MCP.Market

Codebase Chat MCP server

by shinzarou-eng·io.github.shinzarou-eng/codebase-chat·v0.10.1·2 stars
No reviews yet

Local-first codebase intelligence: cited answers, audits, reports. EN/FR.

C69/100grade C
Write a reviewInstall
What users say
No reviews yet
Be the first
Safety scan
C69/100

full report

Adoption
Growing

2 stars288 downloads/wk

Reviews

Write one

Nobody has reviewed Codebase Chat yet.

If you have run it, two minutes of your experience saves the next person an afternoon.

Codebase Chat tools (7)

write = sends, deletes, buys or posts

Read from the package source without running it. The installed server may list more.

  • codebase_check

    Verify your changes vs a git ref: blast radius, complexity, findings and delta vs the committed baseline (.codebase-chat/baseline.json). Deterministic, no LLM call.

  • codebase_deep_audit

    Full deterministic audit (~30 analyses): git churn & bus factor, churn × complexity risk, dependency integrity (undeclared imports, dead deps, lockfile drift, broken package entries), per-function complexity, secrets & sensitive files, env-var coverage, config & README hygiene — all cited file:line. Returns findings directly — no LLM call. Set ui=true to also receive an interactive HTML dashboard

  • codebase_doctor

    Installation & environment diagnostic: node version, index cache, LLM keys presence, tree-sitter, baseline staleness, MCP client integrations. Deterministic, no LLM call.

  • codebase_fix

    Apply mechanical repairs for the rules where the fix is unambiguous — env-undoc (append to .env.example), dead-dep (remove from package.json), unused-export (delete or un-export), console/debugger lines (delete). Each fix re-checks: the finding disappears. Pass dry=true to preview without writing. Deterministic, no LLM call.

  • codebase_health

    Deterministic static analysis: circular deps, dead code, duplication, complexity hotspots, health score. Returns findings directly — no LLM call.

  • codebase_ignore

    Silence a finding with a justification (written to .codebase-chat/ignores.json — commit it). `id` may be a full finding id or a prefix like `sec:innerHTML:src/x.ts` covering every such finding in that file. Use action=list/remove to manage entries.

  • codebase_impact

    Blast-radius analysis: which files transitively depend on a target file — what breaks if it changes. Deterministic, no LLM call.

Public scan report

scanner v0.1.10 · 2026-10-03 · same rubric, same numbers if you re-run it

1 high
  • Code scan3 source files scanned25/25
  • –Live reliabilityno gateway calls yet and no remote to proben/a
  • –Tool poisoningtools not inspected (local package is not executed); not countedn/a
  • Auth qualitylocal package, no credentials required12/15
  • Maintenancerepository archived0/15
  • Maintainer identityregistry namespace matches repository owner; GitHub account older than a year8/10

Findings (1)

  • highRepository is archivedmaint.archived
Overall 69/100. Components that don't apply are left out of the denominator. Any critical finding is an F.RubricAppeal a findingJSON

How Codebase Chat compares

Against every graded MCP server, from our own scans and uptime checks. Updated after each scan run.

Safety score
69/100
higher than 32% of 48,243 servers
Tools
7
the typical server has 7
Tools that change things
0%
typical: 0%. Fewer write tools means less an agent can break
GitHub stars
2
more than 75% of 28,706 servers
Downloads a week
288
more than 80% of 12,306 servers with a package

What its tools let an agent do: 7 read

Install Codebase Chat in Claude Code, Cursor or VS Code

Runs npx -y codebase-chat-mcp on your machine. Read the scan report first; the gateway never runs local packages.

claude mcp add codebase-chat -- npx -y codebase-chat-mcp
Add to Cursor

What the publisher says

From the Codebase Chat repository's README, as published. We do not edit it. Read it on GitHub

Local-first codebase intelligence. Chat, search, and audit any repository - every answer cited [source: file:line]. Works inside Cursor, Claude, Windsurf, VS Code, Zed and any MCP client - or standalone in your terminal.

= 20">

Website · MCP docs · Roadmap · Changelog · Contributing

Get started

npx codebase-chat-mcp setup

One command. The wizard detects Cursor, Claude, Windsurf, VS Code, Zed, Gemini CLI, Kiro, Cline and Roo Code, asks how you want answers (host model or API key), writes the config - done. No JSON to edit, no API key required.

Real MCP session on a real 422-file codebase - codebasehealth finds 324 circular deps, codebasechat answers with [source: file:line] receipts · PR review (--diff + --watch) · CLI tour · MCP stdio · French mode

One engine, three surfaces

Every claim comes with a citation. Every metric is computed from your code. Your repo is never uploaded - the model only sees the excerpts that matter.

Local dashboard - --ui

npx codebase-chat --ui    # → http://127.0.0.1:<port> - nothing leaves your machine

The audit as a real app - dense IDE-style UI, not a webpage:

Shortened. The full README is on GitHub.

Nothing above is checked by us. What we check is on the safety report.

Codebase Chat: common questions

Is Codebase Chat MCP server safe?
With care: it is graded C, so read the findings first (69/100). Read the Codebase Chat safety report
How do I install Codebase Chat?
It runs on your machine. Copy the Claude Code, Cursor, VS Code or Claude Desktop config from the install section.
Does Codebase Chat need an API key?
Not as far as the registry entry and our scan can tell: no credentials are declared or required.
Is Codebase Chat maintained?
The last commit was 52 days ago (2026-09-14). The latest release is v0.10.1.
How does Codebase Chat compare with other MCP servers?
safety score 69/100 (higher than 32% of 48,243 servers); tools 7 (the typical server has 7); tools that change things 0% (typical: 0%. Fewer write tools means less an agent can break). Full comparison.