Secret Scrub MCP server
Deterministic no-LLM MCP server that scrubs secrets before they reach an agent. Never leaks values.
0 stars19 downloads/wk
Reviews
Write oneNobody has reviewed Secret Scrub yet.
If you have run it, two minutes of your experience saves the next person an afternoon.
Secret Scrub tools (4)
write = sends, deletes, buys or postsRead from the package source without running it. The installed server may list more.
report_fullscan + redact in one call: scrubbed preview + findings report.
scan_textDetect which secret types are present in text WITHOUT modifying it. Returns types + counts, never the values.
scrub_textDetect and redact/mask/hash secrets in text before it enters agent context or logs. Returns scrubbed text — never the secret value.
secret_profilesList all supported secret detection profiles (type labels).
Public scan report
scanner v0.1.10 · 2026-10-30 · same rubric, same numbers if you re-run it
- Code scan2 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 qualitylocal package, no credentials required12/15
- Maintenancelast push 64 days ago12/15
- Maintainer identityregistry namespace matches repository owner; GitHub account older than a year8/10
How Secret Scrub compares
Against every graded AI and agents MCP server, from our own scans and uptime checks. Updated after each scan run.
- Safety score
- 88/100
- higher than 80% of 4,460 AI and agents servers
- Tools
- 4
- the typical AI and agents server has 6
- Tools that change things
- 0%
- typical: 0%. Fewer write tools means less an agent can break
- Downloads a week
- 19
- more than 5% of 1,538 AI and agents servers with a package
What its tools let an agent do: 4 read
Install Secret Scrub in Claude Code, Cursor or VS Code
claude mcp add mcp-secret-scrub -- uvx mcp-secret-scrub
What the publisher says
From the Secret Scrub repository's README, as published. We do not edit it. Read it on GitHub
mcp-secret-scrub
mcp-name: io.github.sudo-ai-git/mcp-secret-scrub
Deterministic, no-LLM MCP server that scrubs secrets from text, logs, and transcripts before they enter agent context — and never leaks the value.
No LLM. No network. Pure structural detection. MIT. Crown-jewel-free.
The problem it solves
Before you hand raw text to an agent (or store it, or pass it to a tool), you often don't know whether it contains a live secret. Platform scrubbers miss patterns all the time — a private key, an nvapi- token, a githubpat token, an api_key= assignment mid-log. If that text reaches an LLM context or a persisted transcript, the secret is effectively exfiltrated.
This server answers, deterministically:
*Which secrets are in this text, and can you redact them safely before it
goes anywhere?*
Detection coverage (deterministic profiles)
The scan never returns the secret value — only its type, count, and position. That is a hard safety contract, enforced by test.
Tools (MCP)
Modes:
- redact (default) → [REDACTED:TYPE]
- mask → shows first 4 + last 2 chars
- hash → deterministic SHA-256 prefix (reproducible across calls)
Quick start (stdio)
pip install mcp-secret-scrub
mcp-secret-scrub # stdio (default)Or via uv/pipx for an installable console entry:
pipx install mcp-secret-scrubMCP client config:
{ "mcpServers": {
"secret-scrub": { "command": "mcp-secret-scrub" }
}}Streamable HTTP (remote / Smithery-publishable)
python3 mcp_server.py --http --port 8138 # serves on http://<host>:8138/mcp/Determinism & safety guarantees
deterministichash is SHA-256 (no salt) so output is reproducible.
- Deterministic: same input → identical output in every mode, every call.
- Never leaks: scantext and scrubtext never emit the original token;
- No LLM, no network: pure regex + reachable structure detection.
- Input-safe: non-string input returns a clean error, not a traceback.
Verification
determinism, no-leak contract, benign/unicode/empty input, bad-mode)
- python3 test_detector.py — 14/14 core checks (detection, redaction,
the secret does NOT cross the wire
- python3 test_e2e.py — drives the real MCP stdio transport and asserts
License & provenance
MIT. Part of the sudo-ai-git deterministic no-LLM agent-trust MCP family (mcp-skill-sec · mcp-verify-claim · mcp-benchmark-hygiene · mcp-secret-scrub).
Nothing above is checked by us. What we check is on the safety report.
Secret Scrub: common questions
- Is Secret Scrub MCP server safe?
- Yes, by our scan: it is graded A (88/100). Read the Secret Scrub safety report
- How do I install Secret Scrub?
- It runs on your machine. Copy the Claude Code, Cursor, VS Code or Claude Desktop config from the install section.
- Does Secret Scrub need an API key?
- Not as far as the registry entry and our scan can tell: no credentials are declared or required.
- Is Secret Scrub maintained?
- The last commit was 68 days ago (2026-08-28). The latest release is v1.0.0.
- What can I use instead of Secret Scrub?
- Servers from other publishers that do the same job: Decionis MCP server and three.ws Portfolio MCP server.
- How does Secret Scrub compare with other AI and agents MCP servers?
- safety score 88/100 (higher than 80% of 4,460 AI and agents servers); tools 4 (the typical AI and agents server has 6); tools that change things 0% (typical: 0%. Fewer write tools means less an agent can break). Full comparison.
Alternatives to Secret Scrub
Same job from other publishers: the closest match first, then the best rated.
- DecionisAuthorize consequential AI agent actions before executionnot reviewedEstablishedA
- three.ws PortfolioAn agent's trading state — portfolio value, PnL, live balances, trade feed, and signed transfers.not reviewedEstablishedB