Mmcp.market

Repowise MCP server

by repowise.dev·dev.repowise/repowise·v0.17.1
No reviews yet

Codebase intelligence for AI coding agents — graph, git history, docs, decisions, code health.

B82/100grade B
Write a reviewInstall
What users say
No reviews yet
Be the first
Safety scan
B82/100

full report

Adoption
Established

7.1k stars

Reviews

Write one

Nobody has reviewed Repowise yet.

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

Repowise tools (19, 1 write)

write = sends, deletes, buys or posts

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

  • annotate_file

    Attach human-authored notes to a file's wiki page.

  • apply

    Attach every registered tool to *mcp* via ``mcp.tool()``.

  • get_answer

    Synthesised answer to a code question with verified citations and a calibrated trust signal.

  • get_architecture_diagram

    Get a Mermaid diagram for the codebase or a specific module.

  • get_callers_callees

    Find who calls a symbol and what it calls. Also works for class hierarchy.

  • get_community

    Show the architectural community/cluster a file belongs to.

  • get_context

    Triage card for files / modules / symbols — relationships, not source bytes.

  • get_dead_code
  • get_dependency_path

    Find how two files/modules are connected in the dependency graph.

  • get_execution_flows

    Show how the codebase executes: top entry points and their call traces.

  • get_graph_metrics

    Get importance metrics for a file or symbol: PageRank, centrality, community.

  • get_health

    Code-health biomarkers and per-file scores.

  • get_overview

    Architecture map for an unfamiliar repo — first call when you don't know your way around.

  • get_risk

    What history says about touching these files — hotspot, churn, owners, blast radius.

  • get_symbol

    Read one function/class with exact line bounds — cheaper and safer than Read+math.

  • get_thing
  • get_why

    Why this code looks the way it does — decision archaeology git log cannot answer.

  • search_codebase

    Find pages by concept — semantic search across the wiki.

  • update_decision_recordswrite action

Public scan report

scanner v0.1.9 · 2026-09-27 · same rubric, same numbers if you re-run it

1 medium
  • Code scan647 source files scanned20/25
  • –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
  • Maintenancelast push 0 days ago15/15
  • Maintainer identitynamespace and repository owner differ; website matches verified namespace6/10

Findings (1)

  • mediumsubprocess with shell=Trueexec.shell-true
    repowise-0.17.1/packages/cli/src/repowise/cli/commands/distill_cmd.py: …nd_str = _render_command(command) # shell=True on purpose: the user's own command may …
Overall 82/100. Components that don't apply are left out of the denominator. Any critical finding is an F.RubricAppeal a findingJSON

What the publisher says

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

<!-- mcp-name: dev.repowise/repowise -->

Understand your codebase without paying your agent to rediscover it.

Repowise indexes your code, dependency graph, git history, tests, documentation, and decisions once, then gives agents and developers cited answers, change impact, and concrete code-health fixes.

−31.6% 97.2% 2.3× less agent output3.8 vs 7.2 tool callsn=43 · p&lt;0.0001 smaller context payload393 vs 13,984 tokens30 Flask commits more defects surfacedsame 20%-of-lines budget2,770 files · p=0.003

Graph accuracy leader at matched coverage. No tool finding as much was more precise in all 7 compiler-graded cells. 5 tools · 37,853 oracle edges

Zero LLM calls for graph, risk, health, tests, dead code, and PR review. Generated prose is optional. Every benchmark publishes its sample, method, limitations, and losing rows.

Free and self-hosted · core analysis stays on your infrastructure · no API key needed · AGPL-3.0 or commercial

Why Repowise · Agents · Changes · Code health · Workspaces · Evidence · Enterprise · Docs

One index. Three ways to use it.

Shortened. The full README is on GitHub.

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

Install directly

claude mcp add repowise -- uvx repowise
Add to Cursor

Repowise: common questions

Is Repowise MCP server safe?
Mostly: it is graded B (82/100). Read the Repowise safety report
How do I install Repowise?
It runs on your machine. Copy the Claude Code, Claude Desktop or Cursor config from the install section.
Does Repowise need an API key?
Not as far as the registry entry and our scan can tell: no credentials are declared or required.
Is Repowise maintained?
The last commit was in the last day (2026-09-27). The latest release is v0.17.1.
What can I use instead of Repowise?
Servers from other publishers that do the same job: Srclight MCP server, Nexusmem MCP server and SoloMD MCP server. Compare all Repowise alternatives.

Alternatives to Repowise

Same job from other publishers: the closest match first, then the best rated.

All Repowise alternatives →
  • Srclight
    Deep code indexing for AI agents. FTS5 + embeddings + call graphs + git intelligence. Fully local.
    A
  • Nexusmem
    Local-first memory for AI coding agents: shell history with exit codes, git diffs, docs, MCP.
    A
  • SoloMD
    Read and search a folder of Markdown notes: search, backlinks, tags, tasks, outlines, git history.
    B
  • Foremerge
    Coordinate parallel coding agents, above Git
    A
  • argot
    Read-only context and complete checks against patterns learned from git history. Local; no LLM.
    B
Repowise vs SrclightRepowise vs NexusmemRepowise vs SoloMD

More from repowise.dev →