Skip to main content
Glama
Sign In
codedelta

codedelta

Official
by code-delta-app
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Local

Related Servers

Alternatives to codedelta

No user-submitted related servers found.

    Related Servers

    • gitrisk-mcp

      0xmortuex
      A
      license
      Not graded
      quality
      C
      maintenance
      Enables AI assistants to mine a git repository's history and answer pre-change questions: which files are riskiest, who genuinely knows a file or directory (blame-weighted, with bus factor and inactive authors), which files secretly change together, churn timelines, commit search, and release notes. It runs read-only against real git with noise filtering and reproducible, documented formulas.
      MIT

    • codebase-doctor

      subhajitlucky
      A
      license
      A
      quality
      A
      maintenance
      Evidence-backed, read-only codebase diagnostics for coding agents: secrets, dependency, RLS, and source-impact audits with a verify loop and PR review verdicts. Never writes files or uses the network by default.
      7
      114 npm
      MIT

    • Prism

      Shailesh200
      A
      license
      Not graded
      quality
      B
      maintenance
      Gives coding agents local software intelligence: it surfaces the files, tests, and helpers relevant to a task before edits, flags missed callers and uncovered code during review, and returns a single SHIP / NOT PROVEN / NO-SHIP verdict when the agent stops. Everything runs on the local index with no network calls, so repository code stays on the machine.
      3,819 npm
      10
      MIT

    • genpark-live-artifact-version

      alphaparkinc
      F
      license
      Not graded
      quality
      B
      maintenance
      Enables developers and AI agents to compute deterministic in-memory unified diffs between successive versions of live artifacts and receive structured change telemetry in return. It runs with zero external dependencies and plugs into MCP-compliant clients such as Claude Desktop, Cursor, and Windsurf.
      8
      -

    • codelattice

      aiulms
      A
      license
      Not graded
      quality
      B
      maintenance
      Local code-graph engine for AI coding workflows: static analysis of Rust, Cangjie, ArkTS, TypeScript/JavaScript, C/C++, Python, and Shell projects into symbols, imports, call graphs, and quality gates, with pre-commit change review and impact analysis. Read-only by design — never executes build scripts or uploads code.
      6
      1
      MIT

    • diff-sentinel

      TonyStarkgenetic
      A
      license
      Not graded
      quality
      B
      maintenance
      Enables AI assistants to audit git diffs, scan for leaked secrets and unsafe APIs, detect breaking changes, triage issues, generate changelogs, and assess repository hygiene through native stdio JSON-RPC tools.
      6
      Apache 2.0
    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

    A4/5.0

    Scored across 3 tools

    Disambiguation3/5

    churn_scan is clearly distinct, but ai_audit and agent_scan both target the 'AI in this codebase' question — one measuring AI-generated provenance, the other AI SDK/agent usage and commits. The descriptions help separate them, but a vague query like 'how much AI is in this repo?' could reasonably route to either, creating real misfire risk.

    Naming Consistency5/5

    All three follow the same snake_case <subject>_<action> pattern (ai_audit, churn_scan, agent_scan). The verbs vary slightly (audit vs. scan) but the convention is uniform and predictable.

    Tool Count5/5

    Three tools is well-scoped for a focused code-delta/audit engine, and each covers a genuinely distinct analysis (churn metrics, AI-generated code, AI agent inventory). No filler tools and no redundancy in count.

    Completeness4/5

    The three core analyses cover the domain's main questions, and churn_scan produces HTML reports. Minor gaps: no tool to retrieve/correlate prior reports, combine results (e.g. churn vs. AI-generated files), or compare the outputs of the analyses, but these are workable around.

    Maintenance

    ActivityMaintained
    ResponsivenessNo recent community issues

    Resources