Recalld MCP Server

by bit-robotics Your server? Claim it

not responding

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

Managed long-term memory for AI agents, with evolving facts and relevant retrieval through MCP.

Uptime history 47 days of history · worst day 0%

47 days agonow

0.0%

Uptime 24h

0 of 91 checks

—

Tools

hidden behind auth

5 ms

Response time

average over 24h

open, no key

Access

streamable-http

Recalld 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 11 min ago.

Claude Code Claude Desktop Codex Cursor VS Code

run in your terminal

claude mcp add recalld --transport http 'https://{region}.recalld.ai/mcp'

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

https://{region}.recalld.ai/mcp

~/.codex/config.toml

[mcp_servers.recalld]
url = "https://{region}.recalld.ai/mcp"

.cursor/mcp.json

{
  "mcpServers": {
    "recalld": {
      "url": "https://{region}.recalld.ai/mcp"
    }
  }
}

.vscode/mcp.json

{
  "servers": {
    "recalld": {
      "type": "http",
      "url": "https://{region}.recalld.ai/mcp"
    }
  }
}

Endpoints

URL	Transport	State	Latency	Checked
https://{region}.recalld.ai/mcp	streamable-http	answering	5 ms	11 min ago

Alternatives to Recalld

same job, measured the same way

Cuemap MCP

by cuemap-dev

Local memory and context retrieval for AI agents through CueMap.

71 installs/wk local only

Flint

by synuns

Agent long-term memory with search, recording, and hot injection for AI coding agents

local only

Brainfeather

by brainfeather

Long-term memory for AI coding agents: durable project facts, recalled by every MCP client.

57 installs/wk answering

Mazarbul

by mo-cmyk

Local-first memory for AI agents: entities, facts, relations and documents with semantic recall.

local only

Tinycontext

by tinysuitehq

Token-light local memory with SQLite hybrid retrieval for MCP agents.

407 installs/wk local only

Mengram

by alibaizhanov

Long-term memory for AI agents: semantic facts, episodic events, and procedural workflows

answering

Seam Runtime

by blackhatshiftey

SEAM: local-first memory runtime for AI agents, with retrieval and glassbox provenance over MCP.

46 installs/wk local only

Vayl

by ac12644

Reconciling memory for AI agents: a changed fact retires the old value, with history and approval.

247 installs/wk local only

Recalld — questions

Answers built from our own checks of this server.

Is Recalld 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 5 ms. The bar chart above shows every period we have measured.

The registry lists Recalld 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 Recalld?

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 Recalld need an API key?

No. Recalld 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.