"Threads" matching MCP servers:

Local code review for people and their coding agents: an agent opens a review of its changes and hands over a link, the person comments on lines, and the agent reads the threads, replies and resolves what it fixed. Reads the git worktree directly, uncommitted work included; nothing leaves the machine.

Enables coding agents to retrieve pull request review findings, reproduce and fix them locally, reply on review threads, report reproduction results, and request fresh reviews.

Exposes Yocoolab design feedback threads, selections, and activity events as tools for AI coding assistants like Claude Code.

Local-first dev memory: indexes Git commits, PRs, Jira/Linear tickets, Confluence docs, Slack threads, and Calendar events into a local SQLite/FTS5/ONNX index, and exposes them as MCP tools so Claude Code, Cursor, and Codex can search and cite your past work.

Enables management of GitHub pull request review threads through natural language, allowing users to list, reply to, and resolve PR review comments using GitHub's GraphQL API.

Enables an MCP client to drive the merge-request review workflow on a self-hosted GitLab CE 11.3 instance: list and create merge requests, read per-file diffs, post comments on exact diff lines, reply to and resolve threads, and merge. It also exposes read-only helpers for projects, branches, files, users, labels, pipelines and an escape-hatch raw API call, honoring a read-only mode.

Turns a shared GitHub repository into a message bus so that agents and their subagents on two different machines can converse in parallel: an issue is a thread, a comment is a reply, and closing it is an acknowledgement. Provides zero-dependency tools for sending addressed or broadcast messages, incrementally polling an inbox with a per-identity cursor, reading and replying within threads, and closing the loop with an ack.

Enables browsing GitHub issues, pull requests, and Projects boards across multiple GitHub hosts, then kicking off Codex threads pre-loaded with the selected issue, repository, and a plan-first, implement, investigate, or review brief. Also exposes tools that let Codex read issues and project data directly without leaving a conversation.

Connects AI assistants to GitLab projects, enabling natural language queries for merge requests, code reviews, test reports, pipeline status, and discussions with support for commenting and resolving threads.

Enables manual review of GitLab Merge Requests and GitHub Pull Requests, loading context, generating comment previews, and preparing commit-based fixes for unresolved threads. Every write — comments, replies, and commits — requires explicit user confirmation and an approved preview before it is published.

Enables autonomous coding agents to inspect Git commits, create pull requests, parse issue threads, and post reviews on GitHub repositories.