lightrag-memory-mcp
by p-belov
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| LIGHTRAG_URL | No | LightRAG server address | http://localhost:9621 |
| LIGHTRAG_API_KEY | No | API key, if your server has auth enabled (sent as X-API-Key) | |
| LIGHTRAG_MCP_LANG | No | Language of tool descriptions and responses: en or ru | en |
| LIGHTRAG_SEARCH_MODE | No | Default search mode: mix, hybrid, local, global, naive | mix |
| LIGHTRAG_ANSWER_TIMEOUT | No | Timeout for memory_answer, seconds | 180 |
| LIGHTRAG_SEARCH_TIMEOUT | No | Seconds to wait for the primary mode before falling back to naive | 20 |
| LIGHTRAG_MAX_RESULT_CHARS | No | Character budget for one memory_search result | 16000 |
| LIGHTRAG_MCP_INSTRUCTIONS | No | Describes your memory to the agent, for example which projects it covers | generic text |
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