Skip to main content
Glama
dambuchs

redact-pdf-mcp

by dambuchs
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Hybrid

Start a redaction job (does not wait)

redact_pdf

Start a redaction job immediately and return a job ID. Permanently deletes detected PII from PDFs, JPEGs, or PNGs (including scanned documents via OCR) so text cannot be recovered.

Instructions

Start a redaction job and return immediately without waiting. Permanent, irreversible redaction: the sensitive text is deleted from the file, not hidden behind a black rectangle, so it cannot be recovered by copy-paste, "remove object", or text extraction. Handles scanned documents via OCR and detects PII in 100+ languages. Documents are processed on Microsoft Azure in the EU and Switzerland, encrypted in transit and at rest, never used to train AI models, and the original is deleted after processing.

Accepts PDF, JPEG and PNG. Pass a photo or screenshot directly; do NOT convert it to a PDF first, that is handled for you and the output comes back as a redacted PDF either way.

Prefer redact_pdf_and_wait unless you specifically need to fire off several documents in parallel, or the document is large enough that you would rather poll on your own schedule. Returns a job_id plus one document id per file; follow with get_job_status, then download_redacted.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
file_pathYesAbsolute path to the file on this machine. PDF, JPEG and PNG are all accepted — pass an image directly rather than converting it first. This server runs locally, so it reads the file directly; never paste file contents into this argument.
retentionNo"ephemeral" (default) deletes the original after processing and keeps the output only briefly. "studio" keeps the original and the detected masks so a human can review and adjust them at redact-pdf.ai before exporting — use it for high-stakes documents where a person should sign off.
pii_categoriesNoWhich entity types to redact. OMIT this to use the account defaults, which is usually what the user wants — do not pass an empty list, which would mean "redact nothing" and return an unredacted file. Valid values: Person, Email, PhoneNumber, Address, Organization, Date, IBAN, CreditCard.
idempotency_keyNoOptional. By default a key is derived from the file bytes and settings, so repeating an identical call returns the SAME job instead of redacting (and billing) twice. Pass a distinct value here only when you deliberately want a second, separate redaction of the same document.
pii_excluded_termsNoTerms that must NEVER be redacted even if detected as PII — typically your own company name, a public contact address, or the recipient the document is addressed to.
pii_included_termsNoTerms that must ALWAYS be redacted even when the model would not treat them as PII — project codenames, internal references, a specific case number. Matched whole-word and case-insensitive. Wins over excluded terms on conflict.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv0.2.1
    • changedInput schema / properties / file_path / description
      Previous value: -"Absolute path to the PDF (or JPEG/PNG) on this machine. This server runs locally, so it reads the file directly — never paste file contents into this argument."New value: +"Absolute path to the file on this machine. PDF, JPEG and PNG are all accepted — pass an image directly rather than converting it first. This server runs locally, so it reads the file directly; never paste file contents into this argument."
  2. First observedv1.0.0

TDQS

A3.8/5.0
Behavior1/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The description is highly transparent on its own: it states redaction is permanent, irreversible, text is deleted rather than hidden, the original is deleted after processing, and processing occurs on Azure. However, the annotations declare destructiveHint=false, which directly contradicts the description's claims that the tool permanently deletes content and the original file. This is an annotation contradiction and makes the structured safety signal actively misleading.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is longer than average but front-loaded with the key behavior and contains genuinely useful operational information. Some details about encryption and AI training are contextually relevant but not strictly necessary for invoking the tool, so it is not maximally concise.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The description explains the asynchronous nature, accepted file formats, return value (job_id plus document IDs), and the correct follow-up calls (get_job_status, then download_redacted). Since there is no output schema, this return-value guidance is essential and is fully covered. The input schema already documents all parameters in depth, so nothing needed for correct invocation is missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, and the schema already provides detailed, meaningful descriptions for every parameter including idempotency behavior, exclusions, and retention. The tool description adds overall workflow context but not much parameter-level meaning beyond what the schema already states, so baseline 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description opens with a specific verb and resource: 'Start a redaction job and return immediately without waiting.' It clearly distinguishes this tool from redact_pdf_and_wait and describes what the operation does, including the permanent deletion behavior. The scope and behavior are unambiguous.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

It explicitly says to prefer redact_pdf_and_wait unless you need parallel jobs or want to poll on your own schedule, naming the alternative and the conditions for choosing this tool. It also gives concrete input guidance: pass images directly, do not convert them to PDF first.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Deploy Server

Other Tools