CPersona runs on your own machine — the client starts it, so there is no endpoint to ping. 5 030 installs a week from pypi. Last commit 2 Nov 2026.
Persistent AI memory in one SQLite file: 3-layer hybrid search, confidence scoring, 29 tools.
We read the source, 5 h ago · rules 995398eba69f
What this server is able to do. For an MCP server this is often the job itself — a terminal server runs commands because that is what it is for. Listed so you know what you are plugging in, not as an accusation.
git_dir = os.path.join(repo_dir, git_dir)
done = subprocess.run(
close.innerHTML = CROSS;
Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.
We found places where it runs commands, builds paths or queries from values it is given. None of that is a flaw by itself — it becomes one when the code changes, and code changes quietly between releases. We re-read it on every one.
This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.
claude mcp add cpersona -- uvx cpersona
{
"mcpServers": {
"cpersona": {
"command": "uvx",
"args": [
"cpersona"
]
}
}
}
[mcp_servers.cpersona]
command = "uvx"
args = ["cpersona"]
{
"mcpServers": {
"cpersona": {
"command": "uvx",
"args": [
"cpersona"
]
}
}
}
{
"servers": {
"cpersona": {
"type": "stdio",
"command": "uvx",
"args": [
"cpersona"
]
}
}
}
Optional settings from the registry entry, left out of the block above:
CPERSONA_DB_PATH (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), CPERSONA_EMBEDDING_MODE (Embedding mode: 'http' to use an embedding server for vector search, 'none' for lexical layers only), CPERSONA_EMBEDDING_URL (Embedding server endpoint, e.g. http://127.0.0.1:8401/embed. Required when CPERSONA_EMBEDDING_MODE=http), CPERSONA_RECALL_MODE (Recall fusion strategy: 'rrf' (default), 'rsf', or 'cascade').
Lightweight persistent memory for AI agents. Hybrid search. 16 tools. One SQLite file.
Persistent memory for AI coding agents. Local-first SQLite + vector search. 17 MCP tools.
Persistent, zero-dependency AI memory using SQLite. Local-first, cross-tool portable.
Persistent, verified, cross-session memory for AI agents. 26 tools. SQLite + sync.
Persistent, verified, cross-session memory for AI agents. 26 tools. SQLite + sync.
Persistent local memory for MCP-compatible AI coding agents, stored per repository in SQLite.
Bi-temporal, provenance-carrying long-term memory for AI agents, in one SQLite file.
Persistent layered memory for AI agents. SQLite FTS5, fact versioning, zero-cloud.
Answers built from our own checks of this server.