Skip to main content
Glama
tonytanglab

cursor-relay-mcp

by tonytanglab
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Local

Related Servers

Alternatives to cursor-relay-mcp

No user-submitted related servers found.

    Related Servers

    • Agent Bus MCP

      rickkeller
      A
      license
      Not graded
      quality
      B
      maintenance
      Enables 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

    • agent-workflows-mcp

      ndmxjp
      A
      license
      Not graded
      quality
      B
      maintenance
      Enables MCP clients to run declarative agents and DAG workflows as plain tools, with parallel nodes, review loops, and per-run least-privilege sandboxing.
      13 npm
      MIT

    • LinkedRun

      ShiroganeKaichou
      A
      license
      A
      quality
      C
      maintenance
      Enables agents to submit and manage persistent, dependency-aware task graphs with immutable artifacts, resource reservations, durable event streaming, and retryable process execution over MCP.
      12
      MIT

    • mcp-poll

      yyjeqhc
      A
      license
      Not graded
      quality
      C
      maintenance
      Enables MCP apps to manage durable, model-defined goal phases with persistent state, checkpointed progress, and safe resumption after interruptions or lost turns, ensuring elapsed time never implies completed business work.
      1
      MIT

    • Wolbarg Coordination for

      wolbarg
      A
      license
      D
      quality
      C
      maintenance
      Provides MCP tools and hooks for agent coordination within Cursor workspaces, enabling claim-based scope management, compliance auditing, and production readiness checks.
      4
      MIT
    Deploy Server
    One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

    TDQS

    A3.5/5.0

    Scored across 10 tools

    Disambiguation5/5

    Each tool targets a distinct aspect of the run lifecycle: authorization, starting/reply runs, querying state, waiting, cancelling, listing, reading events, checking config, and discovering models. Even the similar start_run and reply_run are clearly separated by their purpose and description.

    Naming Consistency4/5

    Most tools follow a clear verb_noun pattern (authorize_workspace, start_run, cancel_run, list_runs, read_events, list_models). 'doctor' breaks the pattern, but it's a single minor deviation; the overall style is consistent.

    Tool Count5/5

    Ten tools is appropriate for a run-relay server; each tool has a clear role and the set covers the core workflow without unnecessary bloat.

    Completeness4/5

    The tools cover the full run lifecycle: create/reply (start_run, reply_run), read (get_run, list_runs, read_events), wait/cancel, plus prerequisite discovery (list_models) and diagnostics (doctor). The only minor gap is that events have a quantity limit with no pagination tool, but that's a practical constraint.

    Maintenance

    ActivityMaintained
    ResponsivenessNo issues

    Resources