agentmods.dev

score-studio

score-studio is an MCP server for Claude Code, Codex, Cursor, Gemini CLI, OpenCode from score-technologies/score-studio-agent-plugins. Its token cost is not measured, scanned A, original, Apache-2.0.

A local connector for Score Studio, a service used for computer-vision workflows, which process and interpret images or video. It runs from an npm package and needs a Score Studio token.

In plain words
What is it for?
It is for operating evidence-gated computer-vision workflows in Score Studio.
Why use it?
It provides the configured connection an agent needs to work with Score Studio.

MCP server for Claude CodeCodexCursorGemini CLIOpenCode

Part of the score-studio plugin — 1 skill, 1 MCP server shipped together

not rated 0 3d ago A scan tokens not measured original Apache-2.0
View the source file score-technologies/score-studio-agent-plugins
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add mcp/score-technologies/score-studio-agent-plugins/score-studio-score-studio
Clone the repo
git clone --depth 1 https://github.com/score-technologies/score-studio-agent-plugins

Made for: Claude Code, Codex, Cursor, Gemini CLI, OpenCode.

Or install score-studio, the plugin that ships this one along with the rest of its 1 skill, 1 MCP server.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for score-studio

README.md
[![agentmods](https://agentmods.dev/badge/mcp/score-technologies/score-studio-agent-plugins/score-studio-score-studio.svg)](https://agentmods.dev/mcp/score-technologies/score-studio-agent-plugins/score-studio-score-studio)
Your own site
<a href="https://agentmods.dev/mcp/score-technologies/score-studio-agent-plugins/score-studio-score-studio"><img src="https://agentmods.dev/badge/mcp/score-technologies/score-studio-agent-plugins/score-studio-score-studio.svg" alt="Measured on agentmods" height="20"></a>
Per session not measured What this adds to a session before it is invoked.
When invoked not measured Not applicable: nothing here is loaded into a session.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Security

Grade A, and why

score-studio scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

plugins/claude/score-studio/.mcp.json · 12 lines

What it actually says

{
  "score-studio": {
    "command": "npx",
    "args": [
      "-y",
      "@score-technologies/score-studio-mcp"
    ],
    "env": {
      "SCORESTUDIO_TOKEN": "${SCORESTUDIO_TOKEN}"
    }
  }
}
Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 4d ago First seen · 12 lines scan A 807283475eef

Subscribe to this mod's changes

score-studio is an MCP server published in the GitHub repository score-technologies/score-studio-agent-plugins (0 stars, last pushed 3d ago), licensed Apache-2.0. Its token cost is not measured: an MCP server costs its tool schemas, not its config file. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Creative and mediachatgpt-pluginclaude-code-plugincomputer-visiongemini-cli-extensionmcpmodel-context-protocol
Related

Other mcp servers, from other repositories

grpvn

MCP server "grpvn" as configured in frane/grpvn. Launched with grpvn serve.

frane/grpvn · not measured

anyapi

MCP server "anyapi", hosted remotely at api.getanyapi.com, as configured in getanyapi-com/skills.

getanyapi-com/skills · not measured

horizon-shield-webmcp

Agent intake desk for property renovation. Read only, CORS open, fail closed, receipts recompute. Remote server at web.horizonshield.dev.

ogasurfproject-jpg/horizon-shield · not measured

hs-audit-app

MCP server "hs-audit-app", hosted remotely at hs-audit-app.oga-surf-project.workers.dev, as configured in ogasurfproject-jpg/horizon-shield.

ogasurfproject-jpg/horizon-shield · not measured

bring-photo-mcp

Add products to Bring! from a photo — MCP for AI recognition, catalog matching, and verified writes. Runs locally from the bring-photo-mcp npm package. Needs 8 environment variables to run.

schnueck/bring-photo-mcp · not measured

toolrouter

MCP server "toolrouter", hosted remotely at api.toolrouter.com, as configured in Humanleap/toolrouter-mcp.

Humanleap/toolrouter-mcp · not measured