claude
f925fd9645
Phase 2 sweep — all modules are post-pivot, so the learner directs the AI agent
(Claude Code as the worked example) to do the git/setup work and verifies, instead
of typing commands by hand; no re-teaching basics. Lesson sections are theory with
example output; all execution lives in the labs. De-slopped ("prose" etc. gone
course-wide, em-dash density thinned). /path/to placeholders -> ~/ai-workflow-course.
Every deliberate teaching device verified intact: M10 ai-change.patch trap,
M12 bad-clear-snippet, M13/M27 planted pending_count bug, M15 secret+typosquat+MD5,
M18 BREAK=1, M21 absent-.gitignore, M22 poisoned skill, M24 no-op patch, M25 --simulate.
Labs compile/parse (py/sh/yaml/json); no junk.
Closes #83
Closes #86
Closes #89
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01TfzV5QvtPDz8LJS3Pu5VLT
10 lines
1006 B
JSON
10 lines
1006 B
JSON
{
|
|
"_comment": "Common shape of an MCP server entry for a local (stdio) server. Many agentic tools accept this 'mcpServers' map; yours may use a different key or location (check its docs). The /home/you/... paths below are placeholders: swap in your own real absolute paths. They MUST be absolute -- a literal ~ may not expand inside JSON, so write the full path. IMPORTANT: 'command' must be the absolute path to the python interpreter that has the MCP SDK installed (your venv's python, the one your agent reported) -- a bare 'python' makes the client launch whatever is on its PATH, which usually does NOT have the SDK, and the server then reports 'not connected'. On Windows the venv python is ...\\.venv\\Scripts\\python.exe. Set 'args' to the absolute path to tasks_mcp_server.py in your tasks-app.",
|
|
"mcpServers": {
|
|
"tasks": {
|
|
"command": "/home/you/ai-workflow-course/tasks-app/.venv/bin/python",
|
|
"args": ["/home/you/ai-workflow-course/tasks-app/tasks_mcp_server.py"]
|
|
}
|
|
}
|
|
}
|