claude
a7907c1ff8
The repo was renamed to ai-workflow-course, so the course's working-directory convention should match. Replace ~/workflow-course (and /home/you/..., /ABSOLUTE/PATH/TO/...) with ~/ai-workflow-course throughout modules/ and capstone/ (20 files, incl. the MCP config example). Safe replacement — already-correct ai-workflow-course references are untouched. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01TfzV5QvtPDz8LJS3Pu5VLT
10 lines
823 B
JSON
10 lines
823 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). IMPORTANT: 'command' must be the ABSOLUTE path to the python interpreter that has the MCP SDK installed (e.g. your venv's python) -- 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": "/ABSOLUTE/PATH/TO/ai-workflow-course/tasks-app/.venv/bin/python",
|
|
"args": ["/ABSOLUTE/PATH/TO/ai-workflow-course/tasks-app/tasks_mcp_server.py"]
|
|
}
|
|
}
|
|
}
|