--- id: hermes-runs-one-mcp-client-for-every-surface title: Hermes runs one MCP client across every surface, and a second one it does not expose kind: nuance summary: CLI, desktop, gateway, TUI gateway, ACP adapter, cron and web all use the same `tools/mcp_tool*` client. No TypeScript SDK, and no hand-rolled client that carries a session. The one other `ClientSession` is internal, drives a computer-use server, and declares nothing. capabilities: - protocolVersions - sampling - elicitation clients: - hermes-agent - cline - openclaw specVersions: - 2025-11-25 sources: - url: https://github.com/NousResearch/hermes-agent title: importers of tools/mcp_tool across cli, gateway, tui_gateway, acp_adapter, cron and web commit: a24c12d1 path: cli.py, gateway/session.py, tui_gateway/server.py, acp_adapter/server.py, cron/scheduler.py, hermes_cli/web_server.py date: 2026-08-27 - url: https://github.com/NousResearch/hermes-agent title: tools/computer_use/cua_backend.py, the internal cua-driver session commit: a24c12d1 path: tools/computer_use/cua_backend.py:1730-1800 date: 2026-08-27 - url: https://github.com/NousResearch/hermes-agent title: importers of tools/mcp_tool across gateway, tui_gateway, acp_adapter, cron, hermes_cli and model_tools commit: 9dcf7714 path: model_tools.py, gateway/session.py, tui_gateway/agent_factory.py, acp_adapter/server.py, cron/scheduler.py, hermes_cli/cli_info_mixin.py, hermes_cli/web_routers/mcp.py date: 2026-11-09 - url: https://github.com/NousResearch/hermes-agent title: tools/computer_use/cua_backend_session.py, the internal cua-driver session commit: 9dcf7714 path: tools/computer_use/cua_backend_session.py:211-235 date: 2026-11-09 - url: https://github.com/NousResearch/hermes-agent title: hermes_platform/resolver/app.py, desktop-app liveness probe commit: 9dcf7714 path: hermes_platform/resolver/app.py:405-440 date: 2026-11-09 status: current lastVerified: 2026-11-09 related: - cline-hand-rolls-stdio-in-its-cli - goose-client-name-varies-by-surface canonical: https://canimcp.io/research/hermes-runs-one-mcp-client-for-every-surface last-updated: 2026-11-11 --- # Hermes runs one MCP client across every surface, and a second one it does not expose Kind: nuance · Status: current · Last verified: 2026-11-09 · Clients: [hermes-agent](/clients/hermes-agent.md), [cline](/clients/cline.md), [openclaw](/clients/openclaw.md) · Revisions: `2025-11-25` Cline's read established that finding a client's MCP client is not enough — its behaviour splits four ways, by surface and again by transport, with the CLI's stdio path hand-written and four revisions behind the rest. goose's splits by surface on the client name. Hermes is the counter-case, and checking cost the same work. Every user-facing surface uses the client in `tools/mcp_tool.py`, which at `9dcf7714` is split across about 25 `tools/mcp_tool_*` modules: the interactive CLI, the Electron desktop app's backend (Tauri at `a24c12d1`), the gateway, the TUI gateway, the ACP adapter, the cron scheduler and the web server. No `package.json` in the repo depends on `@modelcontextprotocol/sdk`, and a search for a hand-rolled `initialize` frame in the TypeScript and TSX sources returns nothing, so the desktop app has no client of its own and drives the Python one. Capability answers therefore hold for the whole product, which has not been true of any other multi-surface client read here. The hand-written `initialize` frames in the repo are not clients. When a configured URL answers with a non-MCP content type, Hermes POSTs a minimal frame at `2025-03-26` naming itself `hermes-probe` to decide whether the endpoint speaks MCP at all before raising `NonMcpEndpointError`. At `9dcf7714` there is a second one: the platform resolver POSTs `initialize` at `2025-06-18` as `hermes` to a declared desktop app's loopback endpoint and reads only the HTTP status to decide whether the app is answering. Neither carries a session. There is a genuine second `ClientSession`, in the computer-use backend. It spawns the `cua-driver` binary over stdio and talks to its MCP server, which makes Hermes an MCP client to a component it ships rather than to anything a user configures. That session, now in `tools/computer_use/cua_backend_session.py`, is constructed bare — no sampling callback, no elicitation callback, no `client_info` — and calls `session.initialize()` directly instead of going through `_negotiate_session`, so it declares no capabilities and has no `server/discover` fallback. It is not reachable from `mcp_servers` config and does not appear in the tool registry, so the registry entry describes the configurable path only. ## Sources - [importers of tools/mcp_tool across cli, gateway, tui_gateway, acp_adapter, cron and web](https://github.com/NousResearch/hermes-agent), commit `a24c12d1`, `cli.py, gateway/session.py, tui_gateway/server.py, acp_adapter/server.py, cron/scheduler.py, hermes_cli/web_server.py`, 2026-08-27 - [tools/computer_use/cua_backend.py, the internal cua-driver session](https://github.com/NousResearch/hermes-agent), commit `a24c12d1`, `tools/computer_use/cua_backend.py:1730-1800`, 2026-08-27 - [importers of tools/mcp_tool across gateway, tui_gateway, acp_adapter, cron, hermes_cli and model_tools](https://github.com/NousResearch/hermes-agent), commit `9dcf7714`, `model_tools.py, gateway/session.py, tui_gateway/agent_factory.py, acp_adapter/server.py, cron/scheduler.py, hermes_cli/cli_info_mixin.py, hermes_cli/web_routers/mcp.py`, 2026-11-09 - [tools/computer_use/cua_backend_session.py, the internal cua-driver session](https://github.com/NousResearch/hermes-agent), commit `9dcf7714`, `tools/computer_use/cua_backend_session.py:211-235`, 2026-11-09 - [hermes_platform/resolver/app.py, desktop-app liveness probe](https://github.com/NousResearch/hermes-agent), commit `9dcf7714`, `hermes_platform/resolver/app.py:405-440`, 2026-11-09 ## Related notes - [cline-hand-rolls-stdio-in-its-cli](/research/cline-hand-rolls-stdio-in-its-cli.md) - [goose-client-name-varies-by-surface](/research/goose-client-name-varies-by-surface.md)