Skip to content
Agentmart
Submit a tool

obsify

Local, privacy-preserving PII toolkit over MCP — shape to the model, substance stays local.

Connector by Formative-Sum41 · GitHub account verified by the MCP Registry

IndexedMITLocal (stdio)
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/formative-sum41-obsify

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

Local, privacy-preserving PII toolkit over MCP — shape to the model, substance stays local.

Reviews

Write a review

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 and install config. Checked Oct 25, 2026.

Tools
2 read · 3 write · 0 delete
Secrets
None asked for
Install scripts
Not scanned yet
Runs as
Python package

Tools by what they do 5

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

Read 2 · Look things up without changing anything.

  • scan_pii
  • verify_value_free

Write 3 · Create, change, send or run things.

  • make_synthetic_twin
  • redact_text
  • run_on_real

Files it touches

  • Any path the agent passes to its tools

Tools (5)

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

  • make_synthetic_twin

    Generate a SYNTHETIC TWIN of a real Excel workbook at `path`, written to `out`. Schema (sheets, headers, column types, true row counts) is preserved; every data value is freshly FAKED — no real value is copied. Reason and write your analysis code against the twin; then run it on the real file with run_on_real. Returns the schema summary (safe shape).

  • redact_text

    Return `text` with detected PII replaced by <TYPE> placeholders (e.g. <AU_TFN>, <PERSON>). Deterministic; checksum-validated identifiers and context/precision rules apply so bare numbers are not over-masked. `entities` is an optional PATH to a local `.obsify.entities` file of KNOWN names to hide; matches (incl. variants) are masked as <KNOWN_ENTITY>. If omitted, a nearby `.obsify.entities` is auto-used.

  • run_on_real

    COMPUTE-TO-DATA: execute your Python `code` LOCALLY against the real file at `data_path` (bound to the variable DATA_PATH in your code); the returned `output` is size-capped and **best-effort** PII-masked. The data never enters your context; substance never leaves. **Return AGGREGATES (counts/sums/summaries) via print()** — output masking is defense-in-depth, NOT a guarantee (NER can miss a name in a raw record), so never print raw records or identifiers. The `masking` field carries this caveat with the result. Network is disabled and a timeout applies.

  • scan_pii

    Scan a file or folder for PII and return TYPES + LOCATIONS + COUNTS only — never the detected values. Safe to surface to an LLM: it learns what PII exists and where, without the substance entering context. Recurses into subfolders; skips unreadable files and caps very large sheets, reporting both as notes. `entities` is an optional PATH to a local `.obsify.entities` file (one name per line) of KNOWN names to hide; matches (incl. suffix/abbreviation variants) are reported as KNOWN_ENTITY. If omitted, a nearby `.obsify.entities` is auto-used. The names are read locally and never returned.

  • verify_value_free

    Fail-closed check that `text` contains NONE of `terms` (nor their suffix-normalized / distinctive-token variants). Returns {"value_free": bool} with zero detail on what matched — for verifying an artifact before it leaves the perimeter.

Signals

Stars
0
Forks
0
Open issues
0
Weekly downloads
30
Last commit
Aug 20, 2026 (2 months ago)
Last release
Aug 20, 2026 (2 months ago)
Last package publish
Aug 20, 2026 (2 months ago)

From GitHub (fetched Oct 24, 2026) and the package registry.

Details

Registry name
io.github.Formative-Sum41/obsify
Version
0.2.0
Auth
No auth
Packages
pypi obsify
License
MIT
Repository
github.com/Formative-Sum41/obsify
First seen
Oct 24, 2026
Last checked
Oct 24, 2026
Source
Official MCP Registrygithub-graphql
Cite this page

obsify MCP server. Agent Mart. https://agentmart.dev/connectors/formative-sum41-obsify (last updated 2026-10-24)