PlainHub
Related Servers
Alternatives to PlainHub
No user-submitted related servers found.
Related Servers
- AlicenseNot gradedqualityBmaintenanceEnables people and their AI agents to share a kanban board whose tasks, hand-offs, reviews, notes and alerts live as markdown files in a private GitHub repo, with per-person access control. Works from Claude, ChatGPT, Claude Code, Codex or any MCP-speaking client, and can draw the board inside chats.234 npmAGPL 3.0
- AlicenseNot gradedqualityAmaintenanceProvides a shared, versioned workspace of plain files that Claude, ChatGPT, Gemini and CLI agents connect to over MCP with OAuth, so any agent can read and write the same project files, browse and restore git-backed history, and log dated hand-off notes. A single onboarding call loads the project guide, status, decisions, journal, file list and recent changes, letting a new conversation catch up immediately.MIT
- AlicenseNot gradedqualityCmaintenanceA self-hosted MCP server that gives Claude access to your GitHub account — read files, browse repos, commit changes, and manage issues and pull requests, all from a conversation.664 npmISC
- AlicenseNot gradedqualityBmaintenanceEnables Claude and any MCP client to store long-term memory as plain Markdown in the user's own private GitHub repo, with hybrid semantic search, a knowledge graph, auto-memory, and commit history. It also keeps working state alive across context compaction through core memory, hook-driven checkpoints, and a resume tool available in any client.1MIT
- AlicenseNot gradedqualityBmaintenanceEnables external MCP clients like Claude Desktop, Claude Code, Cursor and Zed to hand work to a local crew of AI agents that plan, write, check and fix code in a folder, while also acting as an MCP client that can use their tools. Runs locally with user-supplied keys, approval-gated commands, diffable and undoable runs.AGPL 3.0
- AlicenseNot gradedqualityBmaintenanceEnables claude.ai, including free users, to act as a coding agent on your own machine, allowing file edits, shell commands, and git operations within explicitly chosen project folders. It provides a secure local MCP server exposed as a custom connector with OAuth-based consent.GPL 3.0
TDQS
Scored across 14 tools
Most tools are cleanly separated by resource and action: auth vs. auth_status, post vs. decide, and the ledger readers (thread, decisions, tasks, read) each target a distinct file type or listing. The only real friction is plainhub_open vs. plainhub_browse (open one file vs. open the repo sidebar) and plainhub_post/plainhub_decide, which both write ledger files and differ mainly by intent described in prose.
Everything is snake_case under a uniform plainhub_ prefix, which is highly predictable. The one deviation is that ledger operations are split between plainhub_ledger_* (init, sync, decisions, thread, tasks, read) and unprefixed ledger writers (post, decide), so the prefix does not reliably signal the ledger subsystem.
14 tools sit comfortably in the well-scoped 3-15 range for a server that spans browser viewing, GitHub auth, environment checks and a ledger workflow. Each tool maps to a concrete operation with no obviously redundant filler.
The surface covers the full lifecycle for setup (check, auth, auth_status), viewing (open, browse, diff) and the ledger (init, post, decide, sync, read plus three listings), so no workflow dead-ends badly. Gaps remain: there is no tool to create or update a task in .agents/plan/ despite plainhub_ledger_tasks listing them, and decision-card status changes appear to require the human acting in PlainHub rather than an agent tool.