rag-memory-mcp
by MoKarim146
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| HOST | No | Where the server listens. Keep 127.0.0.1 to restrict access to this computer. | 127.0.0.1 |
| PORT | No | The port where the server listens. | 8787 |
| AI_MEMORY_DIR | No | The memory folder containing the markdown notes. | ~/ObsidianVault/AI-Memory |
| MCP_READ_TOKEN | No | Read token used when MCP_AUTH_REQUIRED is true. | |
| RAG_EMBEDDINGS | No | Optional vector search mode: none, ollama (a local model), or ngram. | none |
| MCP_WRITE_TOKEN | No | Write token used when MCP_AUTH_REQUIRED is true. | |
| MCP_AUTH_REQUIRED | No | Set to true to turn on token login using MCP_WRITE_TOKEN and MCP_READ_TOKEN. | false |
| AI_MEMORY_WRITE_REVIEW | No | Which writes wait for review: suspicious, all, or off. | suspicious |
| AI_MEMORY_WRITE_ENABLED | No | Set to false to make the memory read-only. | true |
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