BigBrain MCP Server
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| loop | No | Enable loop mode with custom agent prompt | |
| chatgpt | No | Enable ChatGPT Desktop automation mode | false |
| terminal | No | Specify terminal for ChatGPT mode (Terminal, iTerm, Warp, Alacritty) | |
| max-tokens | No | Set maximum token limit | 40000 |
| disable-sound | No | Disable sound notifications | false |
| disable-notification | No | Disable system notifications | false |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| ask_big_brainA | š§ TRIGGER CONDITIONS: Use this tool when the user mentions "big brain", "BigBrain", "big-brain", or when you get stuck, loop, lose context, or need external AI consultation. This tool formats complex questions for the BigBrain system using intelligent code extraction. ā ļø REQUIRES USER INTERACTION: After calling this tool, the user must paste the prepared content into an external AI system (ChatGPT 5 Pro, Grok Heavy, Claude Opus, etc.) and return with the response. šÆ WHEN TO USE: ⢠User explicitly asks for "big brain" or "BigBrain" help ⢠You are stuck in a loop or losing context ⢠Problem is too complex for current session ⢠Need fresh external AI perspective ⢠User wants to leverage advanced AI models š CRITICAL REQUIREMENTS for your question: 1. ALL specific file paths (absolute paths like /Users/username/project/src/main.rs) 2. SPECIFIC REFERENCES using: # for symbols (main.rs#some_function), : for lines (app.py:45 or app.py:100-150) 3. ALL related dependencies and context - do not omit anything 4. Clear explanation of what needs to be analyzed or modified 5. Complete problem description with background context š§ The system automatically extracts relevant code using Probe based on file paths mentioned in your question. BE COMPREHENSIVE - missing files or symbols will lead to incomplete analysis. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/probelabs/big-brain'
If you have feedback or need assistance with the MCP directory API, please join our Discord server