pdfnative-mcp

Decrypt a PDF

decrypt_pdf

Idempotent

Decrypt password-protected PDFs with a user or owner password and receive an unencrypted copy. Note that the page tree is rebuilt, so digital signatures and AcroForm fields are not preserved.

Instructions

Emit an UNENCRYPTED copy of an encrypted PDF (RC4 V1–V4, AES-128, AES-256) given password (user or owner; empty user password needs none). CAVEAT: the page tree is rebuilt — signatures and AcroForm are DROPPED. To merely READ an encrypted PDF pass password to inspect_pdf / extract_text / extract_attachments / read_form_fields instead. Never cached.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`password`	No	Password to open the encrypted source (user or owner). Omit only for documents with an empty user password.
`pdfBase64`	Yes	Base64-encoded encrypted PDF to decrypt. NOTE: signatures and AcroForm are dropped (page-tree rebuild).
`outputMode`	No	'base64' (default) returns the PDF inline; 'file' writes it inside the PDFNATIVE_MCP_OUTPUT_DIR sandbox (SECURITY_VIOLATION when the sandbox is not configured).	base64
`outputPath`	No	Required when outputMode='file'. Relative path inside the sandbox; must end with .pdf.

Output Schema

TableJSON Schema

Name	Required	Description
`mode`	Yes
`summary`	No	Tool-specific summary, when produced.
`filePath`	No	Sandboxed absolute path (file mode).
`sizeBytes`	Yes
`diagnostics`	No	PDF/A diagnostics (when includeDiagnostics=true).

Schema Changelog

Changes observed during successful MCP inspections.

Changed5 schema fields changedAug 24, 2026

addedInput schema / properties / outputMode / description

Added value: +"'base64' (default) returns the PDF inline; 'file' writes it inside the PDFNATIVE_MCP_OUTPUT_DIR sandbox (SECURITY_VIOLATION when the sandbox is not configured)."

changedOutput schema / description

Previous value: -"Structured result of a PDF-producing tool. In base64 mode the PDF bytes are delivered out-of-band as an embedded `resource` content block (data: URI), NOT duplicated here, to keep responses token-frugal. In file mode `filePath` is the sandboxed absolute path."New value: +"Result of a PDF-producing tool. base64 mode: the PDF arrives as an embedded `resource` content block (not duplicated here); file mode: `filePath`."

addedOutput schema / properties / diagnostics

Added value: +{
+  "description": "PDF/A diagnostics (when includeDiagnostics=true).",
+  "items": {
+    "additionalProperties": false,
+    "properties": {
+      "code": {
+        "type": "string"
+      },
+      "message": {
+        "type": "string"
+      },
+      "severity": {
+        "enum": [
+          "warning"
+        ],
+        "type": "string"
+      }
+    },
+    "required": [
+      "code",
+      "message",
+      "severity"
+    ],
+    "type": "object"
+  },
+  "type": "array"
+}

changedOutput schema / properties / filePath / description

Previous value: -"Absolute sandboxed file path (when mode='file')."New value: +"Sandboxed absolute path (file mode)."

addedOutput schema / properties / summary

Added value: +{
+  "additionalProperties": true,
+  "description": "Tool-specific summary, when produced.",
+  "type": "object"
+}

Addedv1.6.0Jul 22, 2026

TDQS

A4.7/5.0

Behavior5/5

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

The description discloses important non-obvious behaviors: the page tree is rebuilt, signatures and AcroForm are dropped, and results are never cached. This adds substantial value beyond the annotations, and no contradiction exists with idempotentHint/readOnlyHint.

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

Conciseness5/5

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

Three compact sentences front-load the core purpose, then the critical caveat, then the alternative routes. Each sentence earns its place, and the formatting makes the warning noticeable.

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, together with the fully documented schema, is sufficient for an agent to invoke the tool correctly: it covers supported algorithms, password requirements, the destructive caveat, alternate tools, and output modes are already in the schema. No critical operational context 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%, so the schema already documents all parameters and constraints. The description reiterates the password semantics and caveat, matching the schema but adding no substantial new parameter-level detail.

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 uses a specific verb ('Emit an UNENCRYPTED copy') and clearly identifies the resource (encrypted PDF) and supported encryption types. It also explicitly distinguishes itself from read-only PDF tools, so an agent can tell it apart from siblings like inspect_pdf and extract_text.

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 states exactly when to use this tool versus alternatives: to decrypt by emitting a new copy, and when merely reading an encrypted PDF to pass the password to sibling read tools instead. This gives explicit routing guidance with named alternatives.

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