Skip to main content
Glama
Sign In
feellab-mcp

feellab-mcp

by hpdkhoa
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Local

Related Servers

Alternatives to feellab-mcp

No user-submitted related servers found.

    Related Servers

    • Weapon Lab

      hpdkhoa
      A
      license
      C
      quality
      B
      maintenance
      Enables AI clients to track first-person weapon bugs as measurable cases, run a game's own probe to gather metrics and screenshots, and compare candidate fixes against a baseline before a change is approved. It also reads posed weapon parts dumps, rebuilds animation clips in Blender, and validates probe contracts.
      67
      2
      MIT

    • evalsmith-mcp

      diegoperezg7
      A
      license
      A
      quality
      A
      maintenance
      Enables MCP clients to score retrieval quality with recall, precision, nDCG, hit rate and MRR, compare 2-3 configurations with seeded paired-bootstrap confidence intervals, audit agent tool calls against expected traces, and detect prompt regressions against golden sets. It also generates Markdown, JSON or JUnit reports with pass/fail gates, all deterministically and offline without paid API keys.
      6
      172 npm
      1
      MIT

    • html5-games-token-saver

      Alex88Ryabov
      A
      license
      A
      quality
      C
      maintenance
      Validates a built HTML5 game against CrazyGames portal rules — build checks, an emulated SDK v3 session, and frame/layout audits — returning dense JSON lists of failures, warnings and rules it could not exercise instead of screenshots or ad-hoc Playwright scripts. It emulates the portal entirely in-process (no server or port) using the game's own Playwright/Chromium, with a small per-game scenario file driving gameplay steps.
      3
      GPL 3.0
    • keel-mcp

      keel-mcpofficial

      keel-web3
      A
      license
      Not graded
      quality
      C
      maintenance
      Enables agents to plan, capture, beat-analyze, render, verify and visually inspect deterministic beat-synced trailers and scene programs inside a workspace, including stills, contact sheets, timeline linting, editor interchange exports and authored audio arrangements. It also produces typed on-chain scene bundles with local-only reuse review and browser/offline playback checks.
      MIT

    • rendercheck

      rogermsc
      A
      license
      Not graded
      quality
      B
      maintenance
      Turns silent defects in AI-generated video and audio — wrong speaking pace, mismatched loudness, truncation, dead air, late captions, broken layout — into hard assertion failures inside tests and CI. Enables agents to check individual files or whole output directories against platform presets, returning pass/fail exit codes and human-readable bug reports instead of raw measurements.
      21 PyPI
      MIT

    • slop-guard

      Nomura22872
      F
      license
      Not graded
      quality
      A
      maintenance
      Enables agents to score prose from 0-100 for formulaic AI writing tells using purely programmatic rule-based heuristics, with no LLM judge or API calls. Returns a numeric score, band label, specific violations with surrounding context, per-category counts, and concrete advice, and can also analyze a file path directly.
      -
    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

    C2.9/5.0

    Scored across 6 tools

    Disambiguation4/5

    The three list_* tools clearly target distinct resources (checklist, scenes, metrics), and check_timeline vs judge_folder differ in scope (single file validation vs folder-level judging). Minor overlap between check_timeline and judge_folder since both involve evaluation, but descriptions separate them adequately.

    Naming Consistency4/5

    Five of six tools follow a clean verb_noun pattern (list_checklist, list_scenes, list_metrics, check_timeline, judge_folder). gate_rows deviates in form, but it's a single minor exception rather than a systematic inconsistency.

    Tool Count5/5

    Six tools is well-scoped for an evaluation/QA framework: three listing tools plus three analysis tools. Each tool earns its place with no redundancy or padding.

    Completeness4/5

    The surface covers the inspection lifecycle: enumerating resources (checklist, scenes, metrics), validating timelines, judging folders, and emitting gate rows. The toolset is read/analysis-oriented, so authoring or updating checklists/metrics/scenes is absent, but that appears intentional for this domain.

    Maintenance

    ActivityMaintained
    ResponsivenessSyncing

    Resources