What is scopeblind-mcp?

A locally run MCP server that scans, protects, and monitors APIs used by AI coding tools. It is installed and started through the scopeblind-mcp package and includes device-level rate limiting.

Use it to run scopeblind locally, apply device-level limits to API activity, and scan or monitor the APIs connected to AI coding tools.

It helps control and observe API use from coding tools on a device. The description does not provide enough detail to explain its scan results, protection rules, or monitoring interface.

scopeblind-mcp — MCP server for Claude Code and Codex by tomjwxf

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.

Clone the repo

git clone --depth 1 https://github.com/tomjwxf/scopeblind-gateway

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

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.

README.md

[![agentmods](https://agentmods.dev/badge/mcp/tomjwxf/scopeblind-gateway/scopeblind-mcp/github.svg)](https://agentmods.dev/mcp/tomjwxf/scopeblind-gateway/scopeblind-mcp)

Your own site

<a href="https://agentmods.dev/mcp/tomjwxf/scopeblind-gateway/scopeblind-mcp"><img src="https://agentmods.dev/badge/mcp/tomjwxf/scopeblind-gateway/scopeblind-mcp/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/mcp/tomjwxf/scopeblind-gateway/scopeblind-mcp"><img src="https://agentmods.dev/badge/mcp/tomjwxf/scopeblind-gateway/scopeblind-mcp.svg" alt="Reviewed on agentmods" width="80" 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. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Security

Grade A, and why

scopeblind-mcp 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 11d 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.

server.json · 10 lines

What it actually says

{
  "scopeblind-mcp": {
    "command": "npx",
    "args": [
      "-y",
      "scopeblind-mcp"
    ],
    "env": {}
  }
}

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.

11d ago First seen · 10 lines scan A a9bff40a76e8

Subscribe to this mod's changes

scopeblind-mcp is an MCP server published in the GitHub repository tomjwxf/scopeblind-gateway (10 stars, last pushed 2mo ago), licensed MIT. 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.

Backend and APIs Security access-control ai-agent ai-security audit-trail claude-desktop rate-limiting

nodejs-api-docs

An MCP Server for Node.js API documentation. Runs locally from the mcp-server-nodejs-api-docs npm package.

lirantal/ls-mcp · not measured

kafka-schema-registry

MCP server "kafka-schema-registry" as configured in aywengo/kafka-schema-reg-mcp. Runs kafka_schema_registry_unified_mcp.py with python. Needs 3 environment variables to run.

aywengo/kafka-schema-reg-mcp · not measured

ethora-mcp-server

MCP server for the Ethora chat & messaging platform: chat ops, AI agents, RAG, automation. Runs locally from the @ethora/mcp-server npm package. Needs 5 environment variables to run.

dappros/ethora-mcp-server · not measured

mcp-b24

MCP server for Bitrix24 (wraps the Bitrix24 REST API — CRM, Tasks, IM, Disk, Calendar, HR, Smart processes, Mail, Telephony, Workflows, Open Lines, Bots, Document Generator). 43 tools: 870 actions, RU/EN natural-language support, webhook + OAuth 2.0, des. Runs locally from the mcp-b24 npm package.

kostikpenzin/mcp_b24 · not measured

clinic-frontdesk-mcp

MCP server "clinic-frontdesk-mcp" as configured in prashant-cr/Clinic-front-desk-MCP-server. Runs locally from the clinic-frontdesk-mcp Python package.

prashant-cr/Clinic-front-desk-MCP-server · not measured

mandatepay

MCP server "mandatepay" as configured in muhammadashir0/mandatepay. Runs locally from the mandatepay Python package.

muhammadashir0/mandatepay · not measured