A
licenseNot graded
qualityB
maintenanceEnables durable, least-privilege handoff of bounded tasks from a local producer to a configured MCP worker, with atomic claim, complete, and fail operations under expiring leases.
MIT
cursor-relay-mcp
by tonytanglab
Related Servers
Alternatives to cursor-relay-mcp
No user-submitted related servers found.
Related Servers
- AlicenseAqualityBmaintenanceEnables a supervisor agent to dispatch, monitor, follow up on, cancel, and inspect Cursor CLI code tasks through a governed MCP interface, with permission tiers, workspace allowlists, isolated git worktrees, and auditable artifacts. It also exposes an A2A-compatible HTTP endpoint for agent discovery and scheduling.9MIT
- AlicenseNot gradedqualityBmaintenanceEnables AI workers to run local, evidence-driven pull workflows with a shared task/run/event history, lease fencing, bounded permissions, and source-bound machine proof, while callers supply the authorized running worker.MIT
- AlicenseNot gradedqualityBmaintenanceEnables MCP clients to run declarative agents and DAG workflows as plain tools, with parallel nodes, review loops, and per-run least-privilege sandboxing.8 npmMIT
- AlicenseNot gradedqualityBmaintenanceEnables a primary model to delegate clearly scoped tasks to independent worker sessions while retaining planning and final verification, with bounded concurrency, process monitoring, status checks, and cancellation.MIT
- AlicenseNot gradedqualityBmaintenanceEnables MCP clients to access upstream MCP capabilities and OpenAI-compatible model routes through one invariant-preserving, policy-bounded endpoint with deterministic routing, leases, durable Tasks/Runs, and verifiable outcomes.Apache 2.0
TDQS
B3.4/5.0
Scored across 14 tools
Disambiguation3/5
Several tools target run observation and reading state (open_run, get_run, read_events, read_run_progress, view_run, wait_run), and their boundaries are subtle despite descriptions clarifying snapshot vs. streaming vs. live panel. Core run-control and auth tools are distinct, but the monitoring cluster invites misselection.
Naming Consistency4/5
Almost all tools use snake_case verb_noun-style names such as list_models, start_run, and wait_run, with only doctor as a noun exception. The convention is predictable and readable.
Tool Count4/5
14 tools is reasonable for auth, model discovery, workspace authorization, run lifecycle, and monitoring. The monitoring surface is somewhat heavy, but each tool maps to a defined operation.
Completeness4/5
The surface covers configuration/auth, model discovery, run creation, continuation, cancellation, listing, event reading, and progress monitoring. Explicit cleanup/prune/delete for persisted runs is missing, but the core lifecycle is otherwise covered.
Maintenance
ActivityMaintained
ResponsivenessNo issues