CCCMemory MCP
by xiaolai
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| OPENAI_API_KEY | No | OpenAI API key (required if using OpenAI embedding provider). | |
| CCCMEMORY_DB_MODE | No | Database mode: 'global' (default) or 'per-project'. | global |
| CCCMEMORY_DB_PATH | No | Explicit path to the CCCMemory database file (overrides default). | |
| CCCMEMORY_CHUNK_SIZE | No | Target chunk size in tokens. | 450 |
| CCCMEMORY_CHUNK_OVERLAP | No | Overlap between chunks (0-1). | 0.1 |
| CCCMEMORY_RERANK_WEIGHT | No | Vector weight in re-ranking (FTS gets 1-weight). | 0.7 |
| CCCMEMORY_RERANK_ENABLED | No | Enable hybrid re-ranking (vector + FTS). | true |
| CCCMEMORY_QUERY_EXPANSION | No | Enable synonym expansion for queries. | false |
| CCCMEMORY_CHUNKING_ENABLED | No | Enable smart chunking for long messages. | 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
ActivityInactive
ResponsivenessSyncing