Skip to main content
Glama
Secret-art-stack

spillway-mcp

by Secret-art-stack
OverviewSchemaSourceRelated ServersDiscussionsAdmin
JavaScript
Local

Related Servers

Alternatives to spillway-mcp

No user-submitted related servers found.

    Related Servers

    • CascadeGateway

      jadberro
      A
      license
      A
      quality
      A
      maintenance
      Provides an MCP endpoint that lets clients like Google Antigravity and Claude Desktop dispatch LLM tasks to local GPU models with automatic hardware-adaptive routing and cloud fallback, enabling near-zero token cost execution.
      3
      4
      MIT

    • Houtini LM

      Nguyen53
      F
      license
      Not graded
      quality
      A
      maintenance
      An MCP server that lets Claude Code or any MCP client hand bounded work — code review, boilerplate, commit messages, format conversion, embeddings — to a local GPU model, an OpenAI-compatible endpoint, a router, or a cheap cloud API, so those files never enter the orchestrator's context window. This cuts token spend and quota use while providing a second model to sanity-check results.
      -
    • genpark-multi-model-cost-latency-router-skill by alphaparkinc

      genpark-multi-model-costofficial

      alphaparkinc
      F
      license
      Not graded
      quality
      B
      maintenance
      Enables AI agents and MCP clients to dispatch queries to the most suitable model among 70+ LLMs by scoring intent, budget, cost, and latency, returning structured routing decisions with execution telemetry. It runs as a zero-dependency Python MCP server that plugs into Claude Desktop, Cursor, and other MCP-compatible clients.
      8
      -

    • Vibecoders MCP

      RaedBerjaoui
      A
      license
      A
      quality
      D
      maintenance
      One MCP that turns Claude Code into your whole dev stack by swallowing other MCP servers, delegating to Codex & Gemini on your CLI subscriptions, remembering projects in a searchable knowledge graph, and carrying setup across sessions — secret-free by design.
      23
      4
      MIT

    • Houtini LM

      shotaromehta
      A
      license
      Not graded
      quality
      A
      maintenance
      Lets Claude Code or any MCP client hand bounded work such as code review, boilerplate generation, commit messages, and format conversion to a local GPU model, an OpenAI-compatible cloud API, or a LiteLLM/OpenRouter router, so those files never enter the orchestrator's context window. This cuts token cost by roughly 93% on read-heavy tasks and provides a second model for reviewing code, while the main AI platform keeps the planning and judgement calls.
      MIT
    Deploy Server
    Shareable, User-Owned Context BackendPeople, applications, and agents read, write, and coordinate together in one context lake. Reach it over MCP, a CLI, a Python SDK, or REST.fulcradynamics.comAd

    TDQS

    A4.4/5.0

    Scored across 9 tools

    Disambiguation4/5

    The descriptions include explicit routing guidance with 'WHEN TO USE' and 'DO NOT USE FOR' clauses, so boundaries between research, scouting, editing, drafting, and execution are mostly clear. There is still inherent conceptual overlap between agy_delegate_research/local_file_scout and agy_delegate_edit/local_draft_leaf_code, but the workflow distinctions make misselection unlikely.

    Naming Consistency4/5

    All tools use snake_case with consistent agy_ and local_ prefixes that reflect execution tier. The action portion varies between verb-led (delegate_research, spawn_swarm, configure_workspace) and noun-led (status, session_followup, file_scout), so it is not a perfect verb_noun pattern, but it remains predictable and readable.

    Tool Count5/5

    Nine tools is well-scoped for a coding orchestration server. Each tool maps to a distinct orchestration responsibility: research, swarm dispatch, editing, session continuation, configuration, status, disk scouting, execution, and leaf-file drafting.

    Completeness4/5

    The surface covers the core lifecycle of delegated research, editing, follow-up, local scouting, drafting, execution, status, and configuration. Minor gaps remain around explicit session cancellation/cleanup or quota reset, but agents can work around them using status and follow-up tools.

    Maintenance

    ActivityMaintained
    ResponsivenessNo issues

    Resources