Skip to main content
Glama
Vitalini

ebb-ai

by Vitalini
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Local

Related Servers

Alternatives to ebb-ai

No user-submitted related servers found.

    Related Servers

    • eco-router-mcp

      stevensu04
      A
      license
      A
      quality
      A
      maintenance
      Enables AI agents to choose the lowest-carbon cloud region for a workload, with tools for ranking regions by carbon intensity and latency, and for finding optimal start times to reduce emissions.
      3
      40 npm
      1
      MIT

    • LiuHe

      wulun811
      A
      license
      B
      quality
      A
      maintenance
      LLM-native code tools: 44 MCP tools for AI agents to read, understand and modify code. Rust tree-sitter parse daemon (crash-isolated), SQLite symbol index (repo map 98ms), transactional journal-backed writes, deterministic quality gates (zero LLM calls). 512MB cgroup: 128 concurrent, zero OOM. MIT.
      44
      1
      MIT

    • LLM Usage & Cost Tracker

      zhaoyue722
      A
      license
      A
      quality
      A
      maintenance
      A local-first, multi-provider cost meter for LLM usage, exposed as MCP tools. Captures every call into a local SQLite ledger and lets any coding agent query spend, compare providers, and get recommendations — no cloud, no account. First-class support for Chinese providers (Qwen, DeepSeek) alongside Anthropic and OpenAI.
      7
      43 PyPI
      5
      MIT
    • genpark-agent-rate-limit-token-bucket-regulator-skill by alphaparkinc

      genpark-agent-rate-limit-tokenofficial

      alphaparkinc
      F
      license
      Not graded
      quality
      B
      maintenance
      Enables AI agents and multi-agent frameworks to throttle outbound LLM API calls with multi-provider token-bucket and sliding-window limiting, plus predictive token-consumption budgeting to avoid TPM/RPM throttling. It runs deterministically over MCP with zero dependencies, returning rate-limit decisions and telemetry for any client such as Claude Desktop or Cursor.
      7
      -

    • wasmagent-mcp-server

      WasmAgent
      A
      license
      A
      quality
      A
      maintenance
      Code-mode MCP server (docs_search + execute_code two-tool surface) backed by a unified capability manifest across three sandbox kernels (in-process node:vm, WASM via QuickJS / Pyodide / Wasmtime, and remote microVM via E2B / Cloudflare Sandbox). At N=30 tools the bootstrap-context cost drops to 13.6% of direct tool-use. Apache-2.0.
      2
      6
      Apache 2.0

    • genpark-agent-tool-dag

      Alpha-Park
      F
      license
      Not graded
      quality
      B
      maintenance
      Enables agents and MCP-compliant clients to resolve tool execution graphs as topological dependency DAGs, batching independent calls in parallel and speculatively prefetching arguments to cut latency and token burn. Runs deterministically as a zero-dependency JSON-RPC 2.0 stdio server for frameworks like LangGraph, CrewAI, AutoGen, and IDEs such as Cursor, Windsurf, and Claude Desktop.
      7
      -
    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

    A4.2/5.0

    Scored across 9 tools

    Disambiguation5/5

    Each tool targets a distinct action in the carbon-aware scheduling lifecycle: forecast, non-committal recommendation, scheduling, status check, single/bulk cancellation, expedite, deadline update, and retry. Overlaps are minimal, and descriptions clearly distinguish read-only planning tools from committing actions.

    Naming Consistency5/5

    All tools use snake_case with verb-first naming (get_, recommend_, schedule_, check_, cancel_, expedite_, update_, retry_), making the pattern predictable and readable. cancel_all is a minor deviation but still follows the verb-first convention.

    Tool Count5/5

    9 tools is well within the ideal 3-15 range for this domain, and each tool corresponds to a meaningful operation in the scheduling workflow without redundancy.

    Completeness4/5

    The surface covers the full lifecycle from forecasting and recommending through scheduling, status, cancellation, rescheduling, expediting, and retrying. A minor gap is the lack of an explicit tool to retrieve a completed task's output/result, though check_queue_status may provide some detail.

    Maintenance

    ActivityMaintained
    ResponsivenessNo issues

    Resources