BrainstormSAFE
A single model's confident answer can still be wrong, so brainstorm-mcp runs multi-round debates between GPT, Gemini, DeepSeek, Claude, and local Ollama models and returns a structured synthesis, as an MCP server that needs no API keys in hosted mode.
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
[](https://www.npmjs.com/package/brainstorm-mcp) [](https://www.npmjs.com/package/brainstorm-mcp) [](https://github.com/spranab/brainstorm-mcp/blob/main/LICENSE) [](https://ideacred.com/profile/spranab) [](https://www.producthunt.com/products/brainstorm-3?launch=brainstorm-4)
Ask one model a design question and you get one confident answer, with no signal about which parts it is unsure of. Ask three and the disagreement is the signal.
brainstorm-mcp runs multi-round debates between GPT, Gemini, DeepSeek, Claude and local Ollama models from inside your editor: they see and critique each other's answers across rounds, then you get a 3-bullet synthesis — recommendation, key tradeoffs, strongest disagreement. Also does instant quick mode, multi-model code review with verdicts, and red-team/Socratic styles. Hosted mode needs zero API keys.
Don't trust one AI. Make them argue.
Quick start (60 seconds)
claude mcp add brainstorm -- npx -y brainstorm-mcp
Then ask Claude: "Brainstorm using opus, sonnet, and haiku about whether we should use GraphQL or REST."
That runs in hosted mode: no API keys, no provider accounts. The debate uses the models already available in your environment, and you get the 3-bullet synthesis at the end.
Demo
[](https://youtu.be/L5kli5_fgkI)
Click to watch: 3 models debate, cross-examine, and produce a structured verdict — all inside Claude
dc5f3f60410aOBSERVED · 2026-10-07Connect
Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control. Replace the environment placeholders with a token scoped to the least it needs.
claude mcp add brainstorm-mcp --env OPENAI_API_KEY=${OPENAI_API_KEY} --env GEMINI_API_KEY=${GEMINI_API_KEY} --env DEEPSEEK_API_KEY=${DEEPSEEK_API_KEY} -- npx -y [email protected]Exposed tools (7)
3 read · 4 write · 0 destructive.
| Tool | Risk | Description |
|---|---|---|
add_provider | write | Add a new AI provider for brainstorming. Supports any OpenAI-compatible API, |
brainstorm | write | Run a multi-round brainstorming debate between multiple AI models. |
brainstorm_collect | write | Submit collected model responses for a hosted brainstorm session. |
brainstorm_quick | read | Get instant multi-model perspectives on any question — no debate rounds, no synthesis delay. |
brainstorm_respond | write | Submit YOUR (Claude |
brainstorm_review | read | Multi-model code review. Pass a diff and get structured findings with severity, |
list_providers | read | List all configured AI providers and their default models for brainstorming. |
Trust audit
SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | PASS |
| L1 | Static analysis of the code | PASS |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | PASS |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- none-observed
- Network
- none-observed
- Shell
- none-observed
- Dependencies
- not all pinned
- Secrets in source
- none-found
Findings (5)
.mcp.json.example
.mcpbignore
sudo mv mcp-publisher /usr/local/bin/
@modelcontextprotocol/sdk, openai, zod, @types/node, tsx, typescript
brainstorm-mcp-v1.5.3.mcpb
Gates applied: no_behavioural_pass.
dc5f3f60410afull audit observations/trust-audit/mcp-server/spranab__brainstorm.json · Report an issue / request a re-scanAudit history
Every audit this server has had. A grade with a past is a grade somebody is still checking.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-07 | dc5f3f60410a | SAFE | B | 89 | first audit |
Questions
What is the Brainstorm MCP server?
A single model's confident answer can still be wrong, so brainstorm-mcp runs multi-round debates between GPT, Gemini, DeepSeek, Claude, and local Ollama models and returns a structured synthesis, as an MCP server that needs no API keys in hosted mode.
What tools does Brainstorm expose?
7 in total: 3 read-only, 4 that write, and 0 that can delete or overwrite. Every one is listed on this page with its risk.
Is Brainstorm safe to connect to an agent?
The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean server reads B.
What credentials does Brainstorm need?
It reads DEEPSEEK_API_KEY, GEMINI_API_KEY, GROK_API_KEY, OPENAI_API_KEY and XAI_API_KEY from the environment. Give it a token scoped to the least it needs — an agent that can be talked into calling a tool can be talked into calling it with your credentials.
How does Brainstorm run?
It speaks stdio, so it runs as a local process your client starts. It is published on npm as brainstorm-mcp at 1.8.0.
How current is this page?
The grade is for one exact copy of the source (dc5f3f60410a), read on 2026-10-07. The repository is watched and re-audited when it changes.