OMP Tandem
Related Servers
Alternatives to OMP Tandem
No user-submitted related servers found.
Related Servers
- AlicenseNot gradedqualityCmaintenanceProvides coding agents with structured planning, persistent project memory, automated verification, and safety permission controls through MCP tools, enabling better planning, context retention, self-checking, and guarded execution.1 npmMIT
- FlicenseNot gradedqualityAmaintenanceEnables multi-agent AI collaboration by connecting Claude Code, OpenAI Codex, and Google Antigravity, providing cross-model code reviews, independent second opinions, and autonomous validation through MCP tools.1-
- AlicenseNot gradedqualityBmaintenanceProvides MCP tools for AI-powered code review, research, and book writing via a fleet of coding agents.Apache 2.0
- FlicenseAqualityCmaintenanceExposes pi as a sub-agent for MCP-capable coding assistants, enabling task dispatch, messaging, and interactive dialog handling via tools like pi_dispatch, pi_send, and pi_respond.91-
- AlicenseNot gradedqualityCmaintenanceEnables AI coding agents to plan, split, and build one project together through shared tasks, file leases, a versioned contract, and urgent interrupts over MCP.MIT
- FlicenseNot gradedqualityBmaintenanceEnables Claude Code to delegate work to persistent oh-my-pi (omp) subagents via an MCP server with 7 tools (spawn, send, output, status, list, stop, prune), wrapping omp RPC mode with enforcement hooks for descriptive agent naming, model configuration, denylists, write-scope ownership, and cooperative locking.-
TDQS
Scored across 22 tools
Most tools have distinct purposes (starting, continuing, waiting, artifact, review, etc.), but some overlap exists between tandem_result and tandem_wait (both wait for tasks), and between tandem_context_read and tandem_import_context (both bring in context). Descriptions are detailed enough to clarify differences, but a few pairs could cause misselection.
All tools follow the same tandem_ prefix, creating a strong, predictable pattern. Verbs are consistently camelCase (start, continue, result, reply, publish_artifact, read_artifact) and clearly indicate the action. No naming style mixing or ambiguity.
With 23 tools, the server is on the heavy side but still within a manageable range. The tool count is justifiable given the complex workflows (reviews, artifacts, context transfer, channels), but it approaches the upper limit and may be overwhelming for simple use cases.
The tool surface covers the full lifecycle of task management, collaboration, artifact sharing, review, and context governance. It includes not only core operations but also advanced features like receipts, channel delivery, and audit, addressing potential dead ends. No obvious missing operations for the stated scope.