Khwan MCP Server

by khwan Your server? Claim it

answering

Khwan is answering right now. Last checked 6 min ago. 4 272 installs a week from pypi. Last commit 27 Aug 2026.

Durable AI memory: recall distilled facts in a later session or subagent, and remember new ones.

Installs per day peak 1 417 · avg 179 · +454% w/w

a month agotoday

Uptime history 6 days of history

6 days agonow

100.0%

Uptime 24h

91 of 91 checks

—

Tools

hidden behind auth

426 ms

Response time

average over 24h

4 272

Installs / week

npm and PyPI

Nothing serious here today

Today is the operative word: we check Khwan every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.

Connect this server

Endpoint below is the one we actually reach during checks — not the one copied from a README. Last verified 6 min ago.

Claude Code Claude Desktop Codex Cursor VS Code

run in your terminal

claude mcp add khwan-mcp --transport http https://mcp.khwan.ai/mcp/{core}/{user}

~/Library/Application Support/Claude/claude_desktop_config.json

{
  "mcpServers": {
    "khwan-mcp": {
      "url": "https://mcp.khwan.ai/mcp/{core}/{user}"
    }
  }
}

~/.codex/config.toml

[mcp_servers.khwan-mcp]
url = "https://mcp.khwan.ai/mcp/{core}/{user}"

.cursor/mcp.json

{
  "mcpServers": {
    "khwan-mcp": {
      "url": "https://mcp.khwan.ai/mcp/{core}/{user}"
    }
  }
}

.vscode/mcp.json

{
  "mcpServers": {
    "khwan-mcp": {
      "url": "https://mcp.khwan.ai/mcp/{core}/{user}"
    }
  }
}

This endpoint answered with an authorization challenge — the server is running, but you need an API key or OAuth to use it.

Endpoints

URL	Transport	State	Latency	Checked
https://mcp.khwan.ai/mcp/{core}/{user}	streamable-http	needs key	371 ms	6 min ago

Alternatives to Khwan

same job, measured the same way

Netcafe Memory

by ainetcafe

Cross-session, cross-device memory for your agent: remember and recall notes. No key to start.

4 tools answering

GoodMemory

by hjqcan

Durable user/project memory for MCP clients: recall context and remember selected facts.

262 installs/wk local only

Memory

by sharedmemoryai

Persistent memory for AI agents. Remember, recall, and explore a shared knowledge graph.

66 installs/wk local only

Goldhold

by jerrysrodz

Persistent memory for AI agents. Search, store, and recall across sessions.

58 installs/wk answering

Central Intelligence

by alekseimarchenko

Persistent memory for AI agents. Store, recall, and share knowledge across sessions.

96 installs/wk local only

MemorySync

by memorysync

Persistent memory for AI agents. Search and store durable facts, preferences and decisions.

answering

MADB — Agent Memory Database

by spshkar84

Durable causal memory for AI agents — semantic recall, causal lineage, and skills. Local-first.

1 758 installs/wk local only

TMCRA Agent Memory

by reshuibuduo

Role-aware Agent memory with cross-session recall, durable writes, and multi-Agent project scope.

local only

Khwan — questions

Answers built from our own checks of this server.

Why is there no tool list for Khwan?

The server answered our handshake with an authorization challenge, so it is running — but it will not describe its tools to an anonymous client. To see them you need to connect with your own credentials. We record it as alive, not as broken: 100.0% of checks in the last 24 hours got a reply.

Is Khwan working right now?

We send a real MCP handshake every 15 minutes. Over the last 24 hours 91 of 91 checks got a reply (100.0%), average response time 426 ms. The bar chart above shows every period we have measured.

How do I connect Khwan?

Copy the ready config from this page — we generate it for Claude Code, Claude Desktop, Codex, Cursor and VS Code, each with the file path that client actually reads. It is a remote server, so there is nothing to install — the client connects to the address. You will need your own key or an OAuth login: it refuses anonymous clients.

Does Khwan need an API key?

Yes. Every time we knock, Khwan answers with an authorization challenge instead of its tool list — that is how we know it is running and gated rather than broken. Bring your own credentials and it will talk.

How fast is Khwan?

It answers our handshake in 426 ms on average, which is faster than 42% of all working MCP servers we measure. The comparison comes from our own checks across the whole registry, every 15 minutes.

How many people use Khwan?

The pypi package khwan-mcp was installed 4 272 times in the last week. Week over week that is +454%. We show installs rather than GitHub stars on purpose: a star is a bookmark, an install is someone actually running it.

Is Khwan open source?

Yes — it is published under the MIT licence, written in Python and 0 stars on GitHub. The source link is on this page, so you can read exactly what it does with your data before you connect it.