Skip to main content
Glama
Sign In
OppenSteward-MCP

OppenSteward-MCP

by HaobinZhou
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Local

Related Servers

Alternatives to OppenSteward-MCP

No user-submitted related servers found.

    Related Servers

    • WebCodex MCP

      xq3427
      A
      license
      Not graded
      quality
      B
      maintenance
      Enables ChatGPT to operate authorized local projects through MCP, including reading and modifying code, viewing Git changes, running configured programs, and reading local Codex sessions to continue work.
      21 npm
      9
      MIT

    • web-gpt-file-save

      abo1016
      A
      license
      Not graded
      quality
      C
      maintenance
      Enables ChatGPT to save conversation attachments, generated files, and images directly into a configured local macOS project directory with OAuth-secured MCP access.
      MIT

    • Coding Local

      Syx403
      A
      license
      Not graded
      quality
      B
      maintenance
      Enables ChatGPT to inspect selected local projects, make edits, run commands/tests, and review diffs through an authenticated MCP endpoint backed by a containerized workspace.
      Apache 2.0

    • Workroom

      bingak36-creator
      A
      license
      Not graded
      quality
      B
      maintenance
      Enables ChatGPT to inspect and manage approved local project folders, read files, propose edits, patches, and deletions, run shell commands subject to approval, and track jobs and tasks through MCP. It provides controlled access to local project files and execution results on macOS.
      MIT

    • Codex Local Bridge

      yiwancibeishang123
      A
      license
      Not graded
      quality
      B
      maintenance
      Connects the ChatGPT web app to a locally running Codex agent over OAuth-secured MCP so users can plan in chat while their own machine reads authorized project files, applies SHA-guarded edits, and runs sandboxed tests. Per-project grants can be revoked anytime, and every write is backed up, conflict-checked, and audited.
      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

    A3.5/5.0

    Scored across 8 tools

    Disambiguation4/5

    Most tools have distinct purposes, but read_file and fetch overlap: both retrieve document content by ID/chunk with offset-based continuation, and the descriptions spend several sentences clarifying boundaries (e.g. fetch is for search results, read_file for governance docs) — a sign of inherent confusion. list_files also partially overlaps with list_projects/project_overview in exposing project structure.

    Naming Consistency3/5

    Mixed conventions: three list_* tools, but also project_overview, get_skill_guide, refresh_projects, read_file, fetch, search. Verb_noun holds for list_projects/list_files/get_skill_guide/read_file, while fetch and search are bare verbs and project_overview is noun-only. Readable but not a predictable pattern.

    Tool Count5/5

    8 tools is well-scoped for a project-governance/registry server; each tool maps to a distinct operation (list, browse, overview, fetch, guide, read, refresh, search) with no filler.

    Completeness4/5

    Covers the read-oriented lifecycle: discovery (list_projects, list_files, project_overview), retrieval (search, fetch, read_file), skill guidance, and refresh. The surface is explicitly read-only and mentions separate tools (list_discussions, read_discussion) for Discussion, so gaps are intentional boundaries rather than dead ends.

    Maintenance

    ActivitySlowing
    ResponsivenessNo recent community issues

    Resources