Lex runs on your own machine — the client starts it, so there is no endpoint to ping. 211 installs a week from npm. Last commit 17 Sep 2026.
Episodic memory and architectural policy for AI agents. Frames, Atlas, and Policy.
Every tool that appeared, vanished or quietly changed what it asks for. Recorded since 8 September 2026. No other catalogue keeps this.
We read the source, 7 d 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.
этот файл ставится пользователю, но в репозитории его нет
пакет @smartergpt/lex-mcp ссылается на guffawaffle/lex-mcp
DROP POLICY IF EXISTS lex_behavioral_runtime_scope ON ${relation};
let resolvedPath = path.join(currentDir, importPath);
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 lex -- npx -y @smartergpt/lex-mcp
{
"mcpServers": {
"lex": {
"args": [
"-y",
"@smartergpt/lex-mcp"
],
"command": "npx"
}
}
}
[mcp_servers.lex]
command = "npx"
args = ["-y", "@smartergpt/lex-mcp"]
{
"mcpServers": {
"lex": {
"args": [
"-y",
"@smartergpt/lex-mcp"
],
"command": "npx"
}
}
}
{
"mcpServers": {
"lex": {
"args": [
"-y",
"@smartergpt/lex-mcp"
],
"command": "npx"
}
}
}
This one needs environment variables set before it will start:
LEX_WORKSPACE_ROOT (Root directory for the workspace. Defaults to current working directory.), LEX_MEMORY_DB (Path to SQLite database file. Defaults to .smartergpt/lex/lex.db in workspace root.), LEX_DEBUG (Set to any value to enable debug logging to stderr.).
The author declared them in the registry entry; get the values from the project itself.
Episodic memory, Frames, Policy Neighborhoods, and policy enforcement for AI agents.
Universal memory runtime for AI agents — episodic, semantic, and procedural memory.
Long-term memory for AI agents: semantic facts, episodic events, and procedural workflows
Collective episodic memory for AI coding agents — search, deposit, comment, showcase builds.
ADR drift detection, content safety, and decision memory for architectural decisions
AI Agent with Architectural Memory. Impact analysis (free), tests and code from the graph (pro).
Persistent local memory for coding agents: temporal knowledge graph, procedural and episodic recall
Embedded memory for AI agents with SQLite, pgvector, and Neo4j graph search.
Answers built from our own checks of this server.