Skip to main content
Glama
chapmanjw

Rutherford MCP Server

by chapmanjw

Related Servers

Alternatives to Rutherford MCP Server

No user-submitted related servers found.

    Related Servers

    • F
      license
      Not graded
      quality
      Not graded
      maintenance
      Orchestrates multiple AI models (Gemini, OpenAI, Claude, local models) within a single conversation context, enabling collaborative workflows like multi-model code reviews, consensus building, and CLI-to-CLI bridging for specialized tasks.
      -
    • A
      license
      B
      quality
      F
      maintenance
      Enables orchestrating multiple AI CLI agents (Claude Code, Codex, Gemini CLI, Copilot CLI) through a unified MCP interface for task delegation, cross-agent comparison, and specialized tools like code review and debugging.
      14
      3 npm
      14
      MIT
    • A
      license
      Not graded
      quality
      C
      maintenance
      Enables multiple AI coding CLIs (Claude Code, Gemini/Antigravity, Codex, and OpenCode) to collaborate as a coordinated team by routing cross-agent prompts, sharing messages and review tickets, tracking tasks on a shared store, and isolating each agent in its own Git worktree with turn-budget safeguards—all inspectable and steerable from a local web dashboard.
      MIT
    • A
      license
      C
      quality
      B
      maintenance
      Enables delegating coding tasks to multiple AI CLI agents (Claude Code, Antigravity, Codex, Cursor) with session memory and diff inspection.
      16
      41 npm
      MIT
    • A
      license
      B
      quality
      B
      maintenance
      Enables any MCP host to delegate work to multiple coding-agent CLIs such as Codex, Claude Code, and Antigravity as subagents, preserving native sessions and supporting team-based supervision and agent-to-agent messaging.
      17
      139 npm
      Apache 2.0

    TDQS

    A4.3/5.0

    Scored across 18 tools

    Disambiguation4/5

    Most tools target clearly distinct actions: delegate runs one agent, consensus runs many in parallel, debate runs an argument across rounds, and the job tools each cover a different lifecycle stage. However, review and plan are documented as thin wrappers over consensus and delegate respectively, which creates some purpose overlap that agents must be careful to disambiguate.

    Naming Consistency4/5

    Multi-word tool names consistently use snake_case verb_noun or noun_noun patterns (list_jobs, cancel_job, reload_panels, job_result), and single-word names are short readable verbs or nouns. Minor inconsistencies exist, such as 'capabilities' being a bare noun alongside 'list_roles'/'list_jobs', and 'activity' being a noun where 'list_activity' would fit the pattern.

    Tool Count4/5

    At 18 tools, the count sits at the heavier end, but the server spans a broad domain: orchestration actions (delegate, consensus, debate, review, plan), a full background-job subsystem (5 tools), and agent/config management (5 tools). Each tool earns its place for this scope; the count is justified rather than bloated.

    Completeness4/5

    The core lifecycle is well covered: task execution (delegate/consensus/debate), the complete job lifecycle (create async, poll status, fetch result, cancel, continue, list all/active), and agent management (capabilities, doctor, discover, setup). Minor gaps remain — panels are edited via files with no creation tool, and there is no way to explicitly delete kept runs beyond TTL eviction.

    Maintenance

    ActivityMaintained
    ResponsivenessResponsive