SWE2 Bridge
Related Servers
Alternatives to SWE2 Bridge
No user-submitted related servers found.
Related Servers
- AlicenseAqualityCmaintenanceEnables MCP-compatible coding agents to execute the local Codex CLI as a coding agent, including code reviews, session resume/fork, and CLI diagnostics.9MIT
- AlicenseNot gradedqualityCmaintenanceLaunches the official Codex CLI as a persistent MCP server so DeepSeek Harness can invoke Codex models without storing or transmitting ChatGPT credentials to third parties.MIT
- AlicenseNot gradedqualityBmaintenanceEnables MCP clients like Claude Code to delegate coding tasks to the local Cursor Agent CLI, with persistent per-workspace sessions that resume across calls.12 npmMIT
- AlicenseNot gradedqualityBmaintenanceEnables Codex to delegate bounded coding tasks to MiMo Code through a shared local daemon, supporting task boundaries, Git Worktrees, and a collaborative review workflow.3MIT
- AlicenseNot gradedqualityAmaintenanceA local STDIO MCP server that bridges MCP clients to the Codex CLI by sending instructions to a configured workspace, exposing task run, status, and result tools with a read-only sandbox and no remote transport.124MIT
- AlicenseNot gradedqualityBmaintenanceEnables MCP clients and external AI supervisors to oversee and steer native Codex sessions through a thin local stdio bridge. It exposes eleven codex_* supervisory tools for tasks such as listing threads, starting turns, observing progress, steering, responding to approvals, interrupting, checkpointing, and rolling over work.MIT
TDQS
Scored across 3 tools
Each tool maps to a distinct job lifecycle stage: run (start), wait (poll/collect), cancel (stop). Descriptions explicitly distinguish devin_run from devin_wait and mention job_id handoff, so there is no realistic overlap.
All three tools use the same devin_<verb> snake_case pattern with parallel imperative verbs (run, wait, cancel). Fully predictable and readable.
Three tools precisely cover the async start/poll/cancel lifecycle for a single-job bridge. Nothing is redundant; adding more would be overengineering.
Start, wait, and cancel cover the core lifecycle, and cancellation notes that changes are preserved. Minor gaps could be listing/inspecting active jobs or cleaning up terminal job state, but these are workable around.