factstore
A fact store for AI agents, on Postgres: registered attributes, every write citing its evidence.
Install
Add this to your client's MCP configuration (Claude Desktop: claude_desktop_config.json; Cursor: .cursor/mcp.json; VS Code and others use the same "mcpServers" shape).
factstoreclaude mcp add factstore -e 'FACTSTORE_DSN=<your factstore_dsn>' -e 'FACTSTORE_EXCISE_DSN=<your factstore_excise_dsn>' -- uvx factstore==0.1.0 mcp
{
"mcpServers": {
"factstore": {
"command": "uvx",
"args": [
"factstore==0.1.0",
"mcp"
],
"env": {
"FACTSTORE_DSN": "<your factstore_dsn>",
"FACTSTORE_EXCISE_DSN": "<your factstore_excise_dsn>"
}
}
}
}
Environment variables
FACTSTORE_DSNrequired secret The credential `factstore actor STORE NAME` prints: a Postgres connection string for one actor of one store.FACTSTORE_EXCISE_DSNsecret An excision credential (`factstore actor --excise`). Only then is the excise tool listed.
Documentation
From the project's README on GitHub, refreshed weekly. Links open on GitHub.
Contents
factstore
A fact store for AI agents, on Postgres. Agents record what a company's systems and documents say as facts: a value for a registered attribute, in a transaction stamped with who wrote it and the document it came from. Nothing is overwritten, so the store can say what it knew on any date.
Skills that ship with it index a company's systems from their exports, and read documents and mail into facts. They leave people's personal details in the source. MIT-licensed.
Install
pip install factstore
In Claude Code, the plugin brings the MCP server and the skills:
/plugin marketplace add Victor-EU/factstore
/plugin install factstore@factstore
factstore/README.md walks through Postgres, a first store and connecting an agent.
What's here
factstore/ | The kernel, the MCP server, the Python SDK and the CLI |
packages/ | Vocabulary packages: core, and ecom-ops and ecom-index for an online brand |
factstore-skills/ | The catalogue, ontology and ingestion skills |
evals/ | What it was tested on: a synthetic brand, and five public datasets from real companies |
factstore-design.md | The design, and what testing changed in it |
factstore-build-plan.md | The milestones, and where each stands |
Status
0.1.0, alpha. The kernel's code held unchanged through every test, up to 3.2 million facts in one store. The skills passed every round on public data: product lists, a million order lines, a marketplace's duplicate customers, 100 suppliers' forms and a trader's mailbox. No company has run it on its own data yet.
Frequently asked questions
What is factstore?
A fact store for AI agents, on Postgres: registered attributes, every write citing its evidence.
How do I install factstore?
It runs on your machine. In Claude Code: claude mcp add factstore -e 'FACTSTORE_DSN=<your factstore_dsn>' -e 'FACTSTORE_EXCISE_DSN=<your factstore_excise_dsn>' -- uvx factstore==0.1.0 mcp. For other clients, paste the JSON configuration from this page into their MCP settings.
Does factstore need an API key?
Yes. It expects FACTSTORE_DSN, FACTSTORE_EXCISE_DSN, which you set in its configuration.
Is factstore open source?
Yes. Its code is on GitHub under the MIT license.
Who maintains factstore?
It is published by Victor-EU. AI.tn lists it but does not maintain or endorse it.
From the official MCP Registry. Listing is not an endorsement: review a server's code and permissions before giving it access to your data.