Enables AI assistants to process sensitive files by providing schemas, synthetic twins, and local masked computation without exposing raw PII.
Also known as Formative-Sum41/obsify
- Stars
- 0
- Tools
- —
- Downloads, 30 days
- 110
- Latest version
- 0.2.0
- Last commit
- Aug 20, 2026
- License
- MIT
What is obsify MCP?
obsify enables AI assistants to process sensitive files by providing schemas, synthetic twins, and local masked computation without exposing raw PII.
Summary generated from the project's README
About obsify MCP server
Developers working with confidential documents can use obsify to allow AI assistants to reason about sensitive data without exposing raw personally identifiable information. By using a compute-to-data approach, the server ensures that the actual substance of a file stays within your local perimeter while the model only interacts with schemas, synthetic twins, or masked results. This is achieved through a local MCP server that runs as a subprocess via stdio, requiring no remote hosting or network calls at runtime.
The server provides specific tools like scan_pii to identify data types without revealing values, make_synthetic_twin to create fake but structurally faithful versions of Excel workbooks, and run_on_real to execute model-written code against actual files in a local sandbox. It supports PDF, Excel, and Word documents, using regex, checksums, and local NER to detect Australian entities like ABN or TFN, as well as cloud keys and database connection strings. Users can set up a deterministic routing layer using a label-driven manifest to enforce when an assistant must avoid raw data.
What you can do with it
- 1Analyze spreadsheets without leaking rowsAn AI can understand the structure of a financial ledger by looking at its schema instead of the actual sensitive values.
- 2Develop code against realistic fake dataA developer can have an assistant write processing logic using a synthetic version of an Excel workbook that maintains real structure but uses fake values.
- 3Audit files for sensitive credentialsAutomatically detect if a folder contains cloud keys, API tokens, or private keys before processing them.
Written from the project's README. Every use case is checked against a quote from it.
How to install obsify MCP
Formats verified 10 Nov 2026Add to CursorAdd to GooseInstall obsify MCP in Claude Code
$ claude mcp add obsify -- uvx obsifyInstall obsify MCP in Cursor
~/.cursor/mcp.json
{
"mcpServers": {
"obsify": {
"command": "uvx",
"args": [
"obsify"
]
}
}
}Install obsify MCP in VS Code
.vscode/mcp.json
{
"servers": {
"obsify": {
"type": "stdio",
"command": "uvx",
"args": [
"obsify"
]
}
}
}Install obsify MCP in VS Code CLI
$ code --add-mcp '{"name":"obsify","type":"stdio","command":"uvx","args":["obsify"]}'Install obsify MCP in Claude Desktop
claude_desktop_config.json
{
"mcpServers": {
"obsify": {
"command": "uvx",
"args": [
"obsify"
]
}
}
}Install obsify MCP in Codex
$ codex mcp add obsify -- uvx obsifyInstall obsify MCP in Codex config.toml
~/.codex/config.toml
[mcp_servers.obsify] command = "uvx" args = ["obsify"]
Install obsify MCP in Gemini CLI
$ gemini mcp add -s user obsify uvx -- obsifyInstall obsify MCP in Gemini settings.json
~/.gemini/settings.json
{
"mcpServers": {
"obsify": {
"command": "uvx",
"args": [
"obsify"
]
}
}
}Automated checks
Ran Nov 15, 2026Full report →Passed our automated checks. That is not a security audit: read the code and give the server the narrowest access it needs. How checks work
- Source repository linked and reachableformative-sum41/obsify is public and reachablegithub.com/formative-sum41/obsify ↗Pass
- Package names this repository as its sourceobsify names formative-sum41/obsify as sourcepypi.org/project/obsify/ ↗Pass
- Build provenance (Sigstore attestation)Sigstore attestation for obsifypypi.org/project/obsify/ ↗Pass
- Open source license (OSI)MITspdx.org/licenses/MIT.html ↗Pass
- Commit or release in the last yearLast commit or release 2026-08-20github.com/formative-sum41/obsify ↗Pass
- OpenSSF ScorecardNot checked
- Package name not close to a popular packageNo popular package one edit away from obsifyPass
- No critical advisory in the package or its dependencies80 resolved dependencies checked; no critical advisoryosv.dev ↗Pass
- No hidden instructions to the model0 tool descriptions and the README read; no override phrases, credential paths or hidden charactersPass
- Destructive tools are labelledNot checked
- Remote endpoint answers the MCP handshakeNot checked
README
View on GitHubobsify
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:
run_on_realexecutes model-written code in a best-effort local sandbox and masks its output best-effort. It is not a jail. ReadSECURITY.mdbefore 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
| Tool | What it does | Returns |
|---|---|---|
scan_pii(path) |
Scan a file/folder for PII | Types, locations, counts — never values |
make_synthetic_twin(path, out) |
Faithful fake of an Excel workbook | Schema summary; twin written to out (values faked, leak-verified) |
run_on_real(code, data_path) |
Compute-to-data: run your code locally against the real file (bound to DATA_PATH) |
Only PII-masked, size-capped stdout/stderr — return aggregates |
redact_text(text) |
Mask PII in a string to <TYPE> tokens |
The redacted string |
verify_value_free(text, terms) |
Fail-closed check that text leaks none of terms (or their variants) |
{"value_free": bool} |
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;
scan_pii / redact_text deterministically catch them — and the suffix/abbreviation variants
NER misses (BRIGHTWATER HLDGS P/L for Brightwater Holdings Pty Ltd) — as KNOWN_ENTITY. The
list stays local and never enters the model's context. See docs/known_entities.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
Call scan_pii on ./corpus_demo/ledger.xlsx and confirm it returns types / counts /
locations only — never values. See docs/verifying.md.
Try it — synthetic corpus
Generate a fake-but-realistic corpus (all synthetic; ABN/ACN/TFN are checksum-valid) spanning all three formats, then point a tool at it:
pip install "obsify[demo]" # reportlab, for the sample PDFs
python -m obsify.make_corpus --out ./corpus_demo
It writes a multi-sheet Excel ledger (a numeric false-positive minefield), a PDF engagement
letter (prose + trial-balance table), and a DOCX audit memo (paragraphs + vendor table). Great
for kicking the tyres on scan_pii / make_synthetic_twin without touching real data.
Install & run as an MCP server
Requires Python 3.11+. obsify speaks MCP over stdio — the client launches it as a local subprocess; nothing is hosted remotely. Register it with any MCP-capable client (Claude Desktop, Claude Code, Cursor, VS Code, …) by adding one block to that client's config.
Recommended — zero-install via uvx:
{ "mcpServers": { "obsify": { "command": "uvx", "args": ["--from", "obsify", "obsify-mcp"] } } }
uvx fetches obsify from PyPI and runs it on demand — no permanent install. On first run,
obsify downloads the spaCy NER model (en_core_web_lg, ~560 MB) once and caches it; this
fetches a public model and sends no user data (set OBSIFY_AUTO_DOWNLOAD=0 to forbid it and
install the model yourself). Later runs are instant and fully offline.
Or install it (pip / pipx):
pipx install obsify # isolated, on PATH (or: pip install obsify)
Then point the client at the installed command:
{ "mcpServers": { "obsify": { "command": "obsify-mcp" } } }
Restart the client and the tools appear. Optional extras: obsify[tables] (complex-table PDF
fallback via camelot + Ghostscript), obsify[compute] (pandas, handy inside run_on_real code).
PATH gotcha (the #1 cause of "server won't connect"): the
commandmust resolve on the PATH the client sees. A GUI client may not share your venv's PATH. Fixes: useuvx/pipx(globally resolvable), or give an absolute path —"/path/to/.venv/bin/obsify-mcp"(macOS/Linux) or"C:\\path\\to\\.venv\\Scripts\\obsify-mcp.exe"(Windows).
From this repo (before it's on PyPI):
pip install "git+https://github.com/Formative-Sum41/obsify.git" # gets `obsify-mcp` + `obsify`
The routing layer — deterministic, not a judgement call
The hard part of "help me, but don't read the confidential file" is deciding when to protect. obsify moves that decision out of the model and into the environment:
.obsify.json— a label manifest classifying paths (public/confidential/restricted).obsify.guard(run aspython -m obsify.guard) — a PreToolUse guard that blocks a direct read of a labelled file (exit 2) and redirects the assistant toscan_pii/make_synthetic_twin/run_on_real.- A convention (in
CLAUDE.md) so the assistant prefers obsify before it even hits the guard.
Set it up with one command:
obsify init [--dir PATH] [--with-claude-md]
obsify init is non-destructive by design — it owns exactly one file and hands you snippets
for the rest:
.obsify.json— obsify owns this; init writes it (never overwritten without--force)..claude/settings.json— your file: init prints the PreToolUse hook block to paste, never edits it (it runs code, so registering it is your call).CLAUDE.md— your file: the convention is opt-in. Default prints it;--with-claude-mdappends a marker-wrapped, idempotent block that never clobbers your content.
Full convention: docs/obsify_routing.md.
How detection stays precise
- Checksum-validated identifiers. ABN/ACN/TFN candidates are proposed by regex and confirmed by their official checksums, so a random number is never reported as an identifier.
- Context-required IDs. A bare number is only accepted as an ABN/ACN/TFN when a label word ("TFN", "ABN", "BSB", …) is nearby — this kills the sequential-journal-ID false-positive flood on numeric ledgers.
- Letterless / NER-with-digit suppression. Pure numbers, amounts, dates and alnum codes are not flagged as names/orgs; real names, emails and addresses (which carry letters) are unaffected. Validated letterless PII stays exempt: checksum IDs (ABN/ACN/TFN/Medicare), Luhn cards, valid IPs, BSB-adjacent accounts, and phones (via context or phone shape) — while a decimal point still marks an amount, not a phone.
- Credentials, not just PII. Cloud keys (AWS/GitHub/Google/Slack/Stripe), JWTs, private-key
blocks and DB connection strings are flagged as
CREDENTIALby anchored patterns — vendor prefixes (AKIA…,ghp_…) or a keyword-gatedsecret = <value>, never entropy heuristics (which would flood on hex/base64 ledger columns). The wholeBEGIN…ENDprivate-key block is masked, not just its header, so no key body is left behind.
Measured accuracy
obsify ships a scored evaluation harness (eval/ — labelled synthetic corpus + answer key +
scorer against the shipping detector, plus an independent third-party cross-check). Headline
on the synthetic corpus: 100% recall on expected-detect items, 0 false positives on a
numeric FP-torture sheet (with a grouped-number guard), bare context-gated IDs correctly
suppressed. Independent cross-check vs Microsoft presidio-research: EMAIL/IBAN 100%, PERSON 94%.
The harness earned its keep — it found real defects, which were then fixed: credit cards and
phone numbers were being silently suppressed by the numeric-noise filter (now exempt via checksum
validation / phone shape), and Medicare, IP, date-of-birth, AU passport and driver-licence had no
recognizer (now added, checksum- or context-gated). Full method, numbers, and remaining documented
gaps (SWIFT/BIC, non-DOB dates): eval/README.md.
Tests
pip install -e ".[dev]"
pytest tests/ # or run any file directly: python tests/test_obsify.py
Thirteen suites (88 tests), run in CI on Linux + Windows / Python 3.11 + 3.12:
- mcp-protocol — launches the real server over stdio and speaks MCP to it (the same path a
client like Claude uses): confirms all five tools register with valid schemas and that calls
round-trip through JSON-RPC — including
scan_piireturning shape only, end to end. - checksums — anchored to externally-published ABN/ACN/TFN worked examples (valid and corrupted), which breaks the generator↔validator circularity.
- obsify / twin / redaction — the privacy invariants: shape-only output, leak-free twins, and a fail-closed self-check.
- precision — the false-positive suppressors kill numeric-ledger noise while keeping real names.
- credentials — the anchored secret patterns catch cloud keys / tokens / JWTs / private-key blocks / connection strings, while keyword-anchored generics stay precise on prose (no entropy).
- routing — the guard's block/allow classification and
obsify init's non-destructive contract. - corpus — the synthetic PDF+Excel+DOCX corpus end to end: per-format detection, DOCX paragraph+table extraction, and shape-only output across every format.
- evaluation — the scored harness as a regression gate (recall, suppression, FP-torture, gaps).
- robustness — graceful degradation: corrupt/oversized/empty/nested/unsupported inputs never crash and are always surfaced as notes.
- model / variants — first-run model auto-download logic; variant normalization behind
verify_value_free.
For interactive verification (MCP Inspector) and the live-client last-mile check, see
docs/verifying.md.
Related work
obsify is one of several MCP servers tackling "let an AI touch sensitive data safely" — they're mostly complementary, solving the same problem from different ends. Worth knowing where each fits:
| Tool | Approach | Best for |
|---|---|---|
| obsify | Detection + shape-isolation: the model sees only shape, synthetic twins and masked aggregates — never the values (real or faked) | Messy, unstructured docs (PDF/Excel/DOCX) where you can't enumerate PII up front; strict value isolation; enforcement of when to protect |
| cloakbox | Policy-driven pre-sanitization: tokenize a database into a de-identified copy the model queries freely | Known, structured schemas where you want rich analytics (joins/aggregations) on a referentially-intact clean copy |
| redact-mcp | Reversible obfuscation proxy: the model works on consistent fakes; a proxy tool round-trips real API calls | Pentest workflows and secrets, where the model must operate on realistic data and you restore reals later |
| cms-ai | Enterprise redaction service: Presidio + spaCy behind REST/MCP, multi-language, scalable | A hosted, multi-language redaction API with a UI and horizontal scale |
Where obsify is distinct: it's the only one of these where the model gets neither raw values nor a full mirror to operate on — just shape + masked aggregates — combined with checksum-validated identifiers, credential detection, a deterministic routing guard, and a hard no-network / no-LLM guarantee. That's the strictest-isolation end of the spectrum, tuned for confidential financial documents.
Honest trade: obsify optimizes isolation of the values over utility on the data. If you need referentially-intact analytics on a clean copy (cloakbox), reversible round-tripping (redact-mcp), or a multi-language hosted service (cms-ai), those are the better fit — and pair well with obsify rather than competing with it.
Contributing
PRs welcome — see CONTRIBUTING.md for setup, the merge bar, and the
non-negotiable invariants (no LLM calls in the library, no runtime network, no real data,
shape-not-substance). Security issues: SECURITY.md (report privately).
License
MIT — see LICENSE.
obsify MCP questions
How do I add obsify MCP to Claude Code?
Run claude mcp add obsify -- uvx obsify in your terminal. Add --scope user to make it available in every project.
How do I add obsify MCP to Cursor?
Open ~/.cursor/mcp.json and add the server under mcpServers, using the Cursor config shown in the install section above.
Does the raw data leave my machine?
No, the server is local and deterministic. The model reasons over schemas and synthetic twins while the substance stays local.
What file formats are supported?
It supports PDF (including tables), Excel (.xlsx/.xlsm), and Word (.docx) documents.
How does it handle sensitive credentials?
It detects cloud keys, API tokens, private keys, and DB connection strings using anchored patterns rather than entropy heuristics to avoid false positives.