agent-instructions — Decision Integrity MCP Resource

agent-instructions is one of 3 resources on the Decision Integrity MCP server. Connect the server and your client can attach it as context.

by client

How to attach agent-instructions from your client

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

Other resources on this server

• evaluation-schema
• illustrative-example

Read from the server itself, by connecting to it and calling resources/list on 24 September 2026. A listing does not declare its resources, 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 resource's type and contents.