Mirror MCP Server

by mctx-ai Your server? Claim it

not responding

Mirror is listed as active in the registry but did not answer our last check.

Give Claude an honest self-model — behavioral tendencies built from evidence, not session memory. Mi

Uptime history 91 days of history · worst day 0%

91 days agonow

0.0%

Uptime 24h

0 of 91 checks

—

Tools

hidden behind auth

311 ms

Response time

average over 24h

open, no key

Access

streamable-http

Mirror does not always answer

Over the last week it answered 0.0% of our checks. We check every 15 minutes, so you hear about the next outage within the hour — not from your users.

Connect this server

Endpoint below is the one we actually reach during checks — not the one copied from a README. Last verified 12 min ago.

Claude Code Claude Desktop Codex Cursor VS Code

run in your terminal

claude mcp add mirror --transport http https://mirror.mctx.ai/v0.4.0

Settings → Connectors → Add custom connector, then paste this address

https://mirror.mctx.ai/v0.4.0

~/.codex/config.toml

[mcp_servers.mirror]
url = "https://mirror.mctx.ai/v0.4.0"

.cursor/mcp.json

{
  "mcpServers": {
    "mirror": {
      "url": "https://mirror.mctx.ai/v0.4.0"
    }
  }
}

.vscode/mcp.json

{
  "servers": {
    "mirror": {
      "type": "http",
      "url": "https://mirror.mctx.ai/v0.4.0"
    }
  }
}

Endpoints

URL	Transport	State	Latency	Checked
https://mirror.mctx.ai/v0.4.0	streamable-http	answering	311 ms	12 min ago

Alternatives to Mirror

same job, measured the same way

Sentarion

by sammyboi81

Governed MCP orchestration, tamper-evident memory, and Claude Code Seatbelt hooks.

169 installs/wk local only

Context Autopilot

by chiragbachani

Mines your Claude Code and Cursor sessions into evidence-based CLAUDE.md / AGENTS.md rules.

66 installs/wk local only

Recall

by clauderecall

Persistent memory for Claude Code and Codex. Search and re-inject context from any session.

local only

Claude Handoff

by vasilispapg

Session handoff for Claude Code: list sessions and build handoff docs another agent continues from.

434 installs/wk local only

Knowledge MCP

by fulminate-io

Persistent memory graph for coding agents: hypotheses, evidence, and decisions survive sessions.

local only

Recall

by clauderecallhq

Persistent memory for Claude Code. Search, recall, and re-inject context from any session.

208 installs/wk local only

Agent Magnet

by helinakdogan

Behavioral memory layer for AI tools. Learns preferences and context across Claude, Cursor, Codex.

424 installs/wk local only

GhostPaw Codex

by ghostpawjs

Local belief and memory engine with evidence, certainty, and honest revision history.

668 installs/wk local only

Mirror — questions

Answers built from our own checks of this server.

Is Mirror working right now?

We send a real MCP handshake every 15 minutes. Over the last 24 hours 0 of 91 checks got a reply (0.0%), average response time 311 ms. The bar chart above shows every period we have measured.

The registry lists Mirror as active — why does it not respond?

The official MCP registry stores what the author submitted; it does not verify that the server still runs. We check the endpoint ourselves, and this one does not answer. Catalogues that copy the registry without checking will show it as working.

How do I connect Mirror?

Copy the ready config from this page. We generate it for Claude Code, Claude Desktop, Codex, Cursor and VS Code, each in the form that client actually reads. It is a remote server, so there is nothing to install — the client connects to the address.

Does Mirror need an API key?

No. Mirror completed a full MCP handshake with us as an anonymous client and listed its tools without asking for anything. This is what we observed, not what the docs claim.