repowise-dev avatar

Repowise

repowise-dev/repowise

Gives AI agents five intelligence layers over your codebase: a tree-sitter dependency graph with call resolution and PageRank centrality, git history analysis for hotspots and co-change patterns, auto-generated docs with hybrid RAG search, architectural decisions mined from eight sources, and a 25-biomarker code health score calibrated against real defect data. Exposes nine MCP tools for querying graph structure, ownership, health alerts, and refactoring targets. The health layer runs deterministically in under 30 seconds with no LLM calls and benchmarks show 2.3x better defect detection than commercial alternatives. Built for multi-repo workspaces across 15 languages. You'd use this when your agent needs to understand why code exists and how files relate, not just what they contain. Replaces the exploration phase most agents burn tokens on with indexed context that updates on every commit.

GitHub stars
8.1K
tools
9
transport
STDIO
last updated
Nov 2, 2026

Install

From registry metadata
$ npx add-mcp 'uvx repowise mcp --transport stdio' --name repowise

Run in your terminal. add-mcp asks which agents to add it to (Claude Code, Codex, Cursor and more). Add -g to install it for every project.

Review the command, arguments and environment values before installing. MCP servers run with your local permissions.

Other ways

Claude Code

$ claude mcp add repowise -- uvx repowise mcp --transport stdio

Run in your terminal. Replace YOUR_* placeholders with real values; add --scope user to install for every project.

Tools

Verified live · 9 tools

Verified live against the running server on Jun 11, 2026.

get_answerSynthesised answer to a code question with verified citations and a calibrated trust signal. The only tool that pairs RAG retrieval over the wiki with an LLM-written answer plus a separately-reported retrieval_quality. Use it as the first call on "how does X work" / "where is...3 params

Synthesised answer to a code question with verified citations and a calibrated trust signal. The only tool that pairs RAG retrieval over the wiki with an LLM-written answer plus a separately-reported retrieval_quality. Use it as the first call on "how does X work" / "where is...

Parameters* required
question*string
repovalue
scopevalue
get_contextTriage card for files / modules / symbols — relationships, not source bytes. Returns a compact card the agent can use to decide its next move: title, summary, signatures, hotspot bit, top callers, and pointers (decision_record titles, symbol_ids) into the deeper tools. For the...4 params

Triage card for files / modules / symbols — relationships, not source bytes. Returns a compact card the agent can use to decide its next move: title, summary, signatures, hotspot bit, top callers, and pointers (decision_record titles, symbol_ids) into the deeper tools. For the...

Parameters* required
compactboolean
default: true
includevalue
repovalue
targets*array
get_dead_codeUnused exports, unreachable files, zombie packages — what grep cannot tell you. Static reachability analysis the agent cannot derive from imports alone. Returns findings tiered by confidence (high = zero refs; medium = likely unused; low = check first) with per-directory and p...13 params

Unused exports, unreachable files, zombie packages — what grep cannot tell you. Static reachability analysis the agent cannot derive from imports alone. Returns findings tiered by confidence (high = zero refs; medium = likely unused; low = check first) with per-directory and p...

Parameters* required
directoryvalue
group_byvalue
include_internalsboolean
default: false
include_zombie_packagesboolean
default: true
kindvalue
limitinteger
default: 20
min_confidencenumber
default: 0.5
no_unreachableboolean
default: false
no_unused_exportsboolean
default: false
ownervalue
repovalue
safe_onlyboolean
default: false
tiervalue
get_healthCode-health biomarkers and per-file scores. Dashboard mode (no ``targets``) returns repo-level KPIs + the lowest-scoring files. Targeted mode returns per-file findings and metrics for each path in ``targets``. Biomarkers in v1: ``brain_method``, ``nested_complexity``, ``comple...4 params

Code-health biomarkers and per-file scores. Dashboard mode (no ``targets``) returns repo-level KPIs + the lowest-scoring files. Targeted mode returns per-file findings and metrics for each path in ``targets``. Biomarkers in v1: ``brain_method``, ``nested_complexity``, ``comple...

Parameters* required
includevalue
limitinteger
default: 20
repovalue
targetsvalue
get_overviewArchitecture map for an unfamiliar repo — first call when you don't know your way around. Returns the synthesised overview plus key modules, entry points, repo-wide git health (hotspot count, churn trend, bus-factor distribution), the knowledge map (top owners, knowledge silos...1 params

Architecture map for an unfamiliar repo — first call when you don't know your way around. Returns the synthesised overview plus key modules, entry points, repo-wide git health (hotspot count, churn trend, bus-factor distribution), the knowledge map (top owners, knowledge silos...

Parameters* required
repovalue
get_riskWhat history says about touching these files — hotspot, churn, owners, blast radius. The only tool that fuses git temporal signals (churn percentile, trend, bus factor) with graph topology (dependents, co-changes, impact surface) and security findings into one decision-shaped...3 params

What history says about touching these files — hotspot, churn, owners, blast radius. The only tool that fuses git temporal signals (churn percentile, trend, bus factor) with graph topology (dependents, co-changes, impact surface) and security findings into one decision-shaped...

Parameters* required
changed_filesvalue
repovalue
targets*array
search_codebaseFind pages by concept — semantic search across the wiki. The right tool when ``get_answer`` punted and you need candidate files for a conceptual query ("authentication flow", "rate limiting", "where do we handle webhooks"). For exact identifiers or token matches, use Grep — it...5 params

Find pages by concept — semantic search across the wiki. The right tool when ``get_answer`` punted and you need candidate files for a conceptual query ("authentication flow", "rate limiting", "where do we handle webhooks"). For exact identifiers or token matches, use Grep — it...

Parameters* required
kindvalue
limitinteger
default: 5
page_typevalue
query*string
repovalue
get_symbolRead one function/class with exact line bounds — cheaper and safer than Read+math. The only tool that returns the raw source bytes of a single indexed symbol without the agent having to compute offsets or guess at file structure. Bounded to ~400 lines (hard cap) so a misconfig...4 params

Read one function/class with exact line bounds — cheaper and safer than Read+math. The only tool that returns the raw source bytes of a single indexed symbol without the agent having to compute offsets or guess at file structure. Bounded to ~400 lines (hard cap) so a misconfig...

Parameters* required
context_linesinteger
default: 0
queryvalue
repovalue
symbol_id*string
get_whyWhy this code looks the way it does — decision archaeology git log cannot answer. The only tool that surfaces architectural decision records, their status (active / proposed / deprecated / superseded), and the commits that are evidence for them. ``git log`` tells you *what* ch...3 params

Why this code looks the way it does — decision archaeology git log cannot answer. The only tool that surfaces architectural decision records, their status (active / proposed / deprecated / superseded), and the commits that are evidence for them. ``git log`` tells you *what* ch...

Parameters* required
queryvalue
repovalue
targetsvalue

Sponsors

Readme

English | 简体中文

repowise: codebase intelligence for you and your coding agent

Stop paying your agent to re-read your codebase.

Repowise indexes your code, git history, tests and decisions once, on your machine.
Your coding agent asks the index instead of grepping and opening files, so it does about half the work.
You get the same answers in a dashboard: what calls this, what breaks, what to fix first, and why.

Set up in one line Open the live Repowise demo


View the full README on GitHub

Details

Repository
github.com/repowise-dev/repowise
Website
www.repowise.dev
Category
Developer Tools
Package
repowise
Transport
STDIO
Registry
MCP registry, active
Tools verified
Jun 11, 2026

More from repowise-dev

Related Developer Tools MCP servers

View all
1pollinations avatarConnectorspollinations/pollinationsRead Gmail, read and commit to GitHub, update Sheets, and post to Slack through Composio.5.3Kstars
2pollinations avatarComputerpollinations/pollinationsA private persistent computer: files that survive between runs, a bash shell and JavaScript.5.3Kstars
3openosint avatarOpenOSINTopenosint/openosintAI-powered OSINT agent & MCP server. 21 tools: email, breach, IP, WHOIS, DNS, Shodan, GitHub & more.1.9Kstars
4zhitongblog avatarSoloMDzhitongblog/solomdRead and search a folder of Markdown notes: search, backlinks, tags, tasks, outlines, git history.1.5Kstars
5mnemox-ai avatarIdea Reality Mcpmnemox-ai/idea-reality-mcpPre-build reality check. Scans GitHub, HN, npm, PyPI, Product Hunt — returns 0-100 signal.718stars
6rusiaaman avatarWCWGrusiaaman/wcgwShell and coding agent on mcp clients660stars