Brainfeather MCP Server

by brainfeather Your server? Claim it

answering

Brainfeather is answering right now. Last checked 11 min ago. 80 installs a week from npm.

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

Installs per day peak 36 · avg 10 · +208% w/w

a month agotoday

Uptime history 37 days of history · worst day 2%

37 days agonow

100.0%

Uptime 24h

91 of 91 checks

—

Tools

hidden behind auth

349 ms

Response time

average over 24h

Installs / week

npm and PyPI

Nothing serious here today

Today is the operative word: we check Brainfeather every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.

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 mcp --transport http https://brainfeather.com/mcp

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

https://brainfeather.com/mcp

~/.codex/config.toml

[mcp_servers.mcp]
url = "https://brainfeather.com/mcp"

.cursor/mcp.json

{
  "mcpServers": {
    "mcp": {
      "url": "https://brainfeather.com/mcp"
    }
  }
}

.vscode/mcp.json

{
  "servers": {
    "mcp": {
      "type": "http",
      "url": "https://brainfeather.com/mcp"
    }
  }
}

This endpoint answered with an authorization challenge. The server is running, but you need an API key from its owner to call it.

Endpoints

URL	Transport	State	Latency	Checked
https://brainfeather.com/mcp	streamable-http	needs key	296 ms	11 min ago

Alternatives to Brainfeather

same job, measured the same way

GoodMemory

by hjqcan

Durable user/project memory for MCP clients: recall context and remember selected facts.

232 installs/wk local only

Projectmem

by riponcm

Coding agent memory — one local MCP server for every project. Warns before repeating failed fixes.

1 327 installs/wk local only

CP Memory

by cjhuochai

Local-first, governable long-term memory for AI coding agents

115 installs/wk local only

MemoryPilot

by soflution

Long-term memory for AI agents: fast recall, project brains and skills, local, in one binary.

local only

Sprintra

by sprintra-io

The project brain for AI coding agents — memory, decisions, sprints, knowledge base via MCP.

47 installs/wk answering

Th Memory MCP

by worakorn-prince

Local long-term memory MCP server (SQLite) for AI coding agents — OpenCode, Claude Code, Cursor

893 installs/wk local only

Aletheia

by firatmio

Project memory for coding agents whose memories carry code evidence, re-checked on every recall.

610 installs/wk local only

Mengram

by alibaizhanov

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

answering

Brainfeather — questions

Answers built from our own checks of this server.

Why is there no tool list for Brainfeather?

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: 100.0% of checks in the last 24 hours got a reply.

Is Brainfeather working right now?

We send a real MCP handshake every 15 minutes. Over the last 24 hours 91 of 91 checks got a reply (100.0%), average response time 349 ms. The bar chart above shows every period we have measured.

How do I connect Brainfeather?

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. You will need your own key: it refuses anonymous clients.

Does Brainfeather need an API key?

Yes. Every time we knock, Brainfeather 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 Brainfeather?

It answers our handshake in 349 ms on average, which is faster than 40% of all working MCP servers we measure. The comparison comes from our own checks across the whole registry, every 15 minutes.

How many people use Brainfeather?

The npm package @brainfeather/mcp was installed 80 times in the last week. Week over week that is +208%. We show installs rather than GitHub stars on purpose: a star is a bookmark, an install is someone actually running it.