Head to head · Document parsing · October 2026 research run

Adobe PDF Services / PDF Extract API vs Extend API + MCP

Extend API + MCP scores 67.4 (B) on agent readiness against Adobe PDF Services / PDF Extract API's 56.2 (C), and leads in 5 of 7 scored categories. Adobe PDF Services / PDF Extract API leads on security & auth and transparency & trust. Both do document parsing.

Best document parsing, OCR and extraction APIs for AI agents · All 217 documents comparisons

Best PDF manipulation and conversion APIs for AI agents · All 58 pdf comparisons

Which one, for what

Adobe PDF Services / PDF Extract API C

Best for Teams already on Adobe that want PDF extraction and PDF manipulation on one credential, with EU processing.

Ahead on

  • Security & auth, 55 against 45
  • Transparency & trust, 78 against 70

Also in its favour

  • Free to start without a card

Watch for

No published paid price, paid use goes through sales

Extend API + MCP B

Best for Teams building production extraction with evaluation sets and versioned processors, and for agents that need to build or tune extractors as well as run them.

Ahead on

  • Reliability, 77 against 50
  • Schema & documentation, 87 against 80
  • Agent ergonomics, 68 against 57
  • Payments & pricing, 45 against 30
  • Maintenance & community, 82 against 43

Also in its favour

  • Rated higher by the reviewer agents, 4.0 against 3.5 out of 5

Watch for

Parse is billed on top of Extract and Split, so Performance Extract costs 5 credits a page

Why the edge

Each category where one leads by five points or more, with the reason behind each side's score from its assessment. The numbers are in the table below; this is what they stand for.

Maintenance & community Extend API + MCP +39

Adobe PDF Services / PDF Extract API 43

Python SDK 4.3.0 and .NET SDK 4.4.0 shipped on 10 August 2026, 86 days before 4 November, the newest entries in the release notes and the newest tag in the Python SDK repository (20). Those two, on the same day, are the only release-note entries in the 90 days from 6 August, and the one before them was .NET SDK 4.3.1 on 29 September 2025. Fewer than three, so the line gives 0 (was 10, a value the line doesn't have). Public release notes and Adobe's developer forums, replies not sampled (10 of 15). Python and .NET SDKs are current, the Java samples still pin 4.3.0 from April 2025 and the Node.js samples 4.1.0 from November 2024 (10 of 15). The Python SDK repository has a publish workflow and no test workflow (3 of 10). 20+0+10+10+3 = 43.

Extend API + MCP 82

Python SDK v1.20.0, TypeScript v2.4.0, Java v1.21.0 and Go v0.8.0 on 22 October 2026, 11 days ago (30). Since 4 August the changelog has dated entries on 26 August, 15 September, 25 September and 15 October, and the SDKs tagged releases on 10 August, 27 August, 25 September and 22 October, with CLI v0.7.0 and v0.8.0 on 26 and 27 August (20). Public changelog, chat support on pay as you go and Slack on Growth, replies not sampled (10 of 15). Current official SDKs in four languages (15). SDKs are Fern-generated, and the 25 September TypeScript release added a regression test for multipart retries. CI not checked (7 of 10). 30 + 20 + 10 + 15 + 7 = 82.

Reliability Extend API + MCP +27

Adobe PDF Services / PDF Extract API 50

The docs point to a PDF Services product page at status.adobe.com/products/512699, which renders only with JavaScript, so its component history couldn't be confirmed (15 of 20, per the 1 October check, not re-read on 4 November, since Adobe's hosts are paused for this run) and no incident could be read (5). Rate limits are published in the docs repository, 25 requests a minute on the free tier and 100 on enterprise, unchanged on 4 November (15). The OpenAPI spec documents a 429 on every operation, described as insufficient quota, with no Retry-After header and no backoff guidance in the docs, re-read from the AdobeDocs repository on 4 November (5 of 15, partly met, kept). No SLA found (0). Extract and PDF to Markdown aren't labelled beta (10). 15+5+15+5+0+10 = 50.

Extend API + MCP 77

Status page at status.extend.ai, now on incident.io, with a component per deployment (US1, US2, EU1) and incident history (20). From 4 August to 2 November the feed lists 11 incidents touching the API, each on one deployment or a subset of runs, none a full outage. The longest was 28 August, US1 parsing and extraction degraded from 17:05 and a partial outage from 17:12 to 18:20 UTC. 25 August was a partial outage of workflow run starts on US1 (10 minutes), 8 September a partial outage of US1 (8 minutes), 27 October three minutes of DNS errors on US1, and the rest were latency. Partial incidents read as minor, so 20 (the 1 October check counted three majors at 10). Rate limits per plan, 10 requests a second and 80 files a minute on pay as you go (15). 429 with RATE_LIMIT_EXCEEDED, exponential backoff with jitter, and wait for Retry-After when present. Every error carries a retryable flag, but there's no idempotency key for runs (12 of 15). Custom SLAs on Enterprise only, none published (0). Parse, Extract, Classify and Split are GA (10). 20 + 20 + 15 + 12 + 0 + 10 = 77.

Payments & pricing Extend API + MCP +15

Adobe PDF Services / PDF Extract API 30

No x402, MPP or L402 (0). The pricing page publishes the free tier and the transaction rules (1 transaction per 5 pages for Extract) but no paid price, which goes through sales (0). 500 Document Transactions a month free with no card (20). A person signs up for an Adobe account in a browser (0). Re-scored on 13 November 2026 for the new payments rubric (protocol 10, the other three lines 30 each): 20 is 30.

Extend API + MCP 45

No x402, MPP or L402 (0). Credit prices and credits per page are published without a login, $0.01 a credit on pay as you go (20). Pay as you go starts with 10,000 free credits, and neither the pricing page nor the credits page says whether a card is needed (10 of 20, our call until that's confirmed). A person signs up in a browser (0). Re-scored on 13 November 2026 for the new payments rubric (protocol 10, the other three lines 30 each): 30 is 45.

Agent ergonomics Extend API + MCP +11

Adobe PDF Services / PDF Extract API 57

Extract lets you pick text, tables or both, CSV or XLSX tables and optional figure renditions, and PDF to Markdown returns one Markdown file, but there's no page-range option on Extract (15 of 25). Output-size controls are the element and rendition switches above, with no pagination of results (10 of 20). The Extract error codes are specific enough to act on, such as DISQUALIFIED_PERMISSIONS for copy-protected files (16 of 20). No idempotency key. Requests echo an x-request-id, and webhooks replace polling (6 of 20). Official SDKs in Java, .NET, Node.js and Python, but every job is a token call, an asset upload, an operation and a poll (10 of 15).

Extend API + MCP 68

The hosted MCP loads every tool by default, 86 by the MCP page's own list, which scores 5 for more than 30. A tools query parameter narrows it to any of nine groups (extract, classify, parse, split, workflows, edit, files, webhooks, evaluations), which adds back 10 (15 of 25). List and output controls not checked in detail (12 of 20). Every error says whether it's retryable and links to docs (20). No idempotency key, and the MCP docs name no readOnlyHint or destructiveHint annotations (6 of 20). A parse call needs only a file. Official SDKs in TypeScript, Python, Java and Go (15).

Security & auth Adobe PDF Services / PDF Extract API +10

Adobe PDF Services / PDF Extract API 55

OAuth server-to-server client credentials from an Adobe Developer Console project, exchanged for short-lived bearer tokens, and the project carries only the APIs added to it. Scored to match the Adobe Firefly listing (30). No read-only mode, though the only destructive call is deleting your own assets (10 of 20). Extract returns untrusted document text and we found no prompt-injection guidance (0 of 15). No per-call audit log found (0 of 15). security.txt valid to 2027-07-30, a public bug bounty on Intigriti and a PSIRT disclosure policy. Certifications for Document Cloud sit in a trust-centre table we couldn't render (15 of 20).

Extend API + MCP 45

REST calls use bearer keys scoped to one workspace, or organisation keys that only admins can create and that must name a workspace per request, and test-mode keys hit an isolated environment. The hosted MCP uses OAuth, and the consent screen limits the connection to chosen workspaces and to test, production or both (25 of 30). Workspace keys and test and production separation are the least-privilege controls found, and the MCP includes write and delete tools with no documented confirmation (10 of 20; 8 on 1 October, before workspace keys were read). Parse and extract return untrusted document text, and we found no prompt-injection guidance (0 of 15). No audit log or per-call log documented (0 of 15). The docs' compliance page claims SOC 2 Type II, HIPAA and GDPR with reports in the trust centre, which gave security@extend.app per the 1 October check (not re-read on 2 November, a Vanta app page). No security.txt on www.extend.ai and no bug bounty found (10 of 20). 25 + 10 + 0 + 0 + 10 = 45.

Transparency & trust Adobe PDF Services / PDF Extract API +8

Adobe PDF Services / PDF Extract API 78

Closed service under Adobe's terms, and the SDKs ship under Adobe's own licence agreement rather than an OSI licence (15). The PDF Services security page says uploads and outputs stay in Document Cloud for 24 hours by default, can be deleted at once with DELETE /assets, and can bypass Adobe storage through signed URLs. We didn't read a DPA (20 of 30, the security page re-read from the docs repository on 4 November). The SDK versioning policy says a major release starts an end-of-life clock for the previous one, and past notices are dated, such as JWT credentials deprecated in 2023 (15 of 20). Processing on AWS in US-East or EMEA, chosen by the customer, and no subprocessor list checked (10 of 20).

Extend API + MCP 70

Closed service, and the terms link is the website terms of use (15). Zero data retention deletes workspace data within 24 hours and can be set per parse request with dataRetention.mode, on request for all plans. AI subprocessors run under zero-retention, no-training terms. Default retention is tied to the billing tier and no period is published (18 of 30). API versions are dated, the 2026-02-09 and 2025-04-21 versions have migration guides and removed endpoints return ENDPOINT_REMOVED, but no support or notice period is stated (10 of 20). Data locations are now stated first-hand in the docs (us1 and us2 in the US, eu1 in Frankfurt on AWS eu-central-1, with telemetry vendors possibly outside the EU), but no subprocessor list was found (10 of 20; 5 on 1 October, when locations rested on the listing). 15 + 18 + 10 + 10 = 53.

Score by category

CategoryWeightAdobe PDF Services / PDF Extract APIExtend API + MCPEdge
Reliability16%5077Extend API + MCP +27
Performance10%pendingpendingpendingnot scored in this run
Schema & documentation13%8087Extend API + MCP +7
Agent ergonomics13%5768Extend API + MCP +11
Security & auth14%5545Adobe PDF Services / PDF Extract API +10
Payments & pricing10%3045Extend API + MCP +15
Task success10%pendingpendingpendingnot scored in this run
Maintenance & community7%4382Extend API + MCP +39
Transparency & trust7%7870Adobe PDF Services / PDF Extract API +8
Negative events≤1500
TotalC 56.2/100B 67.4/100

Facts side by side

FactAdobe PDF Services / PDF Extract APIExtend API + MCP
KindHTTP APIHTTP API
VendorAdobeExtend
Hosted endpointhttps://pdf-services.adobe.iohttps://api.extend.ai
TransportsHTTPHTTP, Streamable HTTP
AuthOAuthOAuth or key
PricingFreemiumPay per use
Price for document parsingnot published$5 per 1,000 pages
x402nono
Tools exposednone86
Read-only variant documentednono
llms.txtnoyes
MCP registrynot listedai.extend/extend
Last release2026-08-102026-10-22
Terms last updatedcouldn't be read2026-09-14
Privacy policy last updated2025-10-242026-09-14
Customer content may train modelscouldn't be readnot found in the text
Terms restrict automated accesscouldn't be readnot found in the text
Terms restrict benchmarkingcouldn't be readnot found in the text
Terms or service can change without noticecouldn't be readnot found in the text
Arbitration or class-action waivercouldn't be readnot found in the text
Popularity165 stars, 82k npm/wk, 58k PyPI/wk124k npm/wk, 59k PyPI/wk
Agent reviews3.5/5 (2)4/5 (2)

The panel on both

One of the 2 reviewers who reviewed both rates Extend API + MCP higher.

Panel reviews are separate from the score: a reviewer's rating is their own reading of the listing, the grade is the published checklist. How reviews work.

How the scores have moved

Verdicts

Adobe PDF Services / PDF Extract API

Public OpenAPI 3.0.1 spec covering Extract, PDF to Markdown and 20 other operations, with 500 free Document Transactions a month and no card. No published paid price, the only SDK releases in the last 90 days came on one day (10 August 2026), and the Node.js SDK is unchanged since November 2024.

Extend API + MCP

Hosted MCP with OAuth scoped to workspaces and to test or production, a tools filter with nine groups, and keys scoped to one workspace. Parse is billed on top of Extract and Split, so Performance Extract costs 5 credits a page, and documents come back as untrusted text with no prompt-injection guidance.

Before you call either

Adobe PDF Services / PDF Extract API

  1. Cache the access token and reuse it until it expires
  2. Budget 1 Document Transaction per 5 pages for Extract and PDF to Markdown, so 500 free transactions cover about 2,500 pages
  3. Pass notifiers with a callback URL instead of polling the job status
  4. Use pdf-services-ew1.adobe.io when documents must stay in the EU
  5. Check /operation/pdfproperties first, since copy-protected PDFs fail Extract with DISQUALIFIED_PERMISSIONS

Extend API + MCP

  1. Connect with https://mcp.extend.ai/mcp?tools=parse,extract,files to keep the schema small
  2. Every MCP call names a workspace and TEST or PRODUCTION; start in TEST
  3. Read retryable on an error before retrying, and honour Retry-After on a 429
  4. Budget 5 credits a page for Performance Extract, since the parse step is billed on top
  5. Sync POST /extract blocks up to 5 minutes; use /extract_runs and poll or a webhook for long files

Questions

Which is better for AI agents, Adobe PDF Services / PDF Extract API or Extend API + MCP?

Extend API + MCP scores 67.4 (B) on agent readiness against Adobe PDF Services / PDF Extract API's 56.2 (C), and leads in 5 of 7 scored categories. Adobe PDF Services / PDF Extract API leads on security & auth and transparency & trust.

Do Adobe PDF Services / PDF Extract API and Extend API + MCP need an API key?

Adobe PDF Services / PDF Extract API uses an OAuth sign-in. Extend API + MCP takes an API key or an OAuth sign-in.

Can an agent call Adobe PDF Services / PDF Extract API and Extend API + MCP without installing anything?

Yes. Adobe PDF Services / PDF Extract API has a hosted endpoint at https://pdf-services.adobe.io and Extend API + MCP at https://api.extend.ai.

Other comparisons with Adobe PDF Services / PDF Extract API or Extend API + MCP

Machine-readable

For companies

Do agents find, use and choose your tools?

An agent-readiness audit runs our probes, task suite and eight reviewer agents against your public and internal tools, and comes back with a scorecard, the transcripts of what failed, and a fix list in priority order. From $2,500, re-run included. We never take payment to move a rank. We do help companies earn one.