Skip to content
Agentmart
Submit a tool

Redacta MCP

Keep patient identifiers out of AI agent context — a local privacy boundary for healthcare agents.

Connector by nickjlamb · GitHub account verified by the MCP Registry

IndexedMIT-0Local (stdio)★ 8
Write a review

Install

Works with Claude Code, Codex, VS Code, Cursor, Windsurf, Claude Desktop. Read the repository before you give any tool access to your data.

npx agentmarket install connector/nickjlamb-redacta-mcp

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Keep patient identifiers out of AI agent context — a local privacy boundary for healthcare agents.

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this server can do and what it asks for, from its tool list, install config and code. Checked Oct 25, 2026.

Tools
5 read · 1 write · 2 delete
Secrets
None asked for
Install scripts
None found
Runs as
Node.js package

Tools by what they do 8

Read from the source code; the running server may list different tools.

Read 5 · Look things up without changing anything.

  • check_output
  • redact
  • reinstate
  • release_to_client
  • self_check

Write 1 · Create, change, send or run things.

  • release_to_file

Delete 2 · Delete, drop, revoke or wipe things.

  • discard_session
  • protect

Network hosts it talks to 7

  • clawhub.ai · found in code
  • github.com · found in code
  • glama.ai · found in code
  • miro.pharmatools.ai · found in code
  • openapi.vercel.sh · found in code
  • pharmatools.ai · found in code
  • railway.com · found in code

Tools (8)

Read from the source code; the running server may differ. Descriptions are the server’s own words; hidden characters are shown as [U+…].

  • check_outputCheck output for leaked identifiersread-only

    Scan generated text for verbatim reappearance of the original values held in a protected session (tolerant of spacing, dashes and case for identifier-like values) and re-tokenise anything found. Returns which token categories leaked — never the raw values — plus the sanitised text and a general self-check. Scope is verbatim reappearance only: paraphrases and inferred identities are not detected.

  • discard_sessionDiscard a protection session

    Delete a session's private mapping immediately instead of waiting for expiry. Idempotent. After this, no restoration is possible for that session.

  • protectProtect text (mapping stays server-side)

    Redact patient identifiers and PII, replacing each distinct value with a labelled token ([NHS_NUMBER_1], [PATIENT_NAME_1], ...). The reversal mapping is kept privately inside the Redacta server and is NEVER included in this response — you receive only the protected text, an opaque session_id for later controlled restoration, a count of what was replaced, and a self-check of possible leftovers. Sessions expire automatically.

  • redactRedact / pseudonymise text (legacy — exposes token map)read-only

    LEGACY: like protect, but returns the token_map (token -> original value) in the response, which places the reversal key in the client and potentially the model context. Kept for backward compatibility and client-managed workflows. Prefer protect, which keeps the mapping server-side.

  • reinstateRe-identify from a client-held token map (legacy)read-only

    LEGACY: reverse a redaction using a token map held by the client (from the legacy redact tool). Restored personal data will appear in this tool result. For session-based restoration that keeps mappings server-side, use protect + release_to_file.

  • release_to_clientRestore identifiers into this conversation (trusted mode)read-only

    WARNING: returns re-identified text directly in the tool result, so restored personal data WILL enter the MCP client and potentially the model context. Only use in trusted environments. This tool is only available because the server operator enabled it (REDACTA_RELEASE=client or both). Prefer release_to_file.

  • release_to_fileRestore identifiers into a local file

    Restore original identifiers into text produced from a protected session, writing the result to a file inside the server's configured release directory (REDACTA_RELEASE_DIR). Returns only a receipt — file path, size, and counts — so restored data never enters the model context. This is the privacy-preserving way to complete the round trip.

  • self_checkSelf-check for residual identifiersread-only

    Scan already-redacted text for anything that still looks like an identifier (long numbers, emails, postcodes, URLs). A second pair of eyes, not a guarantee. Returns a list of possible leftovers to review.

Compare and alternatives

    Featured in

    Signals

    Stars
    8
    Forks
    0
    Open issues
    0
    Last commit
    Oct 6, 2026 (22 days ago)
    Last release
    Oct 6, 2026 (22 days ago)

    From GitHub (fetched Oct 24, 2026).

    Details

    Registry name
    io.github.nickjlamb/redacta-mcp
    Version
    2.1.1
    Auth
    No auth
    Packages
    npm redacta-mcp
    License
    MIT-0
    First seen
    Oct 24, 2026
    Last checked
    Oct 24, 2026

    More from nickjlamb

    Cite this page

    Redacta MCP. Agent Mart. https://agentmart.dev/connectors/nickjlamb-redacta-mcp (last updated 2026-10-24)