. Pick one.
Option 1 ā Turnkey CLI (fastest)
Run this package's binary instead of appium-mcp's. It is the full
appium-mcp SSE server with the auth plugin composed in ā one process, same
/sse endpoint.
# 1. Configure at least one credential (see "Configuration" below)
export APPIUM_MCP_AUTH_API_KEYS='[{"id":"ci","secret":"CHANGE-ME","subject":"ci-bot","scopes":["appium:use"]}]'
# 2. Start the auth-protected SSE server
npx @appclaw/appium-mcp-auth --httpStream --port=8080 --endpoint=/sse
# ā SSE listening on http://localhost:8080/sse
Option 2 ā Compose the plugin into your own server (most control)
If you already build a custom appium-mcp server, just add the plugin. No core
changes required ā createAppiumMcpServer already accepts plugins.
import { createAppiumMcpServer } from 'appium-mcp/core';
import { createAuthPluginFromEnv } from '@appclaw/appium-mcp-auth';
const server = await createAppiumMcpServer({
plugins: [createAuthPluginFromEnv()], // reads APPIUM_MCP_AUTH_* env vars
});
await server.start({
transportType: 'httpStream',
httpStream: { endpoint: '/sse', port: 8080 },
});
Prefer explicit config over environment variables? Build the config yourself:
import { createAppiumMcpServer } from 'appium-mcp/core';
import { createAuthPlugin, sha256Hex, type AuthConfig } from '@appclaw/appium-mcp-auth';
const config: AuthConfig = {
credentialArg: 'authToken',
publicTools: ['auth_login'],
apiKeys: [
{
id: 'ci',
hash: sha256Hex('CHANGE-ME'), // store the hash, not the secret
subject: 'ci-bot',
kind: 'service',
scopes: ['appium:use'],
},
],
toolScopes: { mobile_clear_app: ['appium:admin'] },
defaultScopes: ['appium:use'],
adminRole: 'admin',
sessionTokenTtlMs: 3_600_000,
rateLimit: { limit: 120, windowMs: 60_000 },
maxSessionsPerSubject: 3,
enforceOwnership: true,
sessionIdArgs: ['sessionId'],
sessionCreatingTools: ['appium_session_management'],
audit: true,
};
const server = await createAppiumMcpServer({
plugins: [createAuthPlugin(config)],
});
How clients authenticate
Whatever the MCP client, the credential is supplied as the authToken
argument on tool calls.
-
Exchange an API key for a session token (the
auth_logintool is public):{ "tool": "auth_login", "arguments": { "apiKey": "ak_ci_CHANGE-ME" } } ā { "sessionToken": "st_ā¦", "expiresAt": "ā¦" } -
Pass the token (or the API key, or an OAuth JWT) as
authTokenon every subsequent call:{ "tool": "appium_session_management", "arguments": { "action": "create", "authToken": "st_ā¦" } } { "tool": "appium_gesture", "arguments": { "sessionId": "ā¦", "authToken": "st_ā¦" } } -
auth_whoamiechoes the caller identity;auth_logoutrevokes a session token.
Will my MCP client work?
| Client behavior | Works? | How |
|---|---|---|
Sends an Authorization: Bearer header (Cursor, Claude Desktop, most SSE clients) |
ā | Run gateway mode (below) ā it reads the header and injects the credential. No per-call argument needed. |
| Forwards agent-chosen tool arguments verbatim (e.g. AppClaw) | ā | Pass the token as the authToken argument (shown above). |
| Injects a fixed argument on every tool call | ā | Set authToken deterministically instead of relying on the LLM. |
Tip: for LLM-driven clients, prefer a session token (
auth_login) over the raw API key so the long-lived secret isn't repeated in every prompt/trace.
Header auth for Cursor / Claude Desktop (gateway mode)
A plugin can't read HTTP headers, so header-based clients are served by a
built-in credential-injecting reverse proxy. It reads the Authorization
header, rewrites each tools/call to add the authToken argument, and forwards
to the appium-mcp server on loopback. Nothing in appium-mcp core changes.
Cursor āā(Authorization: Bearer ak_ā¦)āāāŗ gateway (public :8080) āāāŗ appium-mcp + plugin (127.0.0.1:8790)
reads header, beforeCall sees authToken,
injects authToken arg authorizes exactly as normal
Start it:
export APPIUM_MCP_AUTH_API_KEYS='[{"id":"dev","secret":"CHANGE-ME","subject":"dev","kind":"user","roles":["admin"],"scopes":["appium:use","appium:admin"]}]'
npx @appclaw/appium-mcp-auth --gateway --port=8080 --endpoint=/sse
# gateway (header auth) on http://localhost:8080/sse
# upstream on http://127.0.0.1:8790/sse (loopback ā firewall this port)
Point Cursor at it ā .cursor/mcp.json (project) or ~/.cursor/mcp.json (global):
{
"mcpServers": {
"appium-auth": {
"url": "http://localhost:8080/sse",
"headers": {
"Authorization": "Bearer ak_dev_CHANGE-ME"
}
}
}
}
Claude Desktop connects via the mcp-remote bridge:
{
"mcpServers": {
"appium-auth": {
"command": "npx",
"args": [
"-y", "mcp-remote", "http://localhost:8080/sse",
"--header", "Authorization: Bearer ak_dev_CHANGE-ME"
]
}
}
}
The Bearer value is any accepted credential: an API key (ak_ā¦), a session
token from auth_login (st_ā¦), or an OAuth JWT. Requests with no/invalid
credential get 401. GET /health is always allowed for probes.
Gateway options: --port (public), --upstream-port (loopback inner server),
--endpoint; APPIUM_MCP_AUTH_GATEWAY_HEADER changes which header is read
(default authorization).
Security: put TLS in front (the token is in a header) and firewall the upstream port ā the inner server trusts the injected
authToken, so it must only be reachable through the gateway.
Configuration
All settings are environment variables (used by createAuthPluginFromEnv and the
CLI). Full examples in .env.example.
| Variable | Purpose | Default |
|---|---|---|
APPIUM_MCP_AUTH_API_KEYS |
JSON array of API-key records (id, hash or secret, subject, kind, scopes, roles?, expiresAt?) |
ā |
APPIUM_MCP_AUTH_OAUTH |
JSON OAuth JWT validation config (issuer, audience, jwksUri?, scopeClaim?, rolesClaim?) |
ā |
APPIUM_MCP_AUTH_ARG |
Tool-argument name carrying the credential | authToken |
APPIUM_MCP_AUTH_PUBLIC_TOOLS |
Comma list of tools that skip auth | auth_login |
APPIUM_MCP_AUTH_TOOL_SCOPES |
JSON map `tool ā scope | scope[]` |
APPIUM_MCP_AUTH_DEFAULT_SCOPES |
Scopes required for unlisted tools | appium:use |
APPIUM_MCP_AUTH_ADMIN_ROLE |
Role that bypasses scope checks | admin |
APPIUM_MCP_AUTH_SESSION_TTL_MS |
Session-token lifetime | 3600000 |
APPIUM_MCP_AUTH_RATE_LIMIT |
"<limit>/<windowMs>" per subject |
disabled |
APPIUM_MCP_AUTH_MAX_SESSIONS |
Per-subject Appium session cap (0 = off) | 0 |
APPIUM_MCP_AUTH_ENFORCE_OWNERSHIP |
Enforce session ownership | true |
APPIUM_MCP_AUTH_SESSION_ID_ARGS |
Arg names carrying a session id | sessionId |
APPIUM_MCP_AUTH_SESSION_TOOLS |
Tools that create sessions | appium_session_management |
APPIUM_MCP_AUTH_AUDIT |
Emit JSON audit lines to stderr | true |
If neither API keys nor OAuth are configured, every protected call is denied and the server logs a warning at startup.
Create an API key (built-in command)
Use the keygen command ā it prints the client bearer token and the
server config record (which stores the hash, never the secret):
npx @appclaw/appium-mcp-auth keygen --id=ci --subject=ci-bot --scopes=appium:use
Give this to the CLIENT (Authorization header) ā shown once, store it securely:
Authorization: Bearer ak_ci_Tgaz5NSbOTqgz3A4s_CdPeV7FePHLExS
Add this record to APPIUM_MCP_AUTH_API_KEYS on the SERVER (stores the hash, not the secret):
{"id":"ci","hash":"c65cā¦","subject":"ci-bot","kind":"service","scopes":["appium:use"]}
Flags: --id --subject [--scopes=a,b] [--kind=service|user] [--roles=admin]
[--name="ā¦"] [--expires-in=30d] [--secret=ā¦] [--json].
The three strings are linked: the client presents ak_<id>_<secret>; the server
stores hash = SHA256(secret); on each call it checks
SHA256(presented secret) === stored hash (constant-time). The plaintext secret
never leaves the client, and the --json form is handy for scripting/rotation.
Authorization model
- Scopes ā each tool requires a scope set (
APPIUM_MCP_AUTH_TOOL_SCOPES), falling back toAPPIUM_MCP_AUTH_DEFAULT_SCOPES. A caller needs all of them. - Admin role ā a caller with the
adminrole bypasses scope checks. - Ownership ā sessions a caller creates are bound to its
subject; a call referencing someone else's trackedsessionIdis denied (not_session_owner). Untracked ids (pre-existing / attach flows) pass through. - Quota / rate limit ā per subject, via
MAX_SESSIONSandRATE_LIMIT.
Public API
import {
AppiumAuthPlugin, // the plugin class
createAuthPlugin, // build from an AuthConfig
createAuthPluginFromEnv, // build from environment
buildAuthenticatedServer, // full server (used by the CLI)
loadConfig, sha256Hex, // config helpers
// building blocks: Authenticator, Authorizer, KeyStore, OAuthValidator,
// OwnershipRegistry, RateLimiter, AuditLog
} from '@appclaw/appium-mcp-auth';
Security notes
- Store API-key hashes, never plaintext secrets, in committed config.
- Give services and humans distinct scopes so a leaked CI key can't act as a human.
- Pin OAuth
issuerandaudienceso tokens minted for other apps are rejected. - Rate limiter and ownership map are process-local ā front with a shared store (e.g. Redis) if you run multiple SSE replicas.
- Credentials are never written to audit logs.
Development
npm install
npm run typecheck # tsc --noEmit
npm test # node:test via tsx (35 tests)
npm run build # emit dist/
License
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.
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.
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.
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.
E2B
Using MCP to run code via e2b.