MCP.Market

obsify MCP server

by Formative-Sum41·io.github.Formative-Sum41/obsify·v0.2.0
No reviews yet

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

A88/100grade A
Write a reviewInstall
What users say
No reviews yet
Be the first
Safety scan
A88/100

full report

Adoption
New

0 stars26 downloads/wk

Reviews

Write one

Nobody has reviewed obsify yet.

If you have run it, two minutes of your experience saves the next person an afternoon.

obsify tools (5, 1 write)

write = sends, deletes, buys or posts

Read from the package source without running it. The installed server may list more.

  • 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.

  • run_on_realwrite action

    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 i

  • 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.

  • 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.

Public scan report

scanner v0.1.10 · 2026-11-02 · same rubric, same numbers if you re-run it

no findings
  • Code scan22 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 74 days ago12/15
  • Maintainer identityregistry namespace matches repository owner; GitHub account older than a year8/10
Overall 88/100. Components that don't apply are left out of the denominator. Any critical finding is an F.RubricAppeal a findingJSON

How obsify 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
5
the typical AI and agents server has 6
Tools that change things
20%
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 · 1 create · 1 run or deploy

Install obsify in Claude Code, Cursor or VS Code

claude mcp add obsify -- uvx obsify
Add to Cursor

What the publisher says

From the obsify repository's README, as published. We do not edit it. Read it on GitHub

obsify

<!-- mcp-name: io.github.Formative-Sum41/obsify -->

Let an AI assistant work on sensitive files without their raw values ever entering the model's context.

obsify is a local, deterministic MCP server. The frontier model reasons over shape — schemas, synthetic twins, masked feedback — while deterministic local code touches the substance and returns only masked, aggregated results. No LLM calls, no network at runtime: detection is regex + checksums + dictionaries + Presidio's local NER.

It ships with Australian entity support (ABN / ACN / TFN, checksum-validated), credential/secret detection (cloud keys, API tokens, private keys, DB connection strings), and a label-driven routing layer that makes "when should the assistant avoid raw data" a deterministic, enforced decision rather than a judgement call.

Honest scope: runonreal executes model-written code in a best-effort local sandbox

and masks its output best-effort. It is not a jail. Read SECURITY.md before

pointing it at anything you cannot afford to leak. Return aggregates.

Why

Feeding confidential documents to a hosted LLM means the substance leaves your perimeter. The usual answers are "don't use the LLM" or "trust the provider." obsify takes a third path — compute-to-data: bring the code to the data, not the data to the model.

  • The model sees the schema of a spreadsheet, not its rows.
  • The model develops against a synthetic twin (faked values, real structure).
  • The model's analysis code runs locally; only masked, aggregated output returns.

The frontier model's reasoning is preserved. Only its eyes on raw values are removed.

Tools

Supported documents: PDF (text + tables; complex-table fallback via obsify[tables]), Excel .xlsx/.xlsm, and Word .docx (paragraphs + tables). Unreadable or unsupported files are surfaced as explicit notes/blind spots, never silently dropped. (No OCR yet — scanned/image pages are flagged as low-coverage, not transcribed.)

Known-entity masking (optional). Supply a local .obsify.entities list of names to hide; scanpii / redacttext deterministically catch them — and the suffix/abbreviation variants NER misses (BRIGHTWATER HLDGS P/L for Brightwater Holdings Pty Ltd) — as KNOWNENTITY. The list stays local and never enters the model's context. See docs/knownentities.md.

Demo

Poke at all five tools live against synthetic data with the official MCP Inspector:

python -m obsify.make_corpus --out ./corpus_demo
npx @modelcontextprotocol/inspector obsify-mcp

Shortened. The full README is on GitHub.

Nothing above is checked by us. What we check is on the safety report.

obsify: common questions

Is obsify MCP server safe?
Yes, by our scan: it is graded A (88/100). Read the obsify safety report
How do I install obsify?
It runs on your machine. Copy the Claude Code, Cursor, VS Code or Claude Desktop config from the install section.
Does obsify need an API key?
Not as far as the registry entry and our scan can tell: no credentials are declared or required.
Is obsify maintained?
The last commit was 76 days ago (2026-08-20). The latest release is v0.2.0.
What can I use instead of obsify?
Servers from other publishers that do the same job: Serena MCP: the IDE for your agent MCP server, agent-device MCP server and Pm Claude Skills MCP server.
How does obsify compare with other AI and agents MCP servers?
safety score 88/100 (higher than 80% of 4,460 AI and agents servers); tools 5 (the typical AI and agents server has 6); tools that change things 20% (typical: 0%. Fewer write tools means less an agent can break). Full comparison.

Alternatives to obsify

Same job from other publishers: the closest match first, then the best rated.

  • Serena MCP: the IDE for your agent
    A powerful toolkit for coding, providing semantic retrieval and editing capabilities.
    C
  • agent-device
    Open source device layer for AI agents: control mobile, web, TV, and desktop apps over MCP
    A
  • Pm Claude Skills
    1310 professional Agent Skills + workflow recipes — searchable & fetchable over MCP.
    A
  • Mockserver
    Mock, record/replay, verify and chaos-test any HTTP, REST, gRPC or LLM dependency over MCP.
    A
  • CHAP Coordinator
    Auditable records of human decisions over AI agent work. Approvals, edits, overrides, escalations.
    A