Skip to main content
Glama
hattimon

Codex Local Ops

by hattimon
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Local

Related Servers

Alternatives to Codex Local Ops

No user-submitted related servers found.

    Related Servers

    • lnwjud

      Jitwisut
      A
      license
      Not graded
      quality
      B
      maintenance
      Enables AI agents to securely access local development capabilities such as files, Git, processes, browser control, Windows automation, WSL, and observability through MCP on Windows and macOS.
      MIT

    • GPT Plus Plus

      ranhunya
      A
      license
      Not graded
      quality
      B
      maintenance
      Enables AI clients to control local Windows development tools by exposing project files, code search, file editing, test execution, Git operations, and resource viewing through a secure MCP interface with permission controls.
      10
      Apache 2.0

    • CodePier

      cyeinfpro
      A
      license
      Not graded
      quality
      A
      maintenance
      Connects ChatGPT and MCP clients to authorized local development environments, enabling secure file access, shell execution, persistent tasks, browser/desktop control, and remote management of projects.
      8
      MIT

    • LocalForge MCP

      takattowo
      A
      license
      Not graded
      quality
      B
      maintenance
      Enables MCP clients to interact with a real Windows workspace by providing tools for file operations, code search, Git, command execution, and managing long-running development processes, all under the current user's context.
      1
      MIT
    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

    D1.4/5.0

    Scored across 146 tools

    Disambiguation2/5

    Many tool names have overlapping boundaries: platform_info/platform_capabilities/local_system_info, run_script/job_start/local_shell_run, and every video_*_async duplicates the synchronous video_* operation. Even within browser automation, browser_start/open/navigate could be confused. The large set is organized by domain prefixes, but without descriptions an agent cannot reliably pick between near-synonyms.

    Naming Consistency3/5

    Most tools follow lowercase_snake_case with domain prefixes (browser_*, video_*, obs_*, ssh_*), which helps navigation. However verb placement is inconsistent: local_shell_run and job_start are object+verb while run_script and health_check are verb+object, and powershell_run breaks the local_shell_* pattern. The naming is readable but uses mixed conventions.

    Tool Count1/5

    146 tools is far beyond the 16–25 'heavy' range and into extreme-mismatch territory. Even if the server intentionally spans shell, SSH, WSL, browser, desktop, video, OBS, Docker, and jobs, the sheer number creates major navigation and selection overhead. Most agents would be better served by several smaller focused servers.

    Completeness3/5

    The surface covers a wide range of local operations—system info, shell, files, SSH/WSL, browser/desktop automation, video editing, OBS, Docker, git, services, and jobs—so it is far from incomplete overall. Still, several subdomains have gaps (file delete/move, git commit/push, docker compose logs), and the lack of descriptions makes lifecycle coverage hard to verify. These gaps are often workaroundable via shell/job tools, so this is a moderate score rather than a failure.

    Maintenance

    ActivityMaintained
    ResponsivenessNo issues

    Resources