MCP.Market

Replen MCP server

by replenhq·io.github.replenhq/replen·v1.3.5·8 stars
No reviews yet

A local intelligence layer for AI coding agents. Maps your repos, matches the open-source frontier.

B80/100grade B
Write a reviewInstall
What users say
No reviews yet
Be the first
Safety scan
B80/100

full report

Adoption
Growing

8 stars41 downloads/wk

Reviews

Write one

Nobody has reviewed Replen yet.

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

Replen tools (14)

write = sends, deletes, buys or posts

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

  • replen_capture_insight

    Capture a PORTFOLIO INSIGHT from triage — Pass 3 (a transferable idea / premise / way-of-working) or Pass 4 (a sharpened boundary).

  • replen_cart

    Atlas Carts — pull a saved, filtered VIEW over the user's decision graph so you can act on it in-session.

  • replen_handoff

    Open a handoff PR in the user's own project repo, adding .digest/handoffs/<repo>-<date>.md describing why the matched OSS surfaced and prompting the agent to evaluate it.

  • replen_help

    List every replen MCP tool available in this session with one-line descriptions and example invocations. Call this when the user types /replen or asks 'what can replen do' / 'what commands do I have'.

  • replen_leaps

    Leaps — Atlas's connection engine. Surface NON-OBVIOUS, high-leverage connections for the user's repos, drawn from Atlas (Replen's knowledge graph of their whole portfolio).

  • replen_onboard_state

    Per-repo onboarding state for the whole portfolio — the cheap PRE-FLIGHT for /replen-onboard. Call this ONCE before

  • replen_queue

    The awareness→action queue. Items land here from the user's weekly brief / alert emails ('queue for next session')

  • replen_recall

    Replen's MEMORY across the user's whole portfolio + decision history. Ask it before re-deriving things the user has already settled. Answers questions like:

  • replen_record_triage

    Record your per-candidate triage decision back to Replen. Call ONCE per candidate during the replen_match loop, AFTER you've formed your verdict but BEFORE / alongside presenting the writeup to the user.

  • replen_set_capabilities

    Set the TECHNICAL CAPABILITIES of a Replen project from what you read in its code. Use this during ONBOARDING

  • replen_set_product

    Group repos into a multi-repo PRODUCT. A product usually spans several repos (a web app, an API,

  • replen_set_tags

    Set the DOMAIN TAG CLOUD on one of the user's registered Replen projects — the single biggest lever on match

  • replen_set_versions

    Report the project's PINNED dependency/runtime versions to Replen — names + versions ONLY, never code.

  • replen_state

    Record a user action on a Replen candidate. Call AFTER you've presented writeups via replen_match and the user has chosen what to do with each one.

Public scan report

scanner v0.1.9 · 2026-09-26 · same rubric, same numbers if you re-run it

no findings
  • Code scan7 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 qualitystatic API keys via environment variables6/15
  • Maintenancelast push 19 days ago15/15
  • Maintainer identityregistry namespace matches repository owner6/10
Overall 80/100. Components that don't apply are left out of the denominator. Any critical finding is an F.RubricAppeal a findingJSON

How Replen compares

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

Safety score
80/100
higher than 60% of 48,273 servers
Tools
14
the typical server has 7
Tools that change things
0%
typical: 0%. Fewer write tools means less an agent can break
GitHub stars
8
more than 86% of 28,534 servers
Downloads a week
41
more than 34% of 11,915 servers with a package

What its tools let an agent do: 14 read

Install Replen in Claude Code, Cursor or VS Code

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

claude mcp add replen -- npx -y @replen/mcp
Add to Cursor

What the publisher says

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

Replen Smarter AI Development Workflows A local intelligence layer for AI coding agents.

Website · Docs · Install · Workflow · MCP · Skill · Self-host · Research · app.replen.dev

Claude Code, Codex and Cursor already help inside the repo you are working on. Replen gives them a local intelligence layer across every repo you build.

It maps each project to what it actually does, building an ontology and knowledge graph of your portfolio: computer vision, geospatial analysis, market-making, scraping, workflow automation, or whatever else you build. It then watches the OSS frontier and continuously scores relevant projects against your real capabilities, using semantic matching and a self-tuning learning loop shaped by what you adopt, skip and review.

The result is not a trending list, a keyword search, or a static repo graph. Replen autonomously surfaces a small number of high-signal suggestions your AI coding tools can actually use.

Sometimes that means adopting a library as-is. Sometimes it means porting a function or algorithm from a larger project. Sometimes it means cherry-picking a technique, or clean-room building an idea from scratch to stay licence-compliant.

The judgement happens locally, inside your session, against your real code. Your code never leaves your machine.

Replen aims for a few useful suggestions a month. Most days it says nothing. When something real lands, your AI tool can mention it the next time you open the repo, as a short note at the end of its first reply:

By the way, D4Vinci/Scrapling could help your scraper get past Cloudflare. Want the full review?

Brainstem, Watchtower, Atlas

Replen has three parts, and they mostly matter together.

Shortened. The full README is on GitHub.

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

Replen: common questions

Is Replen MCP server safe?
Mostly: it is graded B (80/100). Read the Replen safety report
How do I install Replen?
It runs on your machine. Copy the Claude Code, Cursor, VS Code or Claude Desktop config from the install section.
Does Replen need an API key?
Yes. The registry entry asks for DIGEST_TOKEN.
Is Replen maintained?
The last commit was 56 days ago (2026-09-07). The latest release is v1.3.5.
How does Replen compare with other MCP servers?
safety score 80/100 (higher than 60% of 48,273 servers); tools 14 (the typical server has 7); tools that change things 0% (typical: 0%. Fewer write tools means less an agent can break). Full comparison.