Lore Context runs on your own machine — the client starts it, so there is no endpoint to ping. 24 installs a week from npm. Last commit 23 May 2026.
Governed AI-agent memory, Evidence Ledger traces, evals, and portable context tools.
We read the source, 19 h ago · rules 3dff92dd89df
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.
result = subprocess.run(cmd, capture_output=True, text=True, check=False)
const out = execSync(`git diff --name-only ${since} HEAD`, {
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 lore-context-mcp -- npx -y @lore-context/server
{
"mcpServers": {
"lore-context-mcp": {
"args": [
"-y",
"@lore-context/server"
],
"command": "npx"
}
}
}
[mcp_servers.lore-context-mcp]
command = "npx"
args = ["-y", "@lore-context/server"]
{
"mcpServers": {
"lore-context-mcp": {
"args": [
"-y",
"@lore-context/server"
],
"command": "npx"
}
}
}
{
"mcpServers": {
"lore-context-mcp": {
"args": [
"-y",
"@lore-context/server"
],
"command": "npx"
}
}
}
This one needs environment variables set before it will start:
LORE_API_URL (Base URL of the Lore API that the MCP server should proxy tool calls to.), LORE_API_KEY (Optional Lore API key when the API is configured to require authentication.), LORE_MCP_TRANSPORT (MCP stdio transport implementation. Use sdk unless debugging legacy JSON-RPC mode.).
The author declared them in the registry entry; get the values from the project itself.
Append-only event log for cross-agent context/memory sharing via 3 MCP tools.
Model inventory and governance: trace deployed models and their dependencies as an append-only log
Persistent memory for AI agents — log and recall conversation context over MCP.
Self-hosted, source-traceable memory layer and MCP server for AI agents, on your own Postgres.
Verifiable cognition: prove a session ledger is tamper-evident; audit & import any agent's logs.
Governed access to production AI-agent traces in an existing ClickHouse store.
Evidence-traced codebase understanding and security scanning for AI agents over MCP.
Detect stale source context and retain traceable code-chain understanding for AI coding agents.
Answers built from our own checks of this server.