Developer · Local MCP server
MCP Secret Scrub
Deterministic no-LLM MCP server that scrubs secrets before they reach an agent. Never leaks values.
What the MCP Registry states
The entry as published to the official MCP Registry (read 2026-10-04), latest version.
- Registry name
io.github.sudo-ai-git/mcp-secret-scrub- Version
- 1.0.0
- Status
- Active
- Category
- developer
- Transport
- stdio (local process)
- Package
- PyPI
- Published
- 2026-08-28
- Updated
- 2026-08-28
- Publisher
- sudo-ai-git (GitHub) · 4 servers with pages here
- Namespace
- Namespace verified by the MCP Registry via GitHub (github.com/sudo-ai-git) · how
- Repository
- github.com/sudo-ai-git/mcp-secret-scrub
- Source
- Registry API entry
Packages
| Registry | Package | Version | Transport |
|---|---|---|---|
| PyPI | mcp-secret-scrub | 1.0.0 | stdio |
How to connect MCP Secret Scrub
MCP Secret Scrub runs locally from a Python package published to PyPI: mcp-secret-scrub version 1.0.0. It speaks MCP over stdio, so the client starts it as a program and talks to it through standard input and output. It needs Python; clients usually start it with uvx (from uv) or after pip install - the usual command is uvx mcp-secret-scrub.
In the mcpServers JSON format that many desktop and editor MCP clients read, the entry looks like this (placeholders in angle brackets):
{
"mcpServers": {
"mcp-secret-scrub": {
"command": "uvx",
"args": [
"mcp-secret-scrub"
]
}
}
}Derived from the registry entry, not tested here. What the server does, and on what terms, is set by its publisher; check its repository or website before giving it access to your accounts or files. How to add an MCP server to an assistant · Before you connect
More from sudo-ai-git (GitHub)
| Server | Runs |
|---|---|
| MCP Benchmark HygieneDetect pytest config-leakage that corrupts agent-benchmark grading. Deterministic, no-LLM. | Local · stdio |
| MCP Skill SecAudit agent skills/prompts against 8 supply-chain attack patterns. Deterministic, no-LLM scanner. | Local · stdio |
| MCP Verify ClaimForce evidence-gated, tiered claim reporting (FACT/INFERENCE/SPECULATION). No-LLM. | Local · stdio |
More developer servers
| Server | Runs |
|---|---|
| MCP Safety WardenMCP proxy adding security scanning, behavioral profiling, risk gating, and safe tool call execution. | Local · stdio |
| MCP Sandbox Computer VM for AINamed Docker and Fly Machine sandbox computers with an interactive MCP App dashboard. | Local · stdio |
| MCP Schema DesignerDesign database schemas from natural language, validate SQL, generate migrations and types. | Local · stdio |
| MCP SeatbeltMCP runtime security proxy. Blocks dangerous AI agent tool calls with a policy engine. | Local · stdio |
| MCP Security & Vulnerability AuditorStatic AST security scanner detecting command injection, leaked secrets, and SSRF in MCP tools. | Remote · HTTP, SSELive check: sign-in required |
| MCP SentinelZero-trust MCP security proxy with policy enforcement, PII scrubbing, approvals, and audit trails. | Local · stdio |
| MCP Server AnalyzerMCP server for Python, JavaScript, and TypeScript code analysis with Ruff, ty, Vulture, and Biome. | Local · stdio |
| MCP Server BrowserbaseMCP server for AI web browser automation using Browserbase and Stagehand. | Local · stdio |