Mahran MCP
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| OLLAMA_URL | No | URL of the local Ollama server. | http://localhost:11434 |
| GEMINI_MODEL | No | Gemini model to use. Change to an available model from gemini_list_models. | gemini-3.1-flash-lite |
| MAHRAN_MODEL | No | Default Ollama model for the local server. | qwen2.5:7b |
| GEMINI_API_KEY | No | User-supplied Gemini API key. If not set, the key is read from ~/.gemini_mcp/config.json. | |
| MAHRAN_CODE_MODEL | No | Ollama model used for the code router lane. Defaults to the same value as MAHRAN_MODEL. | qwen2.5:7b |
| GEMINI_IMAGE_MODEL | No | Gemini image model to use. Requires an account/model that supports image generation. | gemini-3.1-flash-image |
| MAHRAN_CYBER_MODEL | No | Ollama model used for the cyber router lane. Defaults to the same value as MAHRAN_MODEL. | qwen2.5:7b |
| MAHRAN_PERSONA_FILE | No | Optional path to your own plain-text system prompt file. | |
| MAHRAN_GENERAL_MODEL | No | Ollama model used for the general router lane. Defaults to the same value as MAHRAN_MODEL. | qwen2.5:7b |
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 issues