
NeuralBrain
io.github.alexcurpan-cloudPublished by GitHub account alexcurpan-cloudv1.0.0Updated Nov 2, 2026
NeuralBrain MCP Server - RAG, Vector Memory, LLM Routing, Agent Identity, x402 Payments
The publisher's own server: BrainDog
Overview
Remote NeuralBrain endpoint advertised as an AI agent ecosystem offering RAG, vector memory, LLM routing, agent identity and x402 payments.
- What you can do
- The manifest lists no tools, so capabilities can only be inferred from the one-line description: retrieval-augmented generation and vector memory for storing and recalling context, routing of requests across LLM providers, agent identity, and x402 payments.
- The README describes a 30-day public build of a multi-agent system for small businesses, with agents, chat forms and a secrets manager, but does not document any callable tools.
- No usage instructions, tool list or authentication details are provided, so what an assistant can actually do after connecting is unverified.
- When to use it
- Only worth trying if you specifically want a hosted service combining vector memory, LLM routing and agent identity, and are willing to explore it without documentation. For most users, a documented memory or RAG server is a safer choice.
- Requirements
- A remote streamable HTTP endpoint at neuralbrain.ai; no local package, environment variables or headers are declared. The manifest declares no authentication, so account or key requirements are unclear.
Installation
In SourceWeft
- Open NeuralBrain in the dashboard and add it to a workspace.
- Enable the server for the chats that should use its tools.
Web executable via Streamable HTTP. Remote servers run from the web runtime once configured in a workspace.
Use with an agent
Paste this prompt into Claude Code, Codex, Cursor or another agent — or into SourceWeft chat. The agent reads this server's install guide, shows you its publisher, endpoint and sign-in, and adds it to your client once you agree. Keys never go into a command.
Read https://sourceweft.com/mcp/io.github.alexcurpan-cloud%2Fneuralbrain/install.md and connect the MCP server it describes to my client. Before changing any config, show me its publisher, endpoint and sign-in method and wait for my OK. Never put an API key in a command or in a file I would commit; ask me where it should come from.Other MCP clients
Add this to your client's mcpServers config.
{
"mcpServers": {
"neuralbrain": {
"type": "http",
"url": "https://neuralbrain.ai/mcp"
}
}
}README
NeuralBrain — AI Agent Ecosystem
30-day public build. Day 3 of 30.
Goal: An AI architect for small businesses in Brasov, Romania.
Stack
- Framework: OpenClaw (multi-agent orchestration)
- LLMs: DeepSeek, Gemini 2.5 Flash, Claude
- Forms: Discord, Telegram, WebChat
- Agents: Argus, Jarvis, Magnus, Receptionist AI
Daily Rhythm
- One public post (Moltbook)
- One commit (GitHub)
- One interaction (reply / comment / follow)
Status
- Day 1: Synapse Layer + Moltbook automation
- Day 2: Deep memory + Jarvis fixes
- Day 3: Security consolidation (secrets manager, memory provenance, agent authorization)
Rules
- Consistency beats perfection
- Small steps, every day
- Built in public, no fluff
Started: June 15, 2026 Builder: Alex (@karpan)
Source: README.md at commit ef425f7
Tools
0Version history
1- v1.0.0LatestSep 16, 2026
Score
40% of the applicable checks met
How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.
- Reached in the last 30 daysRequired25 pts
Keep the endpoint answering the MCP handshake; SourceWeft probes it every 30 days.
- Auth declaredRequired10 pts
Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.
- Tools listed15 pts
Answer tools/list without a credential, or ship a package that starts in a sandbox without one.
- DescriptionRequired15 pts
- Logo10 pts
- Documentation15 pts
- License10 pts
Declare a license in the repository or the registry entry.
Other Brain integrations

BrainDog
dog.brainOfficial publisher
BrainDog is a hosted record of projects, decisions and money that connected AI agents read before starting work and write their results into.

Codebase Brain
Published by GitHub account Nomannazir
Indexes a local or public git codebase so an assistant can search it, trace git history, check change impact and find stale docs, all with path:line citations.

Personal Brain
Published by GitHub account zhang-liz
Gives an AI assistant memory of your professional network, stored as a graph in FalkorDB, so it can look up contacts, find people by topic, and save who you…

Second Brain
Published by GitHub account ara-5
Shared Graph-RAG memory for AI agents: markdown vault, wikilink recall, tasks, messaging.

Make0 Brain
Published by GitHub account make0-official
A local, offline memory server that lets Claude Code, Cursor, Codex and other MCP agents share one versioned store of durable facts.