Skip to main content
Glama
WAHA MCP OAuth Bridge

WAHA MCP OAuth Bridge

by Meir553

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
DATA_DIRNoWhere the password hash, keys, and approvals are stored. Init uses ./data../data
MCP_PATHNoLeave this alone./mcp
NODE_ENVNoLeave this alone.production
LOG_LEVELNoinfo is enough. Logs leave out passwords, keys, and tokens.info
LISTEN_HOSTNoUse 127.0.0.1 when Caddy is in front.127.0.0.1
LISTEN_PORTYesThe local port you picked. It does not have to be 443.8787
MAX_STREAMSNoHow many live streams it will hold open at once.8
CODE_TTL_SECNoHow long a login code stays valid.120
TLS_KEY_FILENoStay empty behind Caddy. Fill in only if this program itself serves HTTPS.
PUBLIC_ORIGINYesThe https address Caddy serves, such as https://mcp.example.com.
TLS_CERT_FILENoStay empty behind Caddy. Fill in only if this program itself serves HTTPS.
ACCESS_TTL_SECNoHow long an access token stays valid.900
CIMD_CACHE_SECNoHow long ChatGPT's client description is remembered.300
LOGIN_LOCK_SECNoHow long the lock lasts.900
STREAM_IDLE_MSNoHow long a quiet stream may stay open.120000
BODY_TIMEOUT_MSNoHow long to wait while reading a request.30000
REFRESH_TTL_SECNoHow long a connector can keep renewing access, from the day you approved it.2592000
LOGIN_WINDOW_SECNoThe period those wrong passwords are counted in.900
ORIGIN_ALLOWLISTNoBrowsers allowed to call this program. Init includes your public address and https://chatgpt.com.
SESSION_IDLE_SECNoHow long you can sit idle on the login page.900
TOKEN_WINDOW_SECNoThe length of that window.60
UPSTREAM_API_KEYNoOptional. The first key already lives in data/upstream-secret.json. Leave the environment variable empty. If you set both, they must be the same key.
UPSTREAM_MCP_URLYesThe first WAHA address, usually http://127.0.0.1:3000/mcp. The path is /mcp.
HEADER_TIMEOUT_MSNoHow long to wait for WAHA to start answering.10000
MAX_REQUEST_BYTESNoLargest request this program accepts.1048576
CONNECT_TIMEOUT_MSNoHow long to wait while connecting to WAHA.5000
LOGIN_MAX_FAILURESNoWrong passwords before the login page locks.5
STREAM_LIFETIME_MSNoHow long any stream may stay open.1800000
AUTH_REQUEST_TTL_SECNoHow long ChatGPT's approval request stays valid.600
SESSION_ABSOLUTE_SECNoHow long a browser login lasts in total.28800
TOKEN_MAX_PER_WINDOWNoHow many token requests are allowed in one window.60
ALLOW_PUBLIC_UPSTREAMNoLeave false. Set true only if a WAHA is on a public address.false
UPSTREAM_DISPLAY_NAMENoThe words shown on the approval page for the first WhatsApp.
ENABLE_LOCAL_TEST_HTTPNoLeave this alone.false
UPSTREAM_API_KEY_HEADERNoLeave this as X-Api-Key unless that WAHA expects a different header.X-Api-Key

Instructions

Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.

This server publishes no instructions, or was last inspected before Glama recorded them.

Capabilities

Server capabilities have not been inspected yet.

Tools

Functions exposed to the LLM to take actions

NameDescription

No tools

Prompts

Interactive templates invoked by user choice

NameDescription

No prompts

Resources

Contextual data attached and managed by the client

NameDescription

No resources