Provena Agent Memory runs on your own machine — the client starts it, so there is no endpoint to ping. Last commit 22 Sep 2026.
Evidence-backed, explainable persistent memory for MCP-compatible AI agents.
Today is the operative word: we check Provena Agent Memory 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 provena-memory -- uvx provena-agent-memory
{
"mcpServers": {
"provena-memory": {
"args": [
"provena-agent-memory"
],
"command": "uvx"
}
}
}
[mcp_servers.provena-memory]
command = "uvx"
args = ["provena-agent-memory"]
{
"mcpServers": {
"provena-memory": {
"args": [
"provena-agent-memory"
],
"command": "uvx"
}
}
}
{
"mcpServers": {
"provena-memory": {
"args": [
"provena-agent-memory"
],
"command": "uvx"
}
}
}
This one needs environment variables set before it will start:
PROVENA_API_URL (Base URL of the Provena REST API), PROVENA_API_KEY (Agent credential issued by the Provena service), PROVENA_SCOPE_ID (Exact project or branch scope used for memory).
The author declared them in the registry entry; get the values from the project itself.
Persistent, governed local memory for MCP-compatible AI clients.
Open-source causal memory for AI agents: persistent, explainable, MCP-native memory (13 tools).
Persistent graph-backed conversational memory for AI agents.
Persistent memory for AI coding tools. 11 tools for any MCP-compatible AI tool.
Persistent, evidence-backed code graph for coding agents.
MCP server for persistent, searchable memory for AI agents.
Persistent memory for MCP-compatible agents: memory bank, fact cortex, dreams, graph.
Sovereign Agent OS — Persistent Memory, Governance & Compliance for AI Agents.
Answers built from our own checks of this server.