Skip to main content
Glama
Sign In
Skills MCP Server

Skills MCP Server

by Blindex09
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Local

Related Servers

Alternatives to Skills MCP Server

No user-submitted related servers found.

    Related Servers

    • Skill Management MCP Server

      fkesheh
      A
      license
      A
      quality
      D
      maintenance
      Enables Claude to create, edit, run, and manage reusable skills stored locally, including executing scripts with automatic dependency management and environment variables. Works across all MCP-compatible clients like Cursor, Claude Desktop, and claude.ai.
      5
      31
      MIT

    • Forja MCP Server

      gilsonfiho
      A
      license
      Not graded
      quality
      B
      maintenance
      Exposes specialized agents as MCP tools so users can manage and triage Jira tasks, analyze repositories for health and conventions, generate commit/PR/DevOps patterns, assemble reports, produce slides and infographics, and run semantic search over a knowledge base. Everything is invokable directly from inside a coding session in Claude Code, Cursor, or Claude Desktop.
      1
      MIT

    • Skillz

      intellectronica
      A
      license
      Not graded
      quality
      D
      maintenance
      Turns Claude-style skills (SKILL.md files with resources) into callable MCP tools for any agent. Discovers skills from a directory, exposes their instructions and resources, and can execute bundled helper scripts.
      224 PyPI
      409
      MIT

    • Skills MCP Server

      rajpreetcodes
      A
      license
      Not graded
      quality
      B
      maintenance
      Enables dynamic discovery, search, and on-demand retrieval of local Claude Skills, making them accessible as a composable skill registry across MCP-compatible hosts without manual configuration.
      1
      MIT
    Deploy Server
    Claude Code, inside the Godot 4 editorFlockbay puts an AI agent in the real Godot 4 editor: it writes GDScript, runs your game and fixes what breaks. Free, or bring your own Claude Code or Codex.flockbay.comAd

    TDQS

    A3.6/5.0

    Scored across 43 tools

    Disambiguation3/5

    Most tools have distinct purposes, but several clusters genuinely overlap: a11y_aria_snapshot, a11y_observe, a11y_announce and a11y_compare_browsers all surface the accessibility tree, and a11y_tab_order, a11y_reach and a11y_probe(kind=tab_walk) all report keyboard focus order. The very detailed descriptions mitigate this, but an agent still has to carefully pick between tree-reading and focus-walking tools.

    Naming Consistency4/5

    Every tool uses a consistent a11y_ prefix and snake_case, which is highly predictable. However verb style is mixed: many are verb_noun (get_reference, read_file, list_content) while others are bare nouns (a11y_contrast, a11y_dossier, a11y_page_map, a11y_screenshot), a minor deviation from a strict convention.

    Tool Count2/5

    At 43 tools this is a heavy surface, well beyond the 15-tool sweet spot, spanning browser sessions, audits, reporting, file editing, learning and a content base. It is a genuinely broad scope, but the sheer count makes selection and cognitive load a real burden for an agent.

    Completeness5/5

    The lifecycle is remarkably thorough: discovery and reference content, browser session control with approval gating, behavioral probes, fact-gathering, finding/report/export (JSON/EARL/SARIF), run diffing, cross-browser comparison, crawling, NVDA speech, and safe file editing with undo. Almost no obvious dead ends for the stated accessibility-testing purpose.

    Maintenance

    ActivityMaintained
    ResponsivenessNo recent community issues

    Resources