MCP - Model Context Protocol (client + server)

charly speaks MCP in both directions. This skill covers both:

• Client — charly check mcp <method>: connect to any MCP server declared via mcp_provide and probe/call/read. Used to test MCP endpoints shipped by jupyter-mcp, chrome-devtools-mcp, or the charly server itself.
• Server — charly mcp serve: expose the entire charly CLI surface (build + test + deploy modes, 190 tools) as MCP over Streamable HTTP or stdio. Used by LLM agents (Claude Code, Open WebUI, OpenClaw) to drive charly remotely. Deployed in-container via the charly-mcp layer. The 190-tool catalog now includes a project-scaffolding + YAML-editing + file-write authoring surface, so an agent can build an charly project from scratch over RPC — see "Authoring tools" below.

Both surfaces share the same SDK: github.com/modelcontextprotocol/go-sdk v1.5.0.

Part 1 — Client (charly check mcp …)

Overview

charly check mcp connects to Model Context Protocol servers declared by running containers via mcp_provide, using github.com/modelcontextprotocol/go-sdk (v1.5.0). Seven leaf subcommands cover the full MCP client surface: ping, servers, list-tools, list-resources, list-prompts, call, read. No MCP URL argument is ever typed by the user — the verb reads the target image's ai.opencharly.mcp_provide OCI label, resolves {{.ContainerName}} templates, applies pod-aware localhost rewriting, and maps the container-network URL to the published host port automatically.

Also as a declarative verb