Skip to main content
Glama
Nieto-Tech

crew-mcp

by Nieto-Tech
OverviewSchemaSourceRelated ServersDiscussionsAdmin
JavaScript
Local

Related Servers

Alternatives to crew-mcp

No user-submitted related servers found.

    Related Servers

    • Houtini LM

      Hayes57
      A
      license
      Not graded
      quality
      A
      maintenance
      Enables Claude Code and other MCP clients to hand bounded work — code review, test stubs, commit messages, docs, format conversion, mock data, embeddings — to a local GPU model or a cheap cloud/OpenAI-compatible endpoint, so file contents are sent straight to that model instead of entering the main AI platform's context window. This cuts token spend dramatically while giving users a second model for reviewing code, with the orchestrating assistant still checking every result.
      MIT

    • Repo MCP

      jazzyalex
      A
      license
      Not graded
      quality
      A
      maintenance
      Gives ChatGPT and Claude Code policy-scoped access to a local repository checkout, allowing them to list, search, read, edit, and create files, run operator-approved fixture tests, and inspect git diffs. It confines operations to configured paths and resources, and supports an independent read-only review workflow.
      2 npm
      4
      MIT

    • Gauntlet

      Raffymimii
      A
      license
      A
      quality
      B
      maintenance
      Enables Claude Code to submit code, diffs, plans, and security or edge-case questions to Codex, Gemini, and GPT-OSS for read-only review, verifying each quoted line against the real files so fabricated findings are filtered before Claude reads them. It also runs multi-family councils that surface agreement, falls back across models when quotas run out, and supports optional hooks that block git push until edits have been reviewed.
      10
      4
      MIT

    • local-llm-worker

      JoblessJoe
      A
      license
      Not graded
      quality
      A
      maintenance
      Enables Claude to offload noisy commands, large files, and web research to a local OpenAI-compatible LLM, receiving only concise cited answers instead of the raw material. It also optionally delegates writing a single file inside an isolated git worktree, retrying until a Claude-authored test passes.
      0
      2
      MIT

    • Houtini LM

      SagaZhu805
      F
      license
      Not graded
      quality
      A
      maintenance
      Enables Claude Code and other MCP clients to offload bounded work—code review, test stubs, boilerplate, commit messages, format conversion, embeddings—to a local GPU model or a cheaper cloud, OpenAI-compatible endpoint. Source files are read by the server rather than the main model, cutting token spend while the orchestrating model keeps planning and verifying.
      -
    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

    A3.9/5.0

    Scored across 6 tools

    Disambiguation4/5

    Each tool has a distinct role: recon maps code, review_diff audits working-tree changes, second_opinion critiques plans/diffs, check_citations verifies file:line refs deterministically, stats reports telemetry, status reports config. The only real overlap is crew_review_diff vs crew_second_opinion, both of which can consume the current diff, but the descriptions clearly separate a local scout bug review from an independent model reviewer.

    Naming Consistency4/5

    All six names share the crew_ prefix and snake_case, giving a predictable namespace. Minor deviation: most are verb_noun (review_diff, check_citations, second_opinion) while recon, stats and status are bare nouns, but the pattern remains readable and unambiguous.

    Tool Count5/5

    Six tools is well within the well-scoped range and each earns its place: three work tools (recon, review, second opinion), one deterministic checker, and two introspection tools (status, stats). No tool looks like filler or a near-duplicate.

    Completeness4/5

    The surface covers the full delegation lifecycle for its stated purpose: check availability (status), gather context (recon), review (review_diff, second_opinion), verify claims (check_citations), and audit usage (stats). Minor gaps exist around configuring workers or cancelling long-running jobs, but agents can work around these with a status call.

    Maintenance

    ActivityMaintained
    ResponsivenessUnresponsive

    Resources