Memex runs on your own machine — the client starts it, so there is no endpoint to ping. 361 installs a week from npm. Last commit 28 Oct 2026.
Temporal engineering context for agents via MCP.
What the code does
We read the source, 5 d ago · rules 995398eba69f
Things with no honest explanation: a promise that contradicts the code, code that runs at install time while hiding what it does, data leaving the machine.
memex-mcp похож на memdex-mcp
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.
const fullPath = vscode.Uri.file(path.join(workspaceFolders[0].uri.fsPath, filePath));
uv_ver = subprocess.check_output([uv_cmd, "--version"]).decode().strip()
execSync(`${cmd} --version`, { stdio: 'ignore' });
env = dict(os.environ)
Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.
We found things in this code
Code changes quietly between releases, and nobody reads the diff of a dependency. We do, on every release — watch Memex and you get told the day something new turns up.
Connect this server
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 memex -e 'NEO4J_URI=<NEO4J_URI>' -e 'NEO4J_USER=<NEO4J_USER>' -e 'NEO4J_PASSWORD=<NEO4J_PASSWORD>' -e 'GEMINI_API_KEY=<GEMINI_API_KEY>' -- uvx memex-mcp{
"mcpServers": {
"memex": {
"command": "uvx",
"args": [
"memex-mcp"
],
"env": {
"GEMINI_API_KEY": "<GEMINI_API_KEY>",
"NEO4J_PASSWORD": "<NEO4J_PASSWORD>",
"NEO4J_URI": "<NEO4J_URI>",
"NEO4J_USER": "<NEO4J_USER>"
}
}
}
}[mcp_servers.memex]
command = "uvx"
args = ["memex-mcp"]
env = { NEO4J_URI = "<NEO4J_URI>", NEO4J_USER = "<NEO4J_USER>", NEO4J_PASSWORD = "<NEO4J_PASSWORD>", GEMINI_API_KEY = "<GEMINI_API_KEY>" }{
"mcpServers": {
"memex": {
"command": "uvx",
"args": [
"memex-mcp"
],
"env": {
"GEMINI_API_KEY": "<GEMINI_API_KEY>",
"NEO4J_PASSWORD": "<NEO4J_PASSWORD>",
"NEO4J_URI": "<NEO4J_URI>",
"NEO4J_USER": "<NEO4J_USER>"
}
}
}
}{
"servers": {
"memex": {
"type": "stdio",
"command": "uvx",
"args": [
"memex-mcp"
],
"env": {
"GEMINI_API_KEY": "<GEMINI_API_KEY>",
"NEO4J_PASSWORD": "<NEO4J_PASSWORD>",
"NEO4J_URI": "<NEO4J_URI>",
"NEO4J_USER": "<NEO4J_USER>"
}
}
}
}Put your own values in place of
<NEO4J_URI> (Bolt URI of your Neo4j instance), <NEO4J_USER> (Neo4j username), <NEO4J_PASSWORD> (Neo4j password), <GEMINI_API_KEY> (Google Gemini API key for entity extraction).
The author’s registry entry marks them as required.
Alternatives to Memex
same job, measured the same wayMemory, docs, and repo context layer for engineering agents.
Local context and engineering evidence for AI coding agents.
Context Assurance for AI agents: context engineering, AI cost optimization, verification.
Local-first persistent context memory MCP server for AI coding agents.
Context engineering for AI coding agents: product context, project missions, and 360 memory.
Append-only event log for cross-agent context/memory sharing via 3 MCP tools.
Deterministic temporal and business-date arithmetic for AI agents via MCP.
Free context-engineering audits for AI agents. BYOK Anthropic key. Top-3 findings per scan.
Memex — questions
Answers built from our own checks of this server.