2-repro-issue

# Reproduce a LinkedIn-MCP Issue Locally Goal: take an issue number, run the exact failing tool call against the real LinkedIn via the local MCP server, and produce concrete evidence — output JSON, error message, partial state — that confirms or refutes the bug on the current branch. Always use the authenticated profile already at `~/.linkedin-mcp/profile/`. Never mock. ## Phase 1 — Read and map ```bash # Accept "442", "#442", or "https://github.com/.../issues/442" — extract the digits only NUM=$(echo "$ARGUMENTS" | sed -E 's|.*/||; s|#||g' | grep -oE '^[0-9]+' | head -1) [ -z "$NUM" ] && { echo "Invalid input: '$ARGUMENTS'. Pass an issue number or URL." >&2; exit 1; } REPO=stickerdaniel/linkedin-mcp-server gh issue view $NUM --repo $REPO --comments ``` From the issue body extract: - **Which MCP tool** is affected (`get_person_profile`, `connect_with_person`, `search_jobs`, …). The issue templates ask for this explicitly. - **The exact arguments** that trigger the failure (username, company slug, job ID, sections list). - **The expected vs actual** behaviour. - **Any locale signal** — German UI, non-English profile name, RTL language. Locale-sensitive bugs need a deliberately diverse target. Map the tool to code so you know where to look if the repro confirms the bug: 1. `linkedin_mcp_server/tools/<surface>.py` — MCP entrypoint and arg validation 2. `linkedin_mcp_server/scraping/<feature>.py` — actual scraping (`extractor.py`, `connection.py`, `feed.py`, `inbox.py`, …...