WAHA MCP OAuth Bridge
by Meir553
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| DATA_DIR | No | Where the password hash, keys, and approvals are stored. Init uses ./data. | ./data |
| MCP_PATH | No | Leave this alone. | /mcp |
| NODE_ENV | No | Leave this alone. | production |
| LOG_LEVEL | No | info is enough. Logs leave out passwords, keys, and tokens. | info |
| LISTEN_HOST | No | Use 127.0.0.1 when Caddy is in front. | 127.0.0.1 |
| LISTEN_PORT | Yes | The local port you picked. It does not have to be 443. | 8787 |
| MAX_STREAMS | No | How many live streams it will hold open at once. | 8 |
| CODE_TTL_SEC | No | How long a login code stays valid. | 120 |
| TLS_KEY_FILE | No | Stay empty behind Caddy. Fill in only if this program itself serves HTTPS. | |
| PUBLIC_ORIGIN | Yes | The https address Caddy serves, such as https://mcp.example.com. | |
| TLS_CERT_FILE | No | Stay empty behind Caddy. Fill in only if this program itself serves HTTPS. | |
| ACCESS_TTL_SEC | No | How long an access token stays valid. | 900 |
| CIMD_CACHE_SEC | No | How long ChatGPT's client description is remembered. | 300 |
| LOGIN_LOCK_SEC | No | How long the lock lasts. | 900 |
| STREAM_IDLE_MS | No | How long a quiet stream may stay open. | 120000 |
| BODY_TIMEOUT_MS | No | How long to wait while reading a request. | 30000 |
| REFRESH_TTL_SEC | No | How long a connector can keep renewing access, from the day you approved it. | 2592000 |
| LOGIN_WINDOW_SEC | No | The period those wrong passwords are counted in. | 900 |
| ORIGIN_ALLOWLIST | No | Browsers allowed to call this program. Init includes your public address and https://chatgpt.com. | |
| SESSION_IDLE_SEC | No | How long you can sit idle on the login page. | 900 |
| TOKEN_WINDOW_SEC | No | The length of that window. | 60 |
| UPSTREAM_API_KEY | No | Optional. 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_URL | Yes | The first WAHA address, usually http://127.0.0.1:3000/mcp. The path is /mcp. | |
| HEADER_TIMEOUT_MS | No | How long to wait for WAHA to start answering. | 10000 |
| MAX_REQUEST_BYTES | No | Largest request this program accepts. | 1048576 |
| CONNECT_TIMEOUT_MS | No | How long to wait while connecting to WAHA. | 5000 |
| LOGIN_MAX_FAILURES | No | Wrong passwords before the login page locks. | 5 |
| STREAM_LIFETIME_MS | No | How long any stream may stay open. | 1800000 |
| AUTH_REQUEST_TTL_SEC | No | How long ChatGPT's approval request stays valid. | 600 |
| SESSION_ABSOLUTE_SEC | No | How long a browser login lasts in total. | 28800 |
| TOKEN_MAX_PER_WINDOW | No | How many token requests are allowed in one window. | 60 |
| ALLOW_PUBLIC_UPSTREAM | No | Leave false. Set true only if a WAHA is on a public address. | false |
| UPSTREAM_DISPLAY_NAME | No | The words shown on the approval page for the first WhatsApp. | |
| ENABLE_LOCAL_TEST_HTTP | No | Leave this alone. | false |
| UPSTREAM_API_KEY_HEADER | No | Leave 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
| Name | Description |
|---|---|
No tools | |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
This server cannot be deployed
Maintenance
ActivityMaintained
ResponsivenessNo recent community issues