MCP server enabling multi-agent collaboration and coordination
Brainstorm MCP MCP server exists for a simple reason — assistants are far more useful when they can act on Brainstorm MCP directly instead of describing what you should do. MCP server enabling multi-agent collaboration and coordination.
Brainstorm allows multiple Claude Code instances on the same computer to communicate, coordinate, and collaborate on complex tasks through a local MCP server.
Brainstorm is a Model Context Protocol (MCP) server that enables AI agents to collaborate with each other. Instead of isolated single-agent workflows, multiple AI agent instances can coordinate through structured communication, shared resources, and persistent state management.
Once Brainstorm MCP is connected, these are the calls the assistant has available:
Human-in-the — loop coordination**: Coordinators facilitate approval workflows between agents and human supervisorsProject — Based Organization**: Agents join projects with friendly names ("frontend", "backend", "reviewer")Context — Aware Prompts**: 10 intelligent prompts with real-time state injectionLong — Polling Support**: Efficient message delivery (90-second default, 1-hour max)BRAINSTORM_STORAGE — Custom storage path (default: ~/.brainstorm)BRAINSTORM_MAX_PAYLOAD_SIZE — Maximum file size for resources (default: 512000 bytes / 500KB)BRAINSTORM_CLIENT_ID — Manual client ID for containerized deployments or agents running in the same working directory (optional)File — based persistence with atomic writesCross — platform locking using O_CREAT|O_EXCLMigration — ready for future database backendLong-Polling — 2-second intervals, configurable timeout (default 90s, max 3600s)Scale — Recommended <100 agents per project, <10 messages/secondInstallation goes through your MCP client rather than a global install: point it at npm on npm and it is fetched when the client starts. The copy-paste blocks for Claude Desktop, Claude Code and Cursor are further down this page.
You will need one environment variable: BRAINSTORM_CLIENT_ID. Keep credentials in your client's env block or a secrets manager rather than in a file you might commit.
Among the file and storage access options, the useful question is rarely "what can it do" but "what does it cost you to run" — permissions, credentials, and how much of your context its toolset consumes. Brainstorm MCP's toolset — Human-in-the, Project, Context and 11 more — is a fair guide to whether it matches your workflow. It is maintained by theodorstorm; worth a glance at recent repository activity before you build anything load-bearing on it.
SyncDev reviews every entry in this directory against the project's own documentation before publishing, and revisits them as servers change.
| Tool | What it does |
|---|---|
| Human-in-the | loop coordination**: Coordinators facilitate approval workflows between agents and human supervisors |
| Project | Based Organization**: Agents join projects with friendly names ("frontend", "backend", "reviewer") |
| Context | Aware Prompts**: 10 intelligent prompts with real-time state injection |
| Long | Polling Support**: Efficient message delivery (90-second default, 1-hour max) |
| BRAINSTORM_STORAGE | Custom storage path (default: ~/.brainstorm) |
| BRAINSTORM_MAX_PAYLOAD_SIZE | Maximum file size for resources (default: 512000 bytes / 500KB) |
| BRAINSTORM_CLIENT_ID | Manual client ID for containerized deployments or agents running in the same working directory (optional) |
| File | based persistence with atomic writes |
| Cross | platform locking using O_CREAT|O_EXCL |
| Migration | ready for future database backend |
| Long-Polling | 2-second intervals, configurable timeout (default 90s, max 3600s) |
| Scale | Recommended <100 agents per project, <10 messages/second |
| Storage | File system polling, no horizontal scaling |
| Atomicity | Best-effort broadcast delivery via Promise.allSettled |
{
"mcpServers": {
"brainstorm": {
"command": "node",
"args": ["/absolute/path/to/brainstorm/dist/src/index.js"]
}
}
}Configuration as documented by the project. Restart the client after saving.
| Variable | Description | Required |
|---|---|---|
| BRAINSTORM_CLIENT_ID | Configuration value read at startup. | Optional |
Scoped local file access — read, write, search and reorganise files in directories you explicitly allow.
Search and read your Drive — Docs, Sheets and files become context your assistant can actually use.
Query, modify and analyse local SQLite databases in conversation — the fastest way to chat with a data file.
Build a programmable telecommunications stack for connecting telephony services with the Internet via a cloud-based utility.
Chat with your second brain — search, read and write vault notes through the Local REST API.
Connects AI models to an Obsidian knowledge base for direct access and manipulation of notes and folders.