Skip to main content
Glama

Related Servers

Alternatives to crapkit

  • A
    license
    Not graded
    quality
    B
    maintenance
    Enables access to Codacy's code quality platform through natural language, providing repository management, security analysis, pull request reviews, and local CLI-based code analysis. Supports comprehensive code quality monitoring including issues, coverage, security vulnerabilities, and technical debt assessment across organizations and repositories.
    3,691 npm
    58
    MIT
  • A
    license
    A
    quality
    A
    maintenance
    DocGuard, an official, zero-dependency Node.js MCP server (npm: docguard-cli, docguard mcp) exposing 5 read-only doc-governance tools: guard, score, explain, verify-claims, diagnose.
    12
    2,229 npm
    167 PyPI
    34
    MIT
  • A
    license
    A
    quality
    C
    maintenance
    Diffgate MCP server acts as a code review engine, enabling AI coding agents to analyze and validate code diffs before application. It enhances AI workflows by providing self-checking capabilities to optimise and secure code changes.
    7
    95 npm
    5
    Apache 2.0

Related Servers

  • A
    license
    A
    quality
    B
    maintenance
    Read-only MCP server that tells a coding agent what its change did to the whole repository: new dependencies, import rings, functions made hard to read, planning files committed. Every finding is measured, names its limit and says how to check it.
    3
    2
    MIT
  • A
    license
    Not graded
    quality
    C
    maintenance
    Enables coding agents to rank the functions they just changed by CRAP score across TypeScript and C#, flagging gate failures and stating exactly which test evidence is missing. It is read-only, running ts-crap and dotnet-crap over the diff since a base commit and returning one short ranked list with coverage gaps.
    MIT
  • A
    license
    Not graded
    quality
    B
    maintenance
    Enables local repository analysis to find untested functions, link tests to code, record passing runs as proof, and calculate a combined coverage score through MCP tools.
    65 npm
    MIT
  • A
    license
    A
    quality
    B
    maintenance
    Checks a code repository without running it: Safe, Works and Complete scores with an A-F grade, catching leaked keys, dangerous calls, invented or lookalike packages, broken imports and missing project files. Standard-library Python; MCP tools scan, orphans and explain.
    5
    MIT
  • A
    license
    Not graded
    quality
    D
    maintenance
    MCP server that produces scored, evidence-cited audits of public GitHub repos via tools for fetching metadata, reading files, scanning git history, and checking hygiene.
    MIT

TDQS

A4.6/5.0

Scored across 12 tools

Disambiguation4/5

Tools mostly target distinct resources, and the descriptions explicitly cross-reference siblings (get_next_item for the one packet, list_worklist for the ranking, get_function_brief once chosen; list_coupled_files vs list_duplicate_functions). There is mild clustering around 'what to fix' (list_worklist, get_next_item, get_function_brief, list_claims) and around cross-run analysis (get_trend, get_function_history, get_ratchet_report), but each boundary is spelled out.

Naming Consistency5/5

Every tool follows a clean verb_noun snake_case pattern: list_* (list_runs, list_worklist, list_coupled_files, list_duplicate_functions, list_claims), get_* (get_next_item, get_trend, get_function_brief, get_function_history, get_ratchet_report), and check_* (check_config, check_gate). No mixed conventions or vague verbs.

Tool Count5/5

12 tools sits squarely in the well-scoped 3-15 range and each maps to a real operation in the crapkit workflow (discover, survey, pick, inspect, gate-check, audit debt). No obvious filler or redundant entries.

Completeness4/5

The surface covers the analysis lifecycle: runs, config validation, work selection, per-function detail, trends, coupling, duplication, ratchet debt, gate checks, and claims listing. Gaps exist — no tool writes a claim (explicitly CLI-only) and no tool marks the baseline run — but these are documented and workable around.

Maintenance

ActivitySlowing
ResponsivenessOutdated data