openmessage
by MaxGhenis
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| OPENMESSAGES_HOST | No | Host/interface to bind the local web server to | 127.0.0.1 |
| OPENMESSAGES_PORT | No | Web UI port | 7007 |
| OPENMESSAGES_MY_NAME | No | Display name for outgoing imported iMessage/WhatsApp messages | system user name |
| OPENMESSAGES_DATA_DIR | No | Data directory (DB + session) | ~/.local/share/openmessage |
| OPENMESSAGE_TELEMETRY | No | Set to 1 to send one anonymous heartbeat per launch | unset (off) |
| OPENMESSAGES_LOG_LEVEL | No | Log level (debug/info/warn/error/trace) | info |
| OPENMESSAGES_EXPORT_DIR | No | Directory for generate_viz / render_story HTML outputs and photo inputs | ~/Documents/OpenMessage |
| OPENMESSAGES_KLIPY_API_KEY | No | Optional Klipy API key for the web compose GIF picker. KLIPY_API_KEY is also accepted as a fallback. | |
| OPENMESSAGES_SIGNAL_TMP_SWEEP | No | Set to 0 to disable the cleanup of stale signal-cli temp directories | enabled |
| OPENMESSAGES_STARTUP_BACKFILL | No | Startup history sync mode: auto, shallow, deep, or off | auto |
| OPENMESSAGES_MACOS_NOTIFICATIONS | No | Enable/disable native macOS notifications for fresh inbound live messages (1/0) | |
| OPENMESSAGES_ALLOW_ANY_EXPORT_PATH | No | Set to 1/true/yes/on to allow viz/story tools to read photos from, or write HTML to, arbitrary local paths. | unset (off) |
| OPENMESSAGES_BACKFILL_DISCOVER_ORPHANS | No | Opt in to deep backfill's Phase C (contact-based orphan discovery). Off by default because it creates an empty SMS thread on your phone for each contact without prior message history. Enable with 1/true/yes/on only if you understand the side effect. | 0 |
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 | |
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/MaxGhenis/openmessage'
If you have feedback or need assistance with the MCP directory API, please join our Discord server