Kortexio Memory is listed as active in the registry but did not answer our last check. Last commit 28 Sep 2026.
Hosted ambient memory for AI agents. Retrieve context and save notes via MCP tools with OAuth.
What the code does
We read the source, 2 d 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.
this.child = spawn(spec.command, spec.args || [], {
UPDATE agentic_guardrail_catalog
SET "ConfigJson" = $cfg${
"kind": "sandbox-claim",
"feedback": "Rejected: you invented false sandbox limitations. This tenant uses self-hosted-sandbox with outbound HTTP. Emit tool_calls — do n…
&& curl -sL https://aka.ms/InstallAzureCLIDeb | bash \
Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.
This code can reach further than it looks
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.
Connect this server
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 memory --transport http 'https://mcp.kortexio.io/{appId}/mcp'https://mcp.kortexio.io/{appId}/mcp[mcp_servers.memory]
url = "https://mcp.kortexio.io/{appId}/mcp"{
"mcpServers": {
"memory": {
"url": "https://mcp.kortexio.io/{appId}/mcp"
}
}
}{
"servers": {
"memory": {
"type": "http",
"url": "https://mcp.kortexio.io/{appId}/mcp"
}
}
}Endpoints
| URL | Transport | State | Latency | Checked |
|---|---|---|---|---|
| https://mcp.kortexio.io/{appId}/mcp | streamable-http | answering | 391 ms | 14 min ago |
Alternatives to Kortexio Memory
same job, measured the same waySecure durable memory and bounded context for AI agents, with hosted OAuth and local Lite support.
Shared memory for your AI tools: tasks, notes and context every tool can read and write over MCP.
Store, retrieve, and pin encrypted files on IPFS via MCP tools for AI agents and workflows
Persistent memory layer for AI tools. Save and recall notes across Claude and other MCP clients.
Local memory and context retrieval for AI agents through CueMap.
Append-only event log for cross-agent context/memory sharing via 3 MCP tools.
Self-hosted MCP memory for AI agents: persistent context with evidence-backed claims.
Self-hosted Markdown memory for AI agents: notes you can read and edit, with hybrid search.
Kortexio Memory — questions
Answers built from our own checks of this server.