Umbryn MCP server
io.github.Rinava/umbryn-mcp·v0.2.1Redacts PII/PHI from text before it reaches an LLM. Fail-closed, self-hosted, no egress.
0 stars26 downloads/wk
Reviews
Write oneNobody has reviewed Umbryn yet.
If you have run it, two minutes of your experience saves the next person an afternoon.
Umbryn tools (3)
write = sends, deletes, buys or postsRead from the package source without running it. The installed server may list more.
detectReport the PHI/PII entities found in text without modifying it.
redactReplace PHI/PII in text with reversible typed placeholders.
restoreReverse a redaction using its token map, recovering the original text.
Public scan report
scanner v0.1.10 · 2026-11-03 · same rubric, same numbers if you re-run it
- Code scan21 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 82 days ago12/15
- Maintainer identityregistry namespace matches repository owner; GitHub account older than a year8/10
How Umbryn 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
- 3
- 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
- 26
- more than 12% of 1,538 AI and agents servers with a package
What its tools let an agent do: 3 read
Install Umbryn in Claude Code, Cursor or VS Code
claude mcp add umbryn-mcp -- uvx umbryn-mcp
What the publisher says
From the Umbryn repository's README, as published. We do not edit it. Read it on GitHub
<!-- mcp-name: io.github.Rinava/umbryn-mcp -->
umbryn-mcp
An MCP server that redacts PII/PHI from text before it ever reaches an LLM — self-hosted, fail-closed, and HIPAA-aware.
Teams building LLM and agent pipelines in regulated domains have no clean, drop-in way to strip PHI/PII from a payload before it crosses into a model provider's infrastructure. umbryn-mcp is that boundary: three MCP tools — redact, restore, detect — that scrub sensitive values into reversible placeholders, run entirely inside infrastructure you control, and block the request if detection is uncertain instead of leaking data.
redact("Patient MRN: 1234567, provider NPI 1234567893, ssn 078-05-1120, john.doe@example.com")
redacted_text (safe to send to the model):
"Patient MRN: [MEDICAL_RECORD_NUMBER_1], provider NPI [NPI_1], ssn [US_SSN_1], [EMAIL_ADDRESS_1]"
token_map (kept local, never sent to the model):
[MEDICAL_RECORD_NUMBER_1] → 1234567
[NPI_1] → 1234567893
[US_SSN_1] → 078-05-1120
[EMAIL_ADDRESS_1] → john.doe@example.comSend the redacted text to the model; keep the tokenmap local; call restore afterward to rehydrate the result. Round-trips are byte-exact** and proven with property-based tests.
Why this exists
The PHI/PII-redaction MCP niche is real but underserved — the existing options are thin Presidio wrappers with no HIPAA-specific detection and, critically, no guarantee that a detection failure blocks the request instead of silently passing raw data through. So teams either roll their own boundary or ship sensitive data to a provider and lean on a BAA to cover it — the design-time mistake that causes real compliance incidents.
Why it was built: MCP went mainstream fast — it's now first-class in Claude, Cursor, and ChatGPT, across thousands of servers — but the PHI/PII-redaction corner was left to a few unmaintained wrappers. This fills that gap with a single honest, auditable, fail-closed boundary, kept open source so the redaction logic you depend on is fully inspectable rather than a black box.
Features
Shortened. The full README is on GitHub.
Nothing above is checked by us. What we check is on the safety report.
Umbryn: common questions
- Is Umbryn MCP server safe?
- Yes, by our scan: it is graded A (88/100). Read the Umbryn safety report
- How do I install Umbryn?
- It runs on your machine. Copy the Claude Code, Cursor, VS Code or Claude Desktop config from the install section.
- Does Umbryn need an API key?
- No secret keys are declared. It reads 3 settings from the environment.
- Is Umbryn maintained?
- The last commit was 82 days ago (2026-08-13). The latest release is v0.2.1.
- What can I use instead of Umbryn?
- Servers from other publishers that do the same job: PaperBanana MCP server, Decionis MCP server and SuperCompress MCP server.
- How does Umbryn compare with other AI and agents MCP servers?
- safety score 88/100 (higher than 80% of 4,460 AI and agents servers); tools 3 (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 Umbryn
Same job from other publishers: the closest match first, then the best rated.
- PaperBananaGenerate academic diagrams and statistical plots from text using multi-agent AI.not reviewedEstablishedA
- DecionisAuthorize consequential AI agent actions before executionnot reviewedEstablishedA
- SuperCompressCompress coding-agent context ~64%. Hosted Neural Keep MCP for Cursor/Claude/Codex.not reviewedEstablishedB
- Agent SniperSelf-custodial pump.fun sniper: arm strategies, snipe, manage positions. Simulate by default.not reviewedEstablishedB
- Mnemoverse MemoryHosted agent memory that learns from outcomes, with shared rooms. No key: mcp.mnemoverse.com/mcpnot reviewedEstablishedA