Cairn.ink Memory is answering right now. Last checked 1 min ago. Last commit 25 Oct 2026.
Cross-session memory for AI agents with a Source Receipt for every memory, over MCP.
We read the source, 5 h ago · rules 995398eba69f
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 child = spawn(python, [STAGE_SCRIPT], {
try { privateWrite(path.join(root, filename), record); return true; }
completed = subprocess.run(
: type === 'knowledge-update' ? UPDATE
: type === 'single-session-preference' ? PREFERENCE : BASE + FIELDS;
const userconfig = join(app, '.npmrc');
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 1 min ago.
claude mcp add memory --transport http https://cairn.ink/api/mcp
https://cairn.ink/api/mcp
[mcp_servers.memory]
url = "https://cairn.ink/api/mcp"
{
"mcpServers": {
"memory": {
"url": "https://cairn.ink/api/mcp"
}
}
}
{
"servers": {
"memory": {
"type": "http",
"url": "https://cairn.ink/api/mcp"
}
}
}
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://cairn.ink/api/mcp | streamable-http | sign-in | 316 ms | 1 min ago |
Shared memory for AI agents, with a receipt for every write. Hosted MCP at agentics.you/mcp.
Project memory across sessions for AI agents. A queryable decision log in the repo.
Cross-tool decision memory for AI coding agents: search your decision graph, check changes over MCP.
MCP server for Redmine API integration with AI agents.
Persistent memory for AI agents. Search, store, and recall across sessions.
Event-sourced knowledge graph memory for AI coding agents with semantic search
Evidence-backed crypto due diligence with sources, freshness, and a runtime receipt on every call.
Shared, governed long-term memory for AI agents across tools and sessions via MCP and REST.
Answers built from our own checks of this server.