LinkLore runs on your own machine — the client starts it, so there is no endpoint to ping. 122 installs a week from pypi. Last commit 6 Aug 2026.
AI-native structured memory for agents (MCP). Built for agents, not humans.
We read the source, 20 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.
exec(compile(FILEMATCH_SOURCE, "<filematch:match_file>", "exec"), globals())
subprocess.run(
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 llre -- uvx llre
{
"mcpServers": {
"llre": {
"args": [
"llre"
],
"command": "uvx"
}
}
}
[mcp_servers.llre]
command = "uvx"
args = ["llre"]
{
"mcpServers": {
"llre": {
"args": [
"llre"
],
"command": "uvx"
}
}
}
{
"mcpServers": {
"llre": {
"args": [
"llre"
],
"command": "uvx"
}
}
}
This one needs environment variables set before it will start:
LINKLORE_LANG (UI/message language for LinkLore tool output. Supported: en, ko. Leave unset to auto-detect from the OS locale (falls back to en).).
The author declared them in the registry entry; get the values from the project itself.
Live data grids for AI agents. Push structured data; humans review, agents read back via MCP.
Tre — shared memory kanban for humans and agents (MCP Streamable HTTP).
Graph-native memory for AI agents: a knowledge graph built from conversation, via MCP.
Hierarchical markdown memory palace for AI agents — structured palace navigation via MCP tools.
Hierarchical markdown memory palace for AI agents — structured palace navigation via MCP tools.
MCP-native Trust Infrastructure for AI Agents. Persistent encrypted memory with Trust Quotient.
Structured session journals for AI agents. Persistent memory across sessions.
Generate 18 diagram types from structured JSON natively. Built for LLMs and agents.
Answers built from our own checks of this server.