Capability Manifest — Agent Broker MCP Resource
Capability Manifest
is one of 5 resources on the
Agent Broker
MCP server. Connect the server and your client can attach it as context.
by client
How to attach Capability Manifest from your client
- Claude Code Agent Broker Resource/Capability Manifest run in your project directory
- Claude Desktop Agent Broker Resource/Capability Manifest ~/Library/Application Support/Claude/claude_desktop_config.json
- Cursor Agent Broker Resource/Capability Manifest ~/.cursor/mcp.json
- VS Code Agent Broker Resource/Capability Manifest .vscode/mcp.json
- Zed Agent Broker Resource/Capability Manifest ~/.config/zed/settings.json
- Windsurf Agent Broker Resource/Capability Manifest ~/.codeium/windsurf/mcp_config.json
- Cline Agent Broker Resource/Capability Manifest ~/Library/Application Support/Code/User/globalStorage/saoudrizwan.claude-dev/settings/cline_mcp_settings.json
- Gemini CLI Agent Broker Resource/Capability Manifest ~/.gemini/settings.json
- Grok Agent Broker Resource/Capability Manifest .mcp.json (in your project root)
- ChatGPT Agent Broker Resource/Capability Manifest Settings → Connectors → Advanced → Developer mode
- Claude.ai Agent Broker Resource/Capability Manifest Settings → Connectors → Add custom connector
- LangChain Agent Broker Resource/Capability Manifest pip install langchain-mcp-adapters
Other resources on this server
Agent Broker also offers 4 prompts — things you invoke, where a resource is context you attach.
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.