Loading…
Memory database for AI agents: remember and recall over a running Fraise daemon, in FQL.
Fraise is an MCP server entry in ChatHome Skills, sourced from Official MCP Registry and scored 78/100. As a Model Context Protocol server, it exposes tools that MCP-compatible LLM clients such as Claude, Cursor, and Copilot can call directly, extending an agent's reach beyond its built-in capabilities. ChatHome Skills discovered this entry through its daily ingest of official registries and GitHub discovery queries, and re-verifies repository facts, freshness signals, and install metadata on every run. The quality score weighs official-registry presence, a working install command, license clarity, GitHub star trajectory, and repository freshness — the full formula is on the Sources page. The install command above is ready to copy. Review the last-pushed date and repository status before adding Fraise to a production agent workflow; the snapshot facts below are point-in-time values from the most recent ingest.
docker run -i --rm ghcr.io/fraisehq/fraise:0.3.5Review the upstream source before running this command.
{
"_meta": {
"io.modelcontextprotocol.registry/official": {
"status": "active",
"isLatest": true,
"updatedAt": "2026-10-25T20:40:15.570927Z",
"publishedAt": "2026-10-25T20:40:15.570927Z",
"statusChangedAt": "2026-10-25T20:40:15.570927Z"
}
},
"server": {
"name": "io.github.FraiseHQ/fraise",
"title": "Fraise",
"$schema": "https://static.modelcontextprotocol.io/schemas/2025-12-11/server.schema.json",
"version": "0.3.5",
"packages": [
{
"transport": {
"type": "stdio"
},
"identifier": "ghcr.io/fraisehq/fraise:0.3.5",
"runtimeHint": "docker",
"registryType": "oci",
"packageArguments": [
{
"type": "positional",
"value": "mcp",
"valueHint": "subcommand",
"description": "Runs the stdio MCP bridge rather than the daemon the image starts by default."
},
{
"name": "-addr",
"type": "named",
"default": "http://host.docker.internal:9876",
"isRequired": true,
"description": "URL of the running Fraise daemon the bridge forwards to. The daemon runs separately, like a database behind a connection URL: on the host (brew services start fraise, or systemctl --user start fraise), or as its own container with port 9876 published. Inside this container 127.0.0.1 is the bridge itself, so the default names the host."
}
],
"runtimeArguments": [
{
"name": "--add-host",
"type": "named",
"value": "host.docker.internal:host-gateway",
"isRequired": true,
"description": "Resolves host.docker.internal to the host on Linux too, where Docker Desktop is not there to do it."
}
]
}
],
"repository": {
"id": "1207409551",
"url": "https://github.com/FraiseHQ/fraise",
"source": "github"
},
"websiteUrl": "https://docs.getfraise.dev",
"description": "Memory database for AI agents: remember and recall over a running Fraise daemon, in FQL."
}
}