Permet aux assistants IA de traiter des fichiers sensibles en fournissant des schémas, des jumeaux synthétiques et un calcul local masqué sans exposer de données PII brutes.
Aussi connu sous Formative-Sum41/obsify
- Étoiles
- 0
- Outils
- —
- Téléchargements, 30 jours
- 110
- Dernière version
- 0.2.0
- Dernier commit
- 20 août 2026
- Licence
- MIT
Qu'est-ce que obsify MCP ?
Permet aux assistants IA de traiter des fichiers sensibles en fournissant des schémas, des jumeaux synthétiques et un calcul local masqué sans exposer de données PII brutes.
Résumé généré à partir du README du projet
À propos du MCP server obsify
Les développeurs travaillant avec des documents confidentiels peuvent utiliser obsify pour permettre aux assistants IA de raisonner sur des données sensibles sans exposer d'informations personnelles identifiables brutes. En utilisant une approche de calcul de données (compute-to-data), le serveur garantit que la substance réelle d'un fichier reste dans votre périmètre local, tandis que le modèle n'interagit qu'avec des schémas, des jumeaux synthétiques ou des résultats masqués. Cela est possible grâce à un MCP server local qui s'exécute comme un sous-processus via stdio, ne nécessitant aucun hébergement distant ni appel réseau lors de l'exécution.
Le serveur fournit des outils spécifiques tels que scan_pii pour identifier les types de données sans révéler les valeurs, make_synthetic_twin pour créer des versions factices mais structurellement fidèles de classeurs Excel, et run_on_real pour exécuter du code écrit par le modèle sur des fichiers réels dans un bac à sable local. Il prend en charge les documents PDF, Excel et Word, en utilisant des expressions régulières, des sommes de contrôle et du NER local pour détecter des entités australiennes comme l'ABN ou le TFN, ainsi que les clés cloud et les chaînes de connexion de bases de données. Les utilisateurs peuvent mettre en place une couche de routage déterministe à l'aide d'un manifeste piloté par des étiquettes pour imposer les moments où un assistant doit éviter les données brutes.
Ce que vous pouvez faire avec
- 1Analyser des feuilles de calcul sans fuite de lignesUne IA peut comprendre la structure d'un grand livre financier en examinant son schéma plutôt que les valeurs sensibles réelles.
- 2Développer du code sur des données factices réalistesUn développeur peut demander à un assistant d'écrire une logique de traitement en utilisant une version synthétique d'un classeur Excel qui conserve la structure réelle mais utilise des valeurs fictives.
- 3Auditer des fichiers pour détecter des identifiants sensiblesDétectez automatiquement si un dossier contient des clés cloud, des jetons API ou des clés privées avant de les traiter.
Extrait du README du projet. Chaque cas d'utilisation est vérifié par rapport à une citation du document.
Comment installer obsify MCP
Formats vérifiés le 10 nov. 2026Ajouter à CursorAjouter à GooseInstaller obsify MCP dans Claude Code
$ claude mcp add obsify -- uvx obsifyInstaller obsify MCP dans Cursor
~/.cursor/mcp.json
{
"mcpServers": {
"obsify": {
"command": "uvx",
"args": [
"obsify"
]
}
}
}Installer obsify MCP dans VS Code
.vscode/mcp.json
{
"servers": {
"obsify": {
"type": "stdio",
"command": "uvx",
"args": [
"obsify"
]
}
}
}Installer obsify MCP dans VS Code CLI
$ code --add-mcp '{"name":"obsify","type":"stdio","command":"uvx","args":["obsify"]}'Installer obsify MCP dans Claude Desktop
claude_desktop_config.json
{
"mcpServers": {
"obsify": {
"command": "uvx",
"args": [
"obsify"
]
}
}
}Installer obsify MCP dans Codex
$ codex mcp add obsify -- uvx obsifyInstaller obsify MCP dans Codex config.toml
~/.codex/config.toml
[mcp_servers.obsify] command = "uvx" args = ["obsify"]
Installer obsify MCP dans Gemini CLI
$ gemini mcp add -s user obsify uvx -- obsifyInstaller obsify MCP dans Gemini settings.json
~/.gemini/settings.json
{
"mcpServers": {
"obsify": {
"command": "uvx",
"args": [
"obsify"
]
}
}
}Vérifications automatisées
Exécuté le 15 nov. 2026Rapport complet →A passé nos vérifications automatisées. Il ne s'agit pas d'un audit de sécurité : lisez le code et donnez au serveur l'accès le plus restreint dont il a besoin. Fonctionnement des vérifications
- Dépôt source lié et accessibleformative-sum41/obsify is public and reachablegithub.com/formative-sum41/obsify ↗Réussi
- Le nom du package correspond au dépôt sourceobsify names formative-sum41/obsify as sourcepypi.org/project/obsify/ ↗Réussi
- Provenance du build (attestation Sigstore)Sigstore attestation for obsifypypi.org/project/obsify/ ↗Réussi
- Licence open source (OSI)MITspdx.org/licenses/MIT.html ↗Réussi
- Commit ou version publiée au cours de l'année écouléeLast commit or release 2026-08-20github.com/formative-sum41/obsify ↗Réussi
- OpenSSF ScorecardNon vérifié
- Nom du package non proche d'un package populaireNo popular package one edit away from obsifyRéussi
- Aucun avis critique dans le package ou ses dépendances80 resolved dependencies checked; no critical advisoryosv.dev ↗Réussi
- Aucune instruction cachée destinée au modèle0 tool descriptions and the README read; no override phrases, credential paths or hidden charactersRéussi
- Les outils destructifs sont étiquetésNon vérifié
- Le point de terminaison distant répond à la poignée de main MCPNon vérifié
README
Voir sur 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.
Questions sur obsify MCP
Comment ajouter obsify MCP à Claude Code ?
Exécutez claude mcp add obsify -- uvx obsify dans votre terminal. Ajoutez --scope user pour le rendre disponible dans tous les projets.
Comment ajouter obsify MCP à Cursor ?
Ouvrez ~/.cursor/mcp.json et ajoutez le serveur sous mcpServers, avec la configuration Cursor indiquée dans la section d'installation ci-dessus.
Les données brutes quittent-elles ma machine ?
Non, le serveur est local et déterministe. Le modèle raisonne sur des schémas et des jumeaux synthétiques tandis que le contenu réel reste en local.
Quels formats de fichiers sont pris en charge ?
Il prend en charge les documents PDF (y compris les tableaux), Excel (.xlsx/.xlsm) et Word (.docx).
Comment gère-t-il les identifiants sensibles ?
Il détecte les clés cloud, les jetons API, les clés privées et les chaînes de connexion de base de données en utilisant des motifs ancrés plutôt que des heuristiques d'entropie afin d'éviter les faux positifs.