Skip to main content
Glama
pdfdotco

PDF.co MCP Server

Official
by pdfdotco
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Remote

pdf_to_text

Converts PDFs and scanned images into text while preserving layout, enabling extraction of readable content from documents via OCR.

Instructions

Convert PDF and scanned images to text with layout preserved.
Ref: https://developer.pdf.co/api/pdf-to-text/basic.md

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
urlYesURL to the source file. Supports publicly accessible links including Google Drive, Dropbox, PDF.co Built-In Files Storage. Use 'upload_file' tool to upload local files.
langNoLanguage for OCR for scanned documents. Default is 'eng'. See PDF.co docs for supported languages. (Optional, Default: 'eng')eng
nameNoFile name for the generated output. (Optional)
rectNoDefines coordinates for extraction (e.g., '51.8,114.8,235.5,204.0'). (Optional)
pagesNoComma-separated page indices (e.g., '0, 1, 2-' or '1, 3-7'). Use '!' for inverted page numbers (e.g., '!0' for last page). Processes all pages if None. (Optional)
unwrapNoUnwrap lines into a single line within table cells when lineGrouping is enabled. Must be true or false. (Optional)
api_keyNoPDF.co API key. If not provided, will use X_API_KEY environment variable. (Optional)
passwordNoPassword of the PDF file. (Optional)
profilesNoExtra engine options for this endpoint as a JSON object encoded in a string. The options differ per endpoint; see https://developer.pdf.co/api/profiles. (Optional)
expirationNoLifetime of the output link in minutes; the output file is deleted afterwards. API default is 60; the maximum depends on the plan. (Optional)
httppasswordNoHTTP auth password if required to access source url. (Optional)
httpusernameNoHTTP auth user name if required to access source url. (Optional)
line_groupingNoEnables line grouping within table cells when set to '1'. (Optional)0

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changedv0.0.11
    • addedInput schema / properties / expiration
      Added value: +{
+  "anyOf": [
+    {
+      "type": "integer"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "description": "Lifetime of the output link in minutes; the output file is deleted afterwards. API default is 60; the maximum depends on the plan. (Optional)",
+  "title": "Expiration"
+}
    • addedInput schema / properties / profiles
      Added value: +{
+  "default": "",
+  "description": "Extra engine options for this endpoint as a JSON object encoded in a string. The options differ per endpoint; see https://developer.pdf.co/api/profiles. (Optional)",
+  "title": "Profiles",
+  "type": "string"
+}
  2. First observed

TDQS

C2.9/5.0
Behavior2/5

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

No annotations exist, so the description carries the full burden, yet it discloses almost nothing behavioral. It never says whether the call is synchronous or a job requiring get_job_check/wait_job_completion (siblings that strongly suggest async), what the return value is (extracted text vs. a temporary output URL), that the output link expires, or that an API key/environment variable is needed — all of which the schema hints at but the description should surface.

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?

Two short sentences, front-loaded with the core capability and followed by a single reference link — no filler. It is efficient, though the reference URL substitutes for content rather than supplementing it.

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

Completeness2/5

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

For a 13-parameter conversion tool with no annotations and no output schema, the description is too thin: it omits the return shape, the async/job flow, OCR handling implications and the expiration behavior of the produced output. An agent could invoke it but could not predict what it gets back or how to retrieve the result.

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 all 13 parameters including lang, pages, rect, unwrap and profiles are already documented in the schema. The description adds no parameter-level meaning beyond that, so the baseline of 3 applies.

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

Purpose4/5

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

States a specific verb+resource ('Convert PDF and scanned images to text') plus a meaningful qualifier ('layout preserved'), which implicitly separates it from format-specific siblings like pdf_to_json, pdf_to_csv and pdf_to_html. It doesn't name an alternative explicitly, so it stops short of full sibling differentiation.

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

Usage Guidelines2/5

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

No guidance on when to pick this over pdf_to_json, pdf_to_csv, pdf_to_html, or pdf_make_searchable, and no prerequisites or exclusions. The only pointer is an external reference URL, which forces the agent to leave the tool definition to decide.

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