factstore runs on your own machine — the client starts it, so there is no endpoint to ping. 136 installs a week from pypi. Last commit 4 Oct 2026.
A fact store for AI agents, on Postgres: registered attributes, every write citing its evidence.
We read the source, 6 d ago · rules ccca72095570
Found in continuous integration, deployment or infrastructure files, or in a neighbouring package of the same monorepo. None of this is installed when you add the server: it describes how the project is built and released. We list it because a leaked key in a build pipeline is still a real problem, but it is not something this server does on your machine.
attrs, log = pickle.loads(path.read_bytes())
Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.
Today is the operative word: we check factstore every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.
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 factstore -- uvx factstore
{
"mcpServers": {
"factstore": {
"args": [
"factstore"
],
"command": "uvx"
}
}
}
[mcp_servers.factstore]
command = "uvx"
args = ["factstore"]
{
"mcpServers": {
"factstore": {
"args": [
"factstore"
],
"command": "uvx"
}
}
}
{
"mcpServers": {
"factstore": {
"args": [
"factstore"
],
"command": "uvx"
}
}
}
This one needs environment variables set before it will start:
FACTSTORE_DSN (The credential `factstore actor STORE NAME` prints: a Postgres connection string for one actor of one store.), FACTSTORE_EXCISE_DSN (An excision credential (`factstore actor --excise`). Only then is the excise tool listed.).
The author declared them in the registry entry; get the values from the project itself.
Shared memory for AI agents, as a graph in your own Postgres. Writes never call an LLM.
Read-only MCP server for evidence-based PostgreSQL performance auditing.
Durable memory for AI agents: fact extraction, hybrid retrieval, temporal graph. SQLite/Postgres.
Persistent local memory for MCP-compatible AI coding agents, stored per repository in SQLite.
Persistent layered memory for AI agents. SQLite FTS5, fact versioning, zero-cloud.
PostgreSQL security for AI agents: CVEs, yanked releases, exploits, and upgrade paths
Read-only MongoDB for AI agents — find, aggregate (no write stages), count, stats.
PostgreSQL-backed virtual filesystem for agents: session isolation, shared stores, POSIX ops, RLS.
Answers built from our own checks of this server.