Zekra is answering right now. Last checked 14 min ago. Last commit 14 Oct 2026.
Long-term memory and a knowledge graph for AI agents: recall, notes, secrets and data sources.
We read the source, 1 d ago · rules ccca72095570
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.
execFile(file, args, { timeout: timeoutMs, encoding: "utf8" }, (err, stdout, stderr) => {
const has = (rel) => fs.existsSync(path.join(__dirname, rel));
Found in continuous integration, deployment or infrastructure files, or in a neighbouring package of the same monorepo. None of this is installed when you add the server: it describes how the project is built and released. We list it because a leaked key in a build pipeline is still a real problem, but it is not something this server does on your machine.
p = 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.
Endpoint below is the one we actually reach during checks — not the one copied from a README. Last verified 14 min ago.
claude mcp add zekra --transport http https://mcp.zekra.dev
{
"mcpServers": {
"zekra": {
"url": "https://mcp.zekra.dev"
}
}
}
[mcp_servers.zekra]
url = "https://mcp.zekra.dev"
{
"mcpServers": {
"zekra": {
"url": "https://mcp.zekra.dev"
}
}
}
{
"mcpServers": {
"zekra": {
"url": "https://mcp.zekra.dev"
}
}
}
This endpoint answered with an authorization challenge. The server is running, and it signs you in through your browser: there is no API key to paste.
| URL | Transport | State | Latency | Checked |
|---|---|---|---|---|
| https://mcp.zekra.dev | streamable-http | sign-in | 178 ms | 14 min ago |
Local memory engine for AI agents with knowledge graphs, forgetting, and semantic recall
Zero-Trust PII & secrets sanitizer for AI agents with in-memory local redaction.
Zero-knowledge MCP secrets vault for AI agents: secrets injected at runtime, never seen by the model
Agent-first resource directory for AI agents: protocols, security, RAG, memory, evals, and more.
Secure, fragment-based long-term memory for MCP-compatible AI agents.
Git-native project memory for AI coding agents: Markdown source of truth, reviewable, secret-safe.
CVE, KEV, MITRE ATT&CK, CWE and detection graph for AI agents; every link names its source.
Zero-knowledge secrets manager — local crypto-plane MCP server: decrypts and injects secrets.
Answers built from our own checks of this server.