DocForge Data Extraction

Server Details

DocForge turns documents into structured data. Upload a PDF, image, or Office file and get fielded JSON back with per-field confidence scores. 95 templates (invoices, receipts, bank statements, ID docs), custom JSON Schema mode, auto-detect, natural-language instructions. Keyless demo tool included. Free 7-day trial.

Ownership verified

Glama couldn't complete the latest health check. If this server requires authentication, missing or expired test credentials may be the cause. A test profile lets Glama authenticate for health checks and discover tools; it is separate from your personal connections.

If you are the author, claim ownership, then add or update a test profile under Admin → Test Profile.

Status: Unhealthy
Uptime: 6.8% over 40 days
Last Tested: 2026-09-26 09:20
Transport: Streamable HTTP
URL

TDQS

A3.9/5.0

Scored 2026-08-18 04:40 across 6 tools

Disambiguation2/5

docforge_extract_url is explicitly marked as a compatibility alias and recommends using docforge_extract instead, creating direct overlap. This redundancy makes it unclear which tool to use and adds confusion. All other tools are distinct, but this one degrades the overall disambiguation.

Naming Consistency3/5

All tools share the consistent 'docforge_' prefix. The suffixes are descriptive nouns (account, demo, extract, status, templates), but 'extract_url' is a variant of 'extract', breaking the pattern slightly. Overall naming is readable but not perfectly uniform.

Tool Count5/5

Six tools is an appropriate size for a data extraction service. It covers core functionality without being overwhelming or too thin. Each tool has a clear purpose except for the redundant alias.

Completeness4/5

The tool set covers the main extraction workflow (demo, full extraction, status polling), account management, and template listing. The redundant docforge_extract_url occupies a slot that could be eliminated, but it does not create a significant gap. Minor missing features like template management or batch extraction are not essential for core use.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

1 tool updateAug 18, 2026

Changeddocforge_extract10 fields changed

addedInput schema / properties / file_base64 / anyOf

Added value: +[
+  {
+    "type": "string"
+  },
+  {
+    "type": "null"
+  }
+]

addedInput schema / properties / file_base64 / default
```
Added value: +null
```

changedInput schema / properties / file_base64 / description

Previous value: -"The document, base64-encoded. Supported types: PDF, JPG,\nPNG, TIFF, BMP, DOCX, PPTX, HTML, MD, TXT."New value: +"Optional. The local document, base64-encoded.\nSupported types: PDF, JPG, PNG, TIFF, BMP, DOCX, PPTX, HTML,\nMD, TXT. Mutually exclusive with url."

removedInput schema / properties / file_base64 / type
```
Removed value: -"string"
```

addedInput schema / properties / filename / anyOf

Added value: +[
+  {
+    "type": "string"
+  },
+  {
+    "type": "null"
+  }
+]

addedInput schema / properties / filename / default
```
Added value: +null
```

changedInput schema / properties / filename / description

Previous value: -"Original filename with extension (e.g. \"invoice.pdf\") —\nused for type detection."New value: +"Original filename with extension (e.g. \"invoice.pdf\") —\nrequired with file_base64 (used for type detection); ignored\nwith url= (derived from the link automatically)."

removedInput schema / properties / filename / type
```
Removed value: -"string"
```

addedInput schema / properties / url

Added value: +{
+  "anyOf": [
+    {
+      "type": "string"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "description": "Optional. Public http(s) URL of your document — e.g. a Drive\nor S3 share link. PREFERRED: no base64, no context bloat.\nMutually exclusive with file_base64."
+}

removedInput schema / required

Removed value: -[
-  "file_base64",
-  "filename"
-]

1 tool updateAug 18, 2026

Changeddocforge_demo2 fields changed

changedInput schema / properties / file_base64 / description

Previous value: -"Optional. Your document, base64-encoded. Omit to use\nthe bundled sample invoice."New value: +"Optional. Your local document, base64-encoded. Omit\nto use the bundled sample invoice."

addedInput schema / properties / url

Added value: +{
+  "anyOf": [
+    {
+      "type": "string"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "description": "Optional. Public http(s) URL of your document — e.g. a Drive\nor S3 share link. Preferred over base64."
+}

3 tool updatesAug 18, 2026

Changeddocforge_demo3 fields changed

addedInput schema / properties / file_base64

Added value: +{
+  "anyOf": [
+    {
+      "type": "string"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "description": "Optional. Your document, base64-encoded. Omit to use\nthe bundled sample invoice."
+}

addedInput schema / properties / filename

Added value: +{
+  "anyOf": [
+    {
+      "type": "string"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "description": "Optional. Original filename with extension (e.g.\n\"invoice.pdf\") — required when file_base64 is given."
+}

addedInput schema / properties / template / description

Added value: +"Optional template name (see docforge_templates)."

Changeddocforge_extract3 fields changed

changedInput schema / properties / schema / description

Previous value: -"Optional JSON Schema (string) — output conforms to it."New value: +"Optional JSON Schema (string) — output conforms to it\n(Pro-plan feature)."

addedInput schema / properties / schema_id

Added value: +{
+  "anyOf": [
+    {
+      "type": "string"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "description": "Optional layout ID from docforge.biz (upload an\nExcel/CSV spreadsheet and use its column headers as the field\nlist — any plan). Takes precedence over template."
+}

changedInput schema / properties / template / description

Previous value: -"Optional template name (see docforge_templates). If omitted\nalong with schema/instructions, DocForge auto-detects the\ndocument type."New value: +"Optional template name (see docforge_templates). If omitted\nalong with schema/schema_id/instructions, DocForge auto-detects\nthe document type."

Changeddocforge_extract_url1 field changed

addedInput schema / properties / schema_id

Added value: +{
+  "anyOf": [
+    {
+      "type": "string"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null
+}

6 tool updatesAug 17, 2026
- First observeddocforge_account
- First observeddocforge_demo
- First observeddocforge_extract
- First observeddocforge_extract_url
- First observeddocforge_status
- First observeddocforge_templates

Related MCP Connectors

Document to JSON – PDF Invoice/Statement/Contract ParserOAuth
io.github.fashionmascherine-svg
Turn any PDF into structured JSON via AI + OCR: invoices, bank statements, contracts.
Finance AI & Machine Learning
28
DatanemOAuth
com.datanem
Turn PDFs, scans and photos into a queryable database. Invoices, CVs, receipts, in bulk.
AI & Machine Learning Data Platforms Image & Video Processing
1
GeminaOAuth
co.gemina
Extract, search and tag any document: invoices, receipts, contracts, templates. OAuth or API key.
AI & Machine Learning Knowledge & Memory Search
11
mindee A
io.usefulapi
Turn PDFs and images into typed fields — invoices, receipts, IDs and custom models — via Mindee OCR.
AI & Machine Learning Data Platforms
42

Related MCP Servers

AIDataParser MCP server
Data Platforms AI & Machine Learning
shibley
A
license
Not graded
quality
C
maintenance
Enables conversion of PDFs, images, and messy text into schema-guaranteed JSON, with tools for schema inference, validation, and credit management.
Updated 4 days ago (2026-09-22 09:33 UTC)
MIT
Invoice Parser MCP
Finance Image & Video Processing
knportal
A
license
Not graded
quality
D
maintenance
Enables AI agents to extract structured JSON from invoices and receipts in PDF and image formats using Claude Vision. Supports full document parsing, line item extraction, validation, and batch CSV export with API key or cryptocurrency payment options.
Updated 5 months ago (2026-04-28 20:21 UTC)
MIT
DocumentPro MCPofficial
AI & Machine Learning
documentpro
A
license
Not graded
quality
C
maintenance
Extract structured, schema-typed data from invoices, purchase orders, receipts, and tax forms, and classify documents into custom label sets — via a hosted MCP server. Free tier included.
Updated 2 months ago (2026-07-13 11:40 UTC)
MIT
StructureAI MCP Server
Data Platforms Research & Data App Automation
avatrix1
F
license
A
quality
D
maintenance
Extracts structured JSON data from unstructured text using predefined schemas for receipts, invoices, resumes, and emails. It allows users to transform messy text into organized data through built-in or custom-defined fields.
Updated 7 months ago (2026-03-08 20:49 UTC)
1
-