Arca MCP Server

by arca-mcp

answering

Arca is answering right now. Last checked 3 min ago.

Arca is a private data vault where your AI stores your structured data, semantic memory and skills.

Uptime history 61 hours of history · worst hour 0%

61 hours agonow

87.0%

Uptime 24h

80 of 92 checks

—

Tools

hidden behind auth

1681 ms

Response time

average over 24h

API key or OAuth

Access

sse

Connect this server

Endpoint below is the one we actually reach during checks — not the one copied from a README. Last verified 3 min ago.

Claude Code Claude Desktop Codex Cursor VS Code

run in your terminal

claude mcp add arca-mcp-server --transport http https://mcp.arca.build

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

{
  "mcpServers": {
    "arca-mcp-server": {
      "url": "https://mcp.arca.build"
    }
  }
}

~/.codex/config.toml

[mcp_servers.arca-mcp-server]
url = "https://mcp.arca.build"

.cursor/mcp.json

{
  "mcpServers": {
    "arca-mcp-server": {
      "url": "https://mcp.arca.build"
    }
  }
}

.vscode/mcp.json

{
  "mcpServers": {
    "arca-mcp-server": {
      "url": "https://mcp.arca.build"
    }
  }
}

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.arca.build	sse	needs key	3107 ms	3 min ago

Alternatives to Arca

same job, measured the same way

Brains

by spacecowboyian

Personal wiki and memory for AI assistants: store, search, and recall structured notes.

1 914 installs/wk local only

Yaps Local Memory

by richawo

Search and safely manage your private local Yaps Markdown vault from MCP clients.

local only

meshdb

by meshpop

Distributed search and indexing MCP — full-text search, semantic queries, structured data

local only

Drifts

by geeks-accelerator

Multi-sensory AI experiences with time-locked progression and structured sensory data

27 installs/wk local only

Infimium

by aryankumar06

Private AI context layer for semantic code search, dependency graphs, memory, and workspaces.

1 090 installs/wk local only

Creo Memories

by creo-memories

Memory system for AI agents with semantic search. Store and recall memories with ease.

answering

Casemgr MCP

by mstang

Shared workspace your AI agent writes to. 184 tools, persistent memory, semantic search.

25 installs/wk local only

Fuel Prices

by johnisanerd

Gas and fuel prices by station and area, as structured data via a hosted MCP server.

answering

Arca — questions

Answers built from our own checks of this server.

Why is there no tool list for Arca?

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: 87.0% of checks in the last 24 hours got a reply.

Is Arca working right now?

We send a real MCP handshake every 15 minutes. Over the last 24 hours 80 of 92 checks got a reply (87.0%), average response time 1681 ms. The bar chart above shows every period we have measured.

How do I connect Arca?

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 Arca need an API key?

Yes. Every time we knock, Arca 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 Arca?

It answers our handshake in 1681 ms on average, which is faster than 1% of all working MCP servers we measure. That is on the slow side — worth knowing if the tool sits inside an interactive loop. The comparison comes from our own checks across the whole registry, every 15 minutes.