Paperless MCP

Search Documents

search_documents

Read-onlyIdempotent

Search your Paperless-NGX archive by full-text query to locate documents. Each hit includes metadata but omits OCR content, notes, and custom field values.

Instructions

Full-text search documents.

Per-hit OCR content is stripped. Use get_document_content for a bounded preview of one hit. Use more_like for similarity search.

notes[].note and custom_fields[].value are always stripped from search hits; fetch them via get_document or get_document_notes when needed.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`page`	No
`query`	Yes
`more_like`	No
`page_size`	No

Output Schema

TableJSON Schema

Name	Required	Description	Default
`next`	No
`count`	Yes
`results`	No
`previous`	No

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedv2.1.0Sep 21, 2026
- removedInput schema / properties / include_content
```
Removed value: -{
-  "default": false,
-  "type": "boolean"
-}
```
First observedv1.0.1Jul 8, 2026

TDQS

A4.4/5.0

Behavior4/5

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

Annotations already establish the safety profile (readOnlyHint=true, idempotentHint=true, destructiveHint=false), and the description adds genuinely non-obvious behavior on top: per-hit OCR content is stripped, and notes/custom_fields values are 'always' stripped from hits. This is high-value disclosure that annotations cannot express. Minor gaps remain (no mention of result ordering, ranking, or count semantics), but the critical quirks are covered.

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?

Four short, information-dense sentences with zero fluff. Purpose is front-loaded, followed by the OCR-content stripping warning and routing, then the always-stripped field warning. Paragraph breaks group related ideas cleanly and every sentence earns its place.

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

Completeness4/5

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

Given the output schema documents return values and annotations cover the read-only/idempotent safety profile, the description covers the remaining essentials: purpose, sibling routing, and field-stripping behavior. Pagination behavior and exact matching semantics are minor omissions for a moderately simple 4-parameter tool.

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 0%, so the burden is on the description to explain parameters. It adds meaning for more_like ('use for similarity search'), which the schema only types as integer|null. However, query semantics (search syntax, what fields are matched) and page/page_size behavior are left to inference, so compensation is only partial.

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?

"Full-text search documents" uses a specific verb and resource, clearly distinguishing this from list_documents (listing) and get_document/get_document_content (fetching one record). The description further differentiates by naming get_document_content as the preview alternative and get_document/get_document_notes as the routes for stripped fields, so an agent can pick the right sibling without opening schemas.

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?

Explicit routing guidance is given: use get_document_content for a bounded preview of one hit, use more_like for similarity search, and fetch stripped notes/custom fields via get_document or get_document_notes. Conditional alternatives are named concretely rather than left to inference.

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

Deploy Server