Add linkedin-mcp skeleton (human-in-the-loop LinkedIn automation)#1
Draft
byggmesterPRO wants to merge 1 commit into
Draft
Add linkedin-mcp skeleton (human-in-the-loop LinkedIn automation)#1byggmesterPRO wants to merge 1 commit into
byggmesterPRO wants to merge 1 commit into
Conversation
MCP server (TypeScript + Playwright) for low-volume, dedicated-account LinkedIn use: browse feed, read posts, and post comments behind explicit human approval (MCP elicitation, with confirm=true fallback). Includes conservative rate limiting (min interval + jitter, rolling 24h caps) and a one-off manual login flow that persists a Playwright session. Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01LmimEyxBWxUsfCW7NoDLMp
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
What
A starting skeleton for
linkedin-mcp: an MCP server (TypeScript + Playwright) that lets an AI agent act as a single, careful digital employee on LinkedIn — browse the feed, read posts, and post comments with a human in the loop.Design principles (baked in per the discussion)
comment_on_postnever posts on its own — it confirms via MCP elicitation, with aconfirm=truefallback for clients without elicitation.Tools
browse_feed,read_post,quota_status(read) andcomment_on_post(write, gated).This was meant to live in a dedicated repo (
tenki-labs/linkedin-mcp), but this session's GitHub integration is scoped totenki-labs/.githuband lacks org repo-creation permission (403). It's staged here so the work isn't lost — move it to its own repo when one exists.LinkedIn's User Agreement prohibits automated access. This is built for low-volume personal use on a dedicated, disposable account with human approval on every write — not for mass outreach or scraping.
Status
Skeleton. Typechecks (
npm run typecheck). DOM selectors are best-effort and the most likely thing to break; harden before real use.🤖 Generated with Claude Code
Generated by Claude Code