AgentArmorHQ
Sign in

Capri-AI

MCP server · GitHub · ★ 286 · graded 2026-10-31Source linked

⚡ Tell your PC what to do. Capri is a cyberpunk AI agent that works with your files, projects and code through Claude Code, Codex or Antigravity. Windows installer, no terminal. Fan-made, not affiliated with CD PROJEKT RED.

Not matched to a published package yet

Capri-AI runs shell or system commands; restrict its folder reach, network access, and credentials before installing.

Based on public adoption and transparency signals as of Oct 31, 2026. Our opinion, not a code audit or security guarantee.

Was this verdict for Capri-AI helpful?

What it can access

  • Local filesNo local folder access notedLOW
  • Command executionRuns shell or system commandsREVIEW
  • Network reachLocal or standard API callsLOW
  • CredentialsNo API token requiredLOW
  • Package sourceGitHub (boardshogunfluctuate/Capri-AI)PUBLIC

Inferred from this listing’s public package details and description. Check the project’s source before installing.

Install

No npm or PyPI package is listed. Install from source: github.com/boardshogunfluctuate/Capri-AI ↗

All setup options ↓

Check this skillWatch it in my stackCompareREADME badgeView project

Everything known

We have not matched this listing to a published package, so we cannot say whether outside reports exist for it. Reports that name its GitHub project would be listed here.

Popularity grade: C (from public signals such as stars and downloads, not a code review). Graded 2026-10-31.

Sources we read: OSV, GitHub Advisory Database, CISA Known Exploited Vulnerabilities, 44 security news feeds and our incident library. Last checked 2026-10-31.

Check a specific version →

About Capri-AI

Capri-AI is an MCP server focused on Developer tools and Files & documents: ⚡ Tell your PC what to do. Capri is a cyberpunk AI agent that works with your files, projects and code through Claude Code, Codex or Antigravity. Windows installer, no terminal. Fan-made, not affiliated with CD PROJEKT RED.

It is hosted on GitHub at boardshogunfluctuate/Capri-AI (286 GitHub stars). Based on its public metadata, its operational scope includes: runs shell or system commands.

Setup

These use the package this listing points to. Check the project’s own instructions before running anything.

No npm or PyPI package is listed for this MCP server. Source code and setup steps: github.com/boardshogunfluctuate/Capri-AI.

Why this grade

CC — Moderate risk signals

Signal-based grade (2/7 points): public source code. This reflects adoption and transparency, not a code review.

Popularity and upkeep

27/100
GitHub stars
286
Listing last refreshed
2026-10-31

These are public popularity signals, not a maintenance check. Look at the repository’s commit history and open issues.

Risks to watch for

  • Command execution reach: Public metadata indicates shell, terminal, or container command execution. Run inside an isolated container or VM and require human approval before executing commands.
  • Dependency & version pinning: Distributed via GitHub (boardshogunfluctuate/Capri-AI). Pin an exact release version or commit SHA rather than floating tags so upstream updates are reviewed first.

How to lower the risk

Least-privilege permissions

  • Give it access only to the specific folders, accounts or projects it needs, never your whole drive or admin account.
  • Use a separate, limited API key or login just for this tool so you can switch it off without affecting anything else.

Network isolation

  • Run it on a work computer or sandbox account, not one holding personal or company-sensitive data.
  • If your IT team can, limit which websites and services it is allowed to contact.

Monitoring

  • Check its activity history or logs weekly at first, and look at what it changed or sent.
  • Turn on alerts for new logins or unusual usage on any account it connects to.

Red flags to watch for

  • It asks for more access than its job requires, or prompts you to paste passwords.
  • It suddenly updates with new owners, or starts contacting unfamiliar websites.

Questions

How do I install Capri-AI?

We have not matched this listing to a published package. Follow the setup steps in its source repository at github.com/boardshogunfluctuate/Capri-AI.

Are there security reports about Capri-AI?

We have not matched this listing to a published package, so this page cannot say whether outside reports exist. Capri-AI currently holds Grade C (Moderate risk signals) based on public adoption and transparency signals. Review the permissions and source repository before granting access to local files, shell commands, or API keys.

Is Capri-AI actively maintained?

Capri-AI has 286 GitHub stars. Our directory data was last refreshed on 2026-10-31. Check recent commit activity, release tags, and open issues at github.com/boardshogunfluctuate/Capri-AI before pinning it in production.

What are alternatives to Capri-AI?

Compare Capri-AI side by side with similar MCP servers in the Related tools section on this page, or browse all MCP servers on AgentArmorHQ.

README badge and team notes

Maintain or use Capri-AI? Show its live grade in your GitHub README, docs site, or run a check from the terminal before you install.

AgentArmorHQ Risk Grade C for Capri-AI

GitHub README Markdown:

markdown
[![AgentArmorHQ Risk Grade for Capri-AI](https://agentarmorhq.com/api/badge/boardshogunfluctuate-capri-ai)](https://agentarmorhq.com/skills/boardshogunfluctuate-capri-ai)

HTML embed:

html
<a href="https://agentarmorhq.com/skills/boardshogunfluctuate-capri-ai"><img src="https://agentarmorhq.com/api/badge/boardshogunfluctuate-capri-ai" alt="AgentArmorHQ Risk Grade for Capri-AI" height="20" /></a>

Terminal check:

terminal
curl -fsSL https://agentarmorhq.com/api/cli | node --input-type=module - check "boardshogunfluctuate-capri-ai"

Share with your security lead

Need sign-off to use Capri-AI? Copy this note for Slack, a ticket or a pull request.

### AgentArmorHQ Security Review Memo: Capri-AI
- **Listing URL:** https://agentarmorhq.com/skills/boardshogunfluctuate-capri-ai
- **Type:** App connector
- **Risk Grade:** Grade C (Moderate risk signals)
- **Outside Security Advisories on File:** 0
- **Public Adoption:** 286 GitHub stars

#### Permission & Blast-Radius Signals
- **Local files:** No local folder access noted
- **Command execution:** Runs shell or system commands
- **Network reach:** Local or standard API calls
- **Credentials:** No API token required
- **Package source:** GitHub (boardshogunfluctuate/Capri-AI)

#### Recommended Hardened Setup
- **Source Repo:** https://github.com/boardshogunfluctuate/Capri-AI
- **Controls:** Pin an exact version in `.mcp.json`, scope access to a single workspace folder, and use a least-privilege read-only token where supported.

_Based on public adoption and transparency signals as of Oct 31, 2026. Our opinion, not a code audit or security guarantee._

Key facts

Type
App connector
Publisher
boardshogunfluctuate
Source code
github.com/boardshogunfluctuate/Capri-AI
Est. context load
~900 tokens / turn (~5 tool schemas, 0.45% of 200k context)
Popularity
286 GitHub stars
Last updated
2026-10-31
Last graded
2026-10-31

Community

Discussions for Capri-AI

Ask questions or share configuration tips. Governed by our Community Rules & Terms.

No posts match this filter yet.

Be the first to ask a question or share a working tip.

Was this listing for Capri-AI helpful?

Check before you install, in Claude

Your assistant answers Block, Review or No known issues for any package before it installs it.

Get this check inside ClaudeWatch for bad updates