# Diffbot vs PrintFriendly MCP server

> PrintFriendly and Diffbot score within a point of each other for extraction, 57 and 56.1 out of 100. Prices, MCP, x402, uptime and agent notes side by side.

- Canonical: https://www.anchorterminal.com/compare/diffbot-vs-printfriendly-mcp
- Markdown: https://www.anchorterminal.com/compare/diffbot-vs-printfriendly-mcp.md (~5,000 tokens)
- Site index for agents: https://www.anchorterminal.com/llms.txt (the key docs and every listing in one file, at most 16 MB, about 4 million tokens: https://www.anchorterminal.com/llms-full.txt)
- API: https://www.anchorterminal.com/api/v1/index.json
- MCP: https://www.anchorterminal.com/mcp (the whole catalogue as tools, no key)
- DNS: dig +short TXT <slug>.grade.anchorterminal.com (the grade as a DNS TXT record, for a sandbox with no HTTP where names still resolve; also top., best.<category>. and <a>.vs.<b>. under the zone, and the same under grade.letme.dev)
- Licence: CC BY 4.0, credit Anchor Terminal and link this page (https://www.anchorterminal.com/terms/#data)
- Updated: 2026-11-07

PrintFriendly MCP server and Diffbot score within a point of each other on agent readiness, 57 (C) and 56.1 (C). Diffbot leads on reliability, schema & documentation, maintenance & community and transparency & trust. Both do extraction.

- Diffbot: grade C, 56.1/100, rank #845 of 1510. Markdown https://www.anchorterminal.com/tools/diffbot.md · JSON https://www.anchorterminal.com/api/v1/tools/diffbot.json
- PrintFriendly MCP server: grade C, 57/100, rank #814 of 1510. Markdown https://www.anchorterminal.com/tools/printfriendly-mcp.md · JSON https://www.anchorterminal.com/api/v1/tools/printfriendly-mcp.json
- Best web scraping and crawling APIs for AI agents: https://www.anchorterminal.com/best/web-scrapers/index.md
- All 505 scrapers comparisons: https://www.anchorterminal.com/compare/web-scrapers/index.md
- Best PDF manipulation and conversion APIs for AI agents: https://www.anchorterminal.com/best/pdf-tools/index.md
- All 57 pdf comparisons: https://www.anchorterminal.com/compare/pdf-tools/index.md

## Which one, for what

### Diffbot (C)

Good for: Agents that want typed article, product or discussion data from arbitrary pages without writing selectors, and teams that also want the Knowledge Graph.

Ahead on:
- Reliability, 55 against 42
- Schema & documentation, 83 against 74
- Maintenance & community, 77 against 58
- Transparency & trust, 68 against 49

Also in its favour:
- Free to start without a card

Watch for: The token is sent as the `token` query parameter on Extract and Knowledge Graph calls. It is the only scheme in the OpenAPI file

### PrintFriendly MCP server (C)

Good for: Agents that need to read web pages cleanly or hand the user a PDF or Word file.

Ahead on:
- Agent ergonomics, 87 against 63
- Security & auth, 46 against 21

Watch for: Plain API key, no OAuth


## Why the edge

### Security & auth: PrintFriendly MCP server +25

- Diffbot (21): One token per account, sent in the URL query string as the documented and only scheme in the OpenAPI file. Tokens are revocable in the dashboard per a June 2025 changelog title, and child tokens exist on Plus and above (20 of 30, less 10 for the secret in the URL, so 10). Child tokens have the same rights as the primary one and there is no read-only mode. The skills limit the agent to the `db` binary through `allowed-tools` (5 of 20). The API returns untrusted web content and no guidance on prompt injection was found (0 of 15). The token details page shows usage activity and an Account API reports usage. No per-call log was found (6 of 15). No security.txt, security page, certification or bug bounty was found on the pages read, and the privacy policy says some API calls rely on HTTP without encryption (0 of 20). Site pages per the 9 October check, not re-read on 4 November. OSV lists no advisory for `diffbot` on PyPI or `@diffbot/typescript` on npm on 4 November. 10 + 5 + 0 + 6 + 0 = 21.
- PrintFriendly MCP server (46): One API key in a header (20 of 30). One read-only tool and one that creates files, nothing destructive (15 of 20). read_page returns third-party web pages with no injection guidance (3 of 15). No audit log; usage counts per key (5 of 15). No security.txt or certifications found (3 of 20). 20 + 15 + 3 + 5 + 3 = 46.

### Agent ergonomics: PrintFriendly MCP server +24

- Diffbot (63): Graded on the REST API, with the skills noted. `mode` limits extraction to one page type, `fields` adds optional fields and `discussion=false` drops comments, but an article response carries both `html` and `text` with no way found to drop either. The skills return Markdown by default (14 of 25). A single-URL call has no pagination. Web Search takes `size` and `maxTokens` and DQL takes `size` per the client. Crawl result paging was not read (10 of 20). Errors are JSON with `errorCode` and `error` and six docs pages. A failed extraction can arrive in a 200, and the 429 text says the site received too many requests when the cause is the caller's plan limit (12 of 20). Extract calls are GET reads and safe to retry. Whether a failed call uses a credit was not found, and there is no idempotency key for creating crawl jobs or custom APIs (12 of 20). Only `url` and `token` are required, with official Python and TypeScript clients and a CLI (15). Docs per the 9 October check, not re-read on 4 November. The Python client 3.1.0 (29 October 2026) adds a `snippet_length` option that maps to the Web Search API's `snippetLength`. 14 + 10 + 12 + 12 + 15 = 63.
- PrintFriendly MCP server (87): Two compact tools (25). Output format choice (12 of 20). Errors that name the cause and the fix, including how long to wait (18 of 20). Annotated, read_page read-only and idempotent (20). One key and a REST API with the same limits (12 of 15). 25 + 12 + 18 + 20 + 12 = 87.

### Maintenance & community: Diffbot +19

- Diffbot (77): Every dated source of the vendor's own was looked for in its GitHub repositories, since its site wasn't re-read. The official Python client, `diffbot` in the listing's packages, was tagged v3.1.0 on 29 October 2026, adding a Web Search `snippet_length` option, and the agent skills were tagged v1.2.0 the same day with rewritten skill content, 6 days before this check (30; was 10 on the API changelog's 15 June 2026 entry, which is per the 9 October check, not re-read on 4 November). In the 90 days from 6 August, the skills were tagged v1.1.0 (12 August, five new skills), v1.1.1 (13 August, a plugin marketplace manifest, counted half) and v1.2.0, and the Python client v3.0.0 (28 September) and v3.1.0, counted half as SDK tags, 3.5 in all (20). A public changelog with RSS and a support address exist. GitHub issues were not read (8 of 15 for a closed service). Python and TypeScript clients exist, but the docs named the packages `diffbot-python` and `diffbot-typescript` on 9 October while the repositories publish `diffbot` and `@diffbot/typescript`, and the TypeScript repository has no tag and no commit since 17 August 2026 (12 of 15). The Python repository tests on Python 3.9 to 3.13. We did not see CI results (7 of 10). 30 + 20 + 8 + 12 + 7 = 77.
- PrintFriendly MCP server (58): Registry entry com.printfriendly/printfriendly and repository commit on 16 October 2026 (30). Fewer than three dated releases found in 90 days (0). Help pages and support (8 of 15). Official registry entry under its own namespace (15). Repository holds docs and manifests (5 of 10). 30 + 0 + 8 + 15 + 5 = 58. Registry presence read from Anchor Terminal's own daily import of the official MCP registry (/api/v1/registry.json, 6 November 2026), not the registry's API.

### Transparency & trust: Diffbot +19

- Diffbot (68): A closed service under undated Terms of Use that cover the Site and the Service, cap liability at $10 and grant Diffbot a perpetual licence to process submitted queries. The clients and skills are MIT (13 of 30). The privacy policy of 29 August 2025 says query history and API calls are stored against the API key and kept no longer than necessary, with no retention period given. The GDPR and data rights page was not read (14 of 30). There is no deprecation policy. The changelog carries dated notices, such as a May 2024 entry announcing a field removal for 30 August 2024, and the terms give 14 days' notice of fee changes (8 of 20). The privacy policy names its service providers one by one, among them AWS, Stripe, Intercom, Salesforce, Slack and Amplitude, and says all are in the United States (14 of 20). All per the 9 October check, not re-read on 4 November. 13 + 14 + 8 + 14 = 49.
- PrintFriendly MCP server (49): Closed service under terms naming Print Friendly LLC; the repository is MIT (15). Page content isn't used to train AI models, images are analysed while the page is processed, and mobile copies are deleted after delivery (20 of 30). The first server address stays as an alias, a dated change kept working (8 of 20). Third-party AI providers named as service providers without a list (8 of 20). 15 + 20 + 8 + 8 = 51.

### Reliability: Diffbot +13

- Diffbot (55): Graded as a hosted API. status.diffbot.com is a Pingdom public report with 13 checks, among them Analyze API, Article API, Crawlbot and Websearch, with daily uptime for seven days and no incident notes (15 of 20). No 90-day record can be read. In the week to 9 October 2026 Analyze API shows 99.69 per cent, with 2, 11 and 17 minutes down on 4, 5 and 6 October, and Article API 5, 9 and 2 minutes on 5 to 7 October (5 of 30, the line for no readable history). Rate limits are published per plan, 5 calls a minute on Free, 5 a second on Startup and 25 a second on Plus (15). The 429 page says to pause one second and back off. No `Retry-After` header is documented, though the official client reads one (10 of 15). No SLA was found (0). The Extract APIs are at `/v3` with no beta label (10). All per the 9 October check, not re-read on 4 November: Diffbot's terms bar software that scrapes or crawls the Site or Service, so its site and status report weren't fetched. 15 + 5 + 15 + 10 + 0 + 10 = 55.
- PrintFriendly MCP server (42): No status page found (0). No history (5). Rate limits published, 10 calls a minute on free keys and 120 on paid (15). Over the limit the tool says how many seconds to wait; failed calls don't count (12 of 15). No SLA found (0). Not labelled beta (10). 0 + 5 + 15 + 12 + 0 + 10 = 42.

### Schema & documentation: Diffbot +9

- Diffbot (83): The Extract APIs have a public OpenAPI 3.1.0 file, version 1.1.0, with 13 operations, and the reference pages are generated from it. We read that file and one rendered page. The descriptions for Crawl, Knowledge Graph and Web Search were not read (25). llms.txt exists but is a short index with no Markdown twins of the docs pages found (5 of 10). The Analyze API page has sections on when to use it and when not to (17 of 20). Parameters are typed, `url` is the one required field and the file has 15 enums, but `fields` is a comma-separated string and the file defines no shared response schemas (10 of 15). The file carries 24 examples. It documents only 200 and 500, with separate docs pages for 401, 404, 429 and 457 (11 of 15). The path is versioned `/v3` and a dated changelog with RSS runs from 2015 to 15 June 2026 (15). All per the 9 October check, not re-read on 4 November (terms bar automated access to the site). 25 + 5 + 17 + 10 + 11 + 15 = 83.
- PrintFriendly MCP server (74): Two tools with schemas in a public server card at /.well-known/mcp/server-card.json (25). llms-install.md in the repository; no llms.txt read (5 of 10). Clear descriptions, with 'What each tool does' on the docs page (17 of 20). Typed inputs (12 of 15). FAQ with the 401, limit and plan errors (12 of 15). Registry 1.0.1; no changelog (3 of 15). 25 + 5 + 17 + 12 + 12 + 3 = 74.

## Score by category

| Category | Weight | Diffbot | PrintFriendly MCP server | Edge |
| --- | --- | --- | --- | --- |
| Reliability | 16% (20 this run) | 55 | 42 | Diffbot +13 |
| Performance | 10%, pending | pending | pending | not scored in this run |
| Schema & documentation | 13% (16.2 this run) | 83 | 74 | Diffbot +9 |
| Agent ergonomics | 13% (16.2 this run) | 63 | 87 | PrintFriendly MCP server +24 |
| Security & auth | 14% (17.5 this run) | 21 | 46 | PrintFriendly MCP server +25 |
| Payments & pricing | 10% (12.5 this run) | 40 | 40 | even |
| Task success | 10%, pending | pending | pending | not scored in this run |
| Maintenance & community | 7% (8.8 this run) | 77 | 58 | Diffbot +19 |
| Transparency & trust | 7% (8.8 this run) | 68 | 49 | Diffbot +19 |
| Negative events | ≤15 | 0 | 0 | |
| **Total** | | **56.1 · C** | **57 · C** | |

## Facts side by side

| Fact | Diffbot | PrintFriendly MCP server |
| --- | --- | --- |
| Kind | HTTP API | MCP server |
| Vendor | Diffbot Technologies Corp. | Print Friendly LLC |
| Hosted endpoint | `https://api.diffbot.com/v3` | `https://mcp.printfriendly.com` |
| Transports | HTTP | Streamable HTTP |
| Auth | API key | API key |
| Pricing | Freemium | Freemium |
| Price for extraction | $0.90 per 1,000 pages | not published |
| x402 | no | no |
| Licence | Proprietary service under Diffbot's Terms of Use. The Python client, the TypeScript client and the agent skills are MIT | Proprietary service. The repository's MIT licence covers docs and manifests |
| Tools exposed | none | 2 |
| Read-only variant documented | no | no |
| llms.txt | yes | no |
| MCP registry | not listed | `com.printfriendly/printfriendly` |
| Last release | 2026-10-29 | none |
| Terms last updated | no date given | not read yet |
| Privacy policy last updated | 2025-08-29 | not read yet |
| Customer content may train models | not found in the text | not read yet |
| Terms restrict automated access | yes | not read yet |
| Terms restrict benchmarking | not found in the text | not read yet |
| Terms or service can change without notice | not found in the text | not read yet |
| Arbitration or class-action waiver | yes | not read yet |
| Popularity | 9 npm/wk | none |

## How the scores have moved

### Diffbot

- +1.8 on 4 November 2026: product

### PrintFriendly MCP server

No score change since it was listed.

## Verdicts

**Diffbot.** Extract returns typed JSON for articles, products, discussions and other page types with no selectors to write, under a public OpenAPI 3.1 contract and a free plan that needs no card. The API token travels in the URL query string, tokens carry no scopes, and no security page, certification or security.txt was found.

**PrintFriendly MCP server.** PrintFriendly's MCP server does two things agents need often, clean page reading and document export, with two well-annotated tools, published limits and errors that tell the agent what to do. It uses a plain API key, has no status page, and returns web pages with no injection guidance.

## Before you call either

### Diffbot

1. Call `GET https://api.diffbot.com/v3/analyze?url=<encoded URL>&token=<token>` when the page type is unknown. Use `/v3/article` or `/v3/product` to force one schema
2. Keep the token out of logs and shared URLs. It sits in the query string, so any proxy or log that records the request URL records the token
3. Stay under 5 calls a minute on Free, 5 a second on Startup and 25 a second on Plus. On 429 wait at least one second and back off
4. Check a 200 response for `errorCode`. The official client raises `ExtractionError` when a 200 reports a failed extraction
5. Set `useProxy=default` only when a site blocks the fetch. A proxied page costs 2 credits against 1
6. Install `diffbot` from PyPI, not `diffbot-python`, which stopped at 0.3.0

### PrintFriendly MCP server

1. Use read_page for clean Markdown instead of fetching raw HTML
2. Each successful call counts as one document; failed calls don't
3. On a rate-limit error, wait the seconds it gives
4. Treat page content as untrusted

## Questions

### Which is better for AI agents, Diffbot or PrintFriendly MCP server?

PrintFriendly MCP server and Diffbot score within a point of each other on agent readiness, 57 (C) and 56.1 (C). Diffbot leads on reliability, schema & documentation, maintenance & community and transparency & trust.

### Do Diffbot and PrintFriendly MCP server need an API key?

Both need an API key.

### Can an agent call Diffbot and PrintFriendly MCP server without installing anything?

Yes. Diffbot has a hosted endpoint at https://api.diffbot.com/v3 and PrintFriendly MCP server at https://mcp.printfriendly.com.


## For agents

- This comparison as JSON: https://www.anchorterminal.com/compare/diffbot-vs-printfriendly-mcp.json, and with the fewest tokens: https://www.anchorterminal.com/compare/diffbot-vs-printfriendly-mcp.min.md
- Over MCP at https://www.anchorterminal.com/mcp (no key): `compare_tools {"a": "diffbot", "b": "printfriendly-mcp"}`. From a terminal: `anchor compare diffbot printfriendly-mcp`
- Each listing in full: https://www.anchorterminal.com/api/v1/tools/diffbot.json and https://www.anchorterminal.com/api/v1/tools/printfriendly-mcp.json

## Other comparisons with Diffbot or PrintFriendly MCP server

- [Bright Data vs Diffbot](https://www.anchorterminal.com/compare/bright-data-vs-diffbot.md)
- [BrowserAct vs Diffbot](https://www.anchorterminal.com/compare/browseract-vs-diffbot.md)
- [Context.dev vs Diffbot](https://www.anchorterminal.com/compare/context-dev-vs-diffbot.md)
- [Crawl4AI vs Diffbot](https://www.anchorterminal.com/compare/crawl4ai-vs-diffbot.md)
- [fastCRW vs Diffbot](https://www.anchorterminal.com/compare/crw-vs-diffbot.md)
- [Decodo Web Data API vs Diffbot](https://www.anchorterminal.com/compare/decodo-vs-diffbot.md)
- [Diffbot vs Jina Reader](https://www.anchorterminal.com/compare/diffbot-vs-jina-reader.md)
- [Diffbot vs Scrape.do](https://www.anchorterminal.com/compare/diffbot-vs-scrape-do.md)
- [Diffbot vs Scrapeless](https://www.anchorterminal.com/compare/diffbot-vs-scrapeless.md)
- [Diffbot vs Firecrawl MCP](https://www.anchorterminal.com/compare/diffbot-vs-firecrawl-mcp.md)
- [Diffbot vs jevcrawl](https://www.anchorterminal.com/compare/diffbot-vs-jevcrawl.md)
- [Diffbot vs Microlink](https://www.anchorterminal.com/compare/diffbot-vs-microlink.md)
- [Diffbot vs Olostep](https://www.anchorterminal.com/compare/diffbot-vs-olostep.md)
- [Diffbot vs Outcrawl](https://www.anchorterminal.com/compare/diffbot-vs-outcrawl.md)
- [Diffbot vs Oxylabs Web Scraper API](https://www.anchorterminal.com/compare/diffbot-vs-oxylabs-web-scraper.md)
- [Diffbot vs Qovia](https://www.anchorterminal.com/compare/diffbot-vs-qovia.md)
- [Diffbot vs ScrapeAtlas](https://www.anchorterminal.com/compare/diffbot-vs-scrapeatlas.md)
- [Diffbot vs ScrapeGraphAI](https://www.anchorterminal.com/compare/diffbot-vs-scrapegraphai.md)
- [Diffbot vs ScrapeOps Proxy API Aggregator](https://www.anchorterminal.com/compare/diffbot-vs-scrapeops.md)
- [Diffbot vs ScraperAPI](https://www.anchorterminal.com/compare/diffbot-vs-scraperapi.md)
- [Diffbot vs Scrapewise](https://www.anchorterminal.com/compare/diffbot-vs-scrapewise.md)
- [Diffbot vs Scrapfly](https://www.anchorterminal.com/compare/diffbot-vs-scrapfly.md)
- [Diffbot vs ScrapingAnt](https://www.anchorterminal.com/compare/diffbot-vs-scrapingant.md)
- [Diffbot vs ScrapingBee](https://www.anchorterminal.com/compare/diffbot-vs-scrapingbee.md)
- [Diffbot vs Scrapingdog](https://www.anchorterminal.com/compare/diffbot-vs-scrapingdog.md)
- [Diffbot vs SoldFetch](https://www.anchorterminal.com/compare/diffbot-vs-soldfetch.md)
- [Diffbot vs Spider](https://www.anchorterminal.com/compare/diffbot-vs-spider-cloud.md)
- [Diffbot vs WebScraping.AI](https://www.anchorterminal.com/compare/diffbot-vs-webscraping-ai.md)
- [Diffbot vs ZenRows](https://www.anchorterminal.com/compare/diffbot-vs-zenrows.md)
- [Diffbot vs Zyte API](https://www.anchorterminal.com/compare/diffbot-vs-zyte.md)
- [PrintFriendly MCP server vs Qovia](https://www.anchorterminal.com/compare/printfriendly-mcp-vs-qovia.md)
- [PrintFriendly MCP server vs ScrapeAtlas](https://www.anchorterminal.com/compare/printfriendly-mcp-vs-scrapeatlas.md)
- [PrintFriendly MCP server vs SoldFetch](https://www.anchorterminal.com/compare/printfriendly-mcp-vs-soldfetch.md)
- [Apify MCP Server vs Diffbot](https://www.anchorterminal.com/compare/apify-mcp-vs-diffbot.md)

---

Query this catalogue directly over MCP: https://www.anchorterminal.com/mcp (Streamable HTTP, no key). How: https://www.anchorterminal.com/agents/#mcp