MCP.Market

Personalbrain MCP server

online · 100% uptime
by lonniev·io.github.lonniev/personalbrain-mcp·v1.18.0·3 stars

FastMCP server for TheBrain API — AI access to a personal knowledge graph, Tollbooth-monetized

A97/100grade A
What users say
No reviews yet
Be the first
Safety scan
A97/100

full report

Adoption
Growing

3 stars

Reviews

Write one

Nobody has reviewed Personalbrain yet.

If you have run it, two minutes of your experience saves the next person an afternoon.

Personalbrain tools

Tool list not cached yet. `describe` through the gateway fetches it live.

Public scan report

scanner v0.1.10 · 2026-10-31 · same rubric, same numbers if you re-run it

no findings
  • –Code scanremote-only server, no package to scann/a
  • Live reliabilityremote reachable in 503ms (auth required)20/20
  • –Tool poisoningtools not inspected (endpoint requires auth); not countedn/a
  • Auth qualityOAuth resource metadata advertised on 40115/15
  • Maintenancelast push 2 days ago15/15
  • Maintainer identityregistry namespace matches repository owner; GitHub account older than a year8/10
Overall 97/100. Components that don't apply are left out of the denominator. Any critical finding is an F.RubricAppeal a findingJSON

How Personalbrain compares

Against every graded MCP server, from our own scans and uptime checks. Updated after each scan run.

Safety score
97/100
higher than 98% of 48,255 servers
Uptime
100%
of our recent checks; the typical remote server answers 100%
Response time
401 ms
faster than 37% of 30,031 servers
GitHub stars
3
more than 80% of 28,688 servers

Release history: 2 versions in the registry since 2026-08-24, latest 2026-10-21, typically one every 58 days.

Install Personalbrain in Claude Code, Cursor or VS Code

claude mcp add --transport http personalbrain-mcp https://personal-brain.fastmcp.app/mcp
Add to Cursor

What the publisher says

From the Personalbrain repository's README, as published. We do not edit it. Read it on GitHub

thebrain-mcp

The first city on the Lightning Turnpike.

An MCP server that gives AI agents read-write access to a personal knowledge graph — and pays for itself with Bitcoin Lightning micropayments.

The metaphors in this project are drawn with admiration from The Phantom Tollbooth by Norton Juster, illustrated by Jules Feiffer (1961). Milo, Tock, the Tollbooth, Dictionopolis, and Digitopolis are creations of Mr. Juster's extraordinary imagination. We just built the payment infrastructure.

The First City

Every turnpike needs its first city. Before the booths can collect fares and the authority can stamp purchase orders, someone has to build a destination worth driving to.

thebrain-mcp is that city — a FastMCP service deployed on Horizon that bridges AI agents to TheBrain, a personal knowledge graph of 9,000+ interconnected thoughts built over a decade. Every thought, link, attachment, and note operation maps directly to TheBrain's cloud API at api.bra.in.

It's also the proving ground for Tollbooth DPYC™ — the first MCP server where every tool call is metered via Bitcoin Lightning micropayments. Pre-fund, use, top up. No subscriptions, no API keys tied to billing accounts, no fiat payment processors. The novel contribution: an MCP server architecture where the operator monetizes AI agent access through Lightning micropayments without ever pestering the client mid-conversation.

Getting Started

Connecting via Horizon MCP

Connect any MCP-compatible client (Claude Desktop, Cursor, your own agent) to the live endpoint:

https://personal-brain.fastmcp.app/mcp

No configuration needed — Horizon OAuth handles authentication automatically.

First Connection Walkthrough

  1. sessionstatus** — Check your current session state.
  2. Get your patron npub from the dpyc-oracle's howtojoin() tool — this is the npub you registered as a DPYC™ Citizen, your identity for credit operations.
  3. Secure Courier onboarding:
  • Call requestcredentialchannel(recipient_npub=) — opens a Secure Courier channel; sends a welcome DM to your Nostr client.
  • Reply via your Nostr client with your credentials in JSON: {"apikey": "...", "brainid": "..."}
  • Call receivecredentials(sendernpub=) — vaults your credentials and activates the session. A seed balance is granted automatically.
  1. listbrains → setactivebrain** — Select which brain to work with.
  2. brainquery** — Start exploring your knowledge graph.

Returning users: call receivecredentials(sendernpub=) — vault-first lookup activates instantly, no relay I/O needed.

Secure Courier

Credentials are delivered via encrypted Nostr DMs — they never appear in the chat window. On first-time relay receipt, the service sends an ncred1... credential card back to the patron via DM for scan-and-paste reuse.

Human in the loop: The patron must consciously approve each credential delivery via their Nostr client. Never auto-poll or auto-retry receive calls — each receivecredentials drains the relay destructively (NIP-09 deletion after pickup). Call it exactly once per credential delivery.

Credits Model

Shortened. The full README is on GitHub.

Nothing above is checked by us. What we check is on the safety report.

Grade history

  • 2026-10-31restoreB → Ascore 97

Personalbrain: common questions

Is Personalbrain MCP server safe?
Yes, by our scan: it is graded A (97/100). Read the Personalbrain safety report
How do I install Personalbrain?
It runs remotely at personal-brain.fastmcp.app. Add it to Claude Code, Cursor, VS Code or Claude Desktop with the snippets above, or call it through the mcp.market gateway without installing anything.
Does Personalbrain need an API key?
No key to paste: it signs you in with OAuth when your client connects.
Is Personalbrain maintained?
The last commit was 6 days ago (2026-10-29). The latest release is v1.18.0.
Is Personalbrain up?
100% of our last 28 checks got an answer. We check remote servers about four times a day.
What can I use instead of Personalbrain?
Servers from other publishers that do the same job: Codebase Memory MCP server and Neo4j Memory MCP server.
How does Personalbrain compare with other MCP servers?
safety score 97/100 (higher than 98% of 48,255 servers); uptime 100% (of our recent checks; the typical remote server answers 100%); response time 401 ms (faster than 37% of 30,031 servers). Full comparison.

Alternatives to Personalbrain

Same job from other publishers: the closest match first, then the best rated.

  • Codebase Memory
    Codebase knowledge graph for AI agents — 162 languages, sub-ms queries, 99% fewer tokens.
    C
  • Neo4j Memory
    MCP Neo4j Knowledge Graph Memory Server
    A

More from lonniev →