MCP Server
MCP
CPersona
Persistent AI memory in one SQLite file: 3-layer hybrid search, confidence scoring, 29 tools.
Install
uvx cpersona
Configuration Example
{
"remotes": [],
"packages": [
{
"registryType": "pypi",
"registryBaseUrl": "https://pypi.org",
"identifier": "cpersona",
"version": "2.5.3",
"runtimeHint": "uvx",
"transport": {
"type": "stdio"
},
"environmentVariables": [
{
"description": "SQLite database path. Defaults to data/cpersona.db, which follows the client's working directory — set it to an absolute path to keep one memory across sessions.",
"default": "data/cpersona.db",
"name": "CPERSONA_DB_PATH"
},
{
"description": "Embedding mode: 'http' to use an embedding server for vector search, 'none' for lexical layers only.",
"default": "none",
"name": "CPERSONA_EMBEDDING_MODE"
},
{
"description": "Embedding server endpoint, e.g. http://127.0.0.1:8401/embed. Required when CPERSONA_EMBEDDING_MODE=http.",
"name": "CPERSONA_EMBEDDING_URL"
},
{
"description": "Recall fusion strategy: 'rrf' (default), 'rsf', or 'cascade'.",
"default": "rrf",
"name": "CPERSONA_RECALL_MODE"
}
]
}
]
}
mcp
model-context-protocol
pypi
By
Comments
Sign in to leave a comment