karst MCP server

karst

<!-- mcp-name: io.github.Moin105/karst -->

Know what your change breaks — without your code leaving your machine. karst gives any AI coding tool — Cursor, Claude Desktop, a custom agent — a local map of your codebase. It answers questions with exact file:line citations and walks a real call / import / inheritance graph to compute the blast radius of a change — "what else breaks if I touch this?" — the question plain search and agentic grep can't answer.

It runs 100% locally, speaks MCP (so it drops into any agent), and never calls an LLM itself — your source code never leaves the box. As a bonus, pack-scoped retrieval cuts ~60% of the input tokens per question.

Regulated, air-gapped, or IP-sensitive team? karst is built for the

environments cloud coding tools structurally can't enter — fully offline, no

telemetry, source you can audit. Start with the

Compliance & Air-Gap Pack (attestation,

network-egress table, pre-filled security questionnaire, offline install).

uv tool install karst      # recommended — fast, and puts `karst` on PATH for you
# or
pipx install karst         # isolated install, also handles PATH
# or
pip install karst          # if `karst` isn't found after, use `python -m karst …`

uv and pipx are the cleanest because they

put the karst command on your PATH automatically. With plain pip --user

(notably Microsoft Store Python) the command may not be on PATH — in that case

python -m karst … always works, no PATH setup required.

Why

Most "chat with your codebase" tools dump tens of thousands of vaguely-related tokens into the model on every question. You can't see what was loaded, you can't scope it, and the bill arrives at the end of the month. karst inverts that:

this?" — which embeddings alone can't.

• Scopes — pack-filtered retrieval reads ~200 chunks, not 5,000.
• Cites — every chunk carries an exact file:line. Verify, don't trust.
• Predicts — a real call/import graph answers "what else breaks if I change

Measured on a real 246-file NestJS + Next.js repo: 906 chunks indexed, re-index 343s → 2.3s incremental, ~$0.019 per question on Sonnet 4.6 (shown before the call), 60% fewer tokens with packs attached.

Quickstart (CLI)

karst command not found? Your Python Scripts dir isn't on PATH (common

with Microsoft Store Python). Everything below works the same with

python -m karst … — no PATH setup. (Or install via uv/pipx, which put

karst on PATH for you.)

cd your-project

# one command: index + call/import graph + suggested packs
karst quickstart                 #  or:  python -m karst quickstart

# ask questions about the code (defaults to this folder's index)
karst ask "how does checkout charge the user?" --no-llm    # cited code, no API key
karst ask -i                     # interactive: ask many questions

# what breaks if I change a function?
karst impact --target checkout --graph-path ~/.karst/indexes/your-project/graph.pkl

# review a diff with severity-tagged, cited findings
karst review --staged --storage ~/.karst/indexes/your-project

karst examples                   # a copy-paste cheatsheet of everything

karst quickstart prints the exact follow-up commands with your index path filled in. karst ask writes an LLM answer when ANTHROPICAPIKEY / OPENAIAPIKEY is set; otherwise add --no-llm for cited chunks (no key). The MCP server below needs no key either — your IDE supplies the model.

Use it from your IDE (MCP)

karst ships an MCP server (karst-mcp) exposing five tools — searchcode, findimpact, listpacks, indexstatus, index_repository — over stdio.

Claude Desktop (claudedesktopconfig.json) or Cursor (.cursor/mcp.json) — pick whichever launcher you have:

Shortened. The full README is on GitHub.