Permite que los asistentes de IA procesen archivos sensibles mediante el uso de esquemas, gemelos sintéticos y computación local enmascarada sin exponer PII real.
También conocido como Formative-Sum41/obsify
- Stars
- 0
- Herramientas
- —
- Descargas, 30 días
- 110
- Última versión
- 0.2.0
- Último commit
- 20 ago 2026
- Licencia
- MIT
¿Qué es obsify MCP?
obsify es un MCP server. Permite que los asistentes de IA procesen archivos sensibles mediante el uso de esquemas, gemelos sintéticos y computación local enmascarada sin exponer PII real.
Resumen generado a partir del README del proyecto
Acerca del MCP server de obsify
Los desarrolladores que trabajan con documentos confidenciales pueden usar obsify para permitir que los asistentes de IA razonen sobre datos sensibles sin exponer información de identificación personal (PII) real. Mediante un enfoque de compute-to-data, el servidor garantiza que la sustancia real de un archivo permanezca dentro de tu perímetro local, mientras que el modelo solo interactúa con esquemas, gemelos sintéticos o resultados enmascarados. Esto se logra a través de un MCP server local que se ejecuta como un subproceso vía stdio, sin necesidad de hosting remoto ni llamadas de red en tiempo de ejecución.
El servidor proporciona herramientas específicas como scan_pii para identificar tipos de datos sin revelar valores, make_synthetic_twin para crear versiones falsas pero estructuralmente fieles de libros de Excel, y run_on_real para ejecutar código escrito por el modelo contra archivos reales en un sandbox local. Es compatible con documentos PDF, Excel y Word, utilizando regex, checksums y NER local para detectar entidades australianas como ABN o TFN, así como claves de la nube y cadenas de conexión a bases de datos. Los usuarios pueden configurar una capa de enrutamiento determinista utilizando un manifiesto basado en etiquetas para imponer cuándo un asistente debe evitar los datos reales.
Qué puedes hacer con él
- 1Analizar hojas de cálculo sin filtrar filasUna IA puede entender la estructura de un libro contable financiero analizando su esquema en lugar de los valores sensibles reales.
- 2Desarrollar código con datos falsos realistasUn desarrollador puede pedirle a un asistente que escriba lógica de procesamiento utilizando una versión sintética de un libro de Excel que mantiene la estructura real pero usa valores falsos.
- 3Auditar archivos en busca de credenciales sensiblesDetecta automáticamente si una carpeta contiene claves de la nube, tokens de API o claves privadas antes de procesarlos.
Escrito a partir del README del proyecto. Cada caso de uso se verifica con una cita del mismo.
Cómo instalar obsify MCP
Formatos verificados el 10 nov 2026Añadir a CursorAñadir a GooseInstalar obsify MCP en Claude Code
$ claude mcp add obsify -- uvx obsifyInstalar obsify MCP en Cursor
~/.cursor/mcp.json
{
"mcpServers": {
"obsify": {
"command": "uvx",
"args": [
"obsify"
]
}
}
}Instalar obsify MCP en VS Code
.vscode/mcp.json
{
"servers": {
"obsify": {
"type": "stdio",
"command": "uvx",
"args": [
"obsify"
]
}
}
}Instalar obsify MCP en VS Code CLI
$ code --add-mcp '{"name":"obsify","type":"stdio","command":"uvx","args":["obsify"]}'Instalar obsify MCP en Claude Desktop
claude_desktop_config.json
{
"mcpServers": {
"obsify": {
"command": "uvx",
"args": [
"obsify"
]
}
}
}Instalar obsify MCP en Codex
$ codex mcp add obsify -- uvx obsifyInstalar obsify MCP en Codex config.toml
~/.codex/config.toml
[mcp_servers.obsify] command = "uvx" args = ["obsify"]
Instalar obsify MCP en Gemini CLI
$ gemini mcp add -s user obsify uvx -- obsifyInstalar obsify MCP en Gemini settings.json
~/.gemini/settings.json
{
"mcpServers": {
"obsify": {
"command": "uvx",
"args": [
"obsify"
]
}
}
}Verificaciones automáticas
Ejecutado 15 nov 2026Informe completo →Pasó nuestras verificaciones automáticas. Esto no es una auditoría de seguridad: lee el código y dale al servidor el acceso más limitado que necesite. Cómo funcionan las verificaciones
- Repositorio de origen vinculado y accesibleformative-sum41/obsify is public and reachablegithub.com/formative-sum41/obsify ↗Aprobado
- El paquete indica este repositorio como su origenobsify names formative-sum41/obsify as sourcepypi.org/project/obsify/ ↗Aprobado
- Procedencia de la compilación (atestación de Sigstore)Sigstore attestation for obsifypypi.org/project/obsify/ ↗Aprobado
- Licencia de código abierto (OSI)MITspdx.org/licenses/MIT.html ↗Aprobado
- Commit o lanzamiento en el último añoLast commit or release 2026-08-20github.com/formative-sum41/obsify ↗Aprobado
- OpenSSF ScorecardNo verificado
- El nombre del paquete no es similar a un paquete popularNo popular package one edit away from obsifyAprobado
- No hay avisos críticos en el paquete ni en sus dependencias80 resolved dependencies checked; no critical advisoryosv.dev ↗Aprobado
- Sin instrucciones ocultas para el modelo0 tool descriptions and the README read; no override phrases, credential paths or hidden charactersAprobado
- Las herramientas destructivas están etiquetadasNo verificado
- El endpoint remoto responde al handshake de MCPNo verificado
README
Ver en 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.
Preguntas sobre obsify MCP
¿Cómo agrego obsify MCP a Claude Code?
Ejecuta claude mcp add obsify -- uvx obsify en tu terminal. Añade --scope user para que esté disponible en todos los proyectos.
¿Cómo agrego obsify MCP a Cursor?
Abre ~/.cursor/mcp.json y añade el servidor en mcpServers, usando la configuración de Cursor que se muestra en la sección de instalación de arriba.
¿Los datos originales salen de mi máquina?
No, el servidor es local y determinista. El modelo razona sobre esquemas y gemelos sintéticos mientras que el contenido real permanece local.
¿Qué formatos de archivo son compatibles?
Es compatible con documentos PDF (incluyendo tablas), Excel (.xlsx/.xlsm) y Word (.docx).
¿Cómo gestiona las credenciales sensibles?
Detecta claves de la nube, tokens de API, claves privadas y cadenas de conexión a bases de datos utilizando patrones anclados en lugar de heurísticas de entropía para evitar falsos positivos.