RLM Memory MCP Server
by jumpino27
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| UI_PORT | No | Port for the web UI. | 3848 |
| LLM_MODEL | No | Model name for the AI provider. | google/gemini-3.5-flash (OpenRouter) / gemini-3.5-flash (direct) |
| LLM_PROVIDER | No | AI provider: auto, openrouter, or gemini. Auto prefers OpenRouter if key is set. | auto |
| RLM_DATA_DIR | No | Directory where project memories are stored. | <install dir>/projects |
| GEMINI_API_KEY | No | Google Gemini API key. Get one at https://aistudio.google.com/ | |
| LLM_MAX_TOKENS | No | Maximum output tokens per LLM call. | 4096 |
| LLM_TIMEOUT_MS | No | Per-request timeout in milliseconds. | 60000 |
| OPENROUTER_API_KEY | No | OpenRouter API key (recommended). Get one at https://openrouter.ai/keys | |
| LLM_REASONING_EFFORT | No | Thinking depth for helper calls: minimal, low, medium, high. | low |
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
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/jumpino27/RLM-Memory-MCP-Server'
If you have feedback or need assistance with the MCP directory API, please join our Discord server