cost_estimation — Agent Broker MCP Prompt

cost_estimation is one of 4 prompts on the Agent Broker MCP server. Connect the server and it appears in your client, ready to invoke.

by client

How to invoke cost_estimation from your client

• Claude Code Agent Broker Prompt/cost_estimation run in your project directory
• Claude Desktop Agent Broker Prompt/cost_estimation ~/Library/Application Support/Claude/claude_desktop_config.json
• Cursor Agent Broker Prompt/cost_estimation ~/.cursor/mcp.json
• VS Code Agent Broker Prompt/cost_estimation .vscode/mcp.json
• Zed Agent Broker Prompt/cost_estimation ~/.config/zed/settings.json
• Windsurf Agent Broker Prompt/cost_estimation ~/.codeium/windsurf/mcp_config.json
• Cline Agent Broker Prompt/cost_estimation ~/Library/Application Support/Code/User/globalStorage/saoudrizwan.claude-dev/settings/cline_mcp_settings.json
• Gemini CLI Agent Broker Prompt/cost_estimation ~/.gemini/settings.json
• Grok Agent Broker Prompt/cost_estimation .mcp.json (in your project root)
• ChatGPT Agent Broker Prompt/cost_estimation Settings → Connectors → Advanced → Developer mode
• Claude.ai Agent Broker Prompt/cost_estimation Settings → Connectors → Add custom connector
• LangChain Agent Broker Prompt/cost_estimation pip install langchain-mcp-adapters

Other prompts on this server

• book_from_any_url
• find_then_book
• compliant_transactional_message

Agent Broker also offers 5 resources — data you attach as context, where a prompt is something you run.

Read from the server itself, by connecting to it and calling prompts/list on 24 September 2026. A listing does not declare its prompts, so asking is the only way to know them, and this is what the server actually offers rather than what its listing claims. Names only are stored; connect the server for each prompt's arguments.