compare_cohorts
UK & Ireland vs Greater China: the widest regional gap in the catalog
UK and Irish providers score twice as high as Greater China on average. Our own coverage of Chinese providers is part of the reason.
United Kingdom & Ireland
Greater China
Each sun is drawn from the cohort's averages: six facet rings, the mean Kin Score and mean agent readiness.
The 573 scored providers in the UK and Ireland average 22.8. The 483 in Greater China average 11.0, with a median of 5.2. Greater China has no exemplars and five strong providers, and its ceiling is 58.3. Access clarity shows the widest single gap: 25.9 against 9.8.
Read this comparison with the warning first. depth_confounded is true, and by a wide margin: 4.9 points less catalog gap on the UK side and four more artifact directories on the median member. Many Chinese providers document in Chinese on platforms our crawl reaches less well, and 467 of 483 are thinly covered. A large part of this 11.8-point delta is our coverage, not the market.
That makes this a coverage map as much as a market comparison. It shows where the catalog needs work, and providers in Greater China can close the gap themselves by claiming their listing.
The distributions
| United Kingdom & Ireland | Greater China | Delta | |
|---|---|---|---|
| Kin Score, mean | 22.8 | 11 | +11.8 |
| Kin Score, median | 18.5 | 5.2 | +13.3 |
| Kin Score, highest | 74.8 | 58.3 | |
| Kin Score, std dev | 16.2 | 11.9 | |
| Agent readiness, mean | 12.4 | 4.2 | +8.2 |
| Agent readiness, highest | 65.4 | 44.1 |
Delta is United Kingdom & Ireland minus Greater China, as the tool returns it.
Where the providers sit
United Kingdom & Ireland
Greater China
Facet averages
| Facet | United Kingdom & Ireland | Greater China | Delta |
|---|---|---|---|
| Discoverability | 59.2 | 53.3 | +5.9 |
| Contract Quality | 16.1 | 5.3 | +10.8 |
| Contract Governance | 6.5 | 2 | +4.5 |
| Operational Transparency | 11.8 | 4.4 | +7.4 |
| Developer Ergonomics | 23.5 | 11.5 | +12 |
| Access Clarity | 25.9 | 9.8 | +16.1 |
What they publish
Share of each cohort's providers publishing each artifact. mcp_pct counts any mcp/ artifact including ones API Evangelist derived from the provider OpenAPI; mcp_first_party_pct counts only servers the provider publishes. Prefer the latter.
| Artifact | United Kingdom & Ireland | Greater China | Delta |
|---|---|---|---|
| First-party MCP server | 7% | 3% | +4 |
| Any MCP artifact (incl. derived) | 7% | 4% | +3 |
| OAuth scopes | 18% | 5% | +13 |
| Spectral rules | 7% | 3% | +4 |
| Arazzo workflows | 2% | 0% | +2 |
| Agent skills | 0% | 0% | 0 |
| Security artifact | 100% | 99% | +1 |
How well we know each cohort
The coverage behind the averages. A cohort with a higher catalog gap and fewer artifact directories has been enriched less, so part of any difference is our coverage rather than the market.
| United Kingdom & Ireland | Greater China | |
|---|---|---|
| Declared members | 609 | 593 |
| Scored (in the averages) | 573 (94%) | 483 (81%) |
| Thinly covered | 542 | 467 |
| Median artifact directories | 9 | 5 |
| Mean catalog gap (points we could add) | 79.4 | 84.3 |
The full compare_cohorts response
{"a":{"kind":"region","slug":"united-kingdom-ireland","name":"United Kingdom & Ireland","members":609,"stats":{"kind":"region","slug":"united-kingdom-ireland","name":"United Kingdom & Ireland","tier":"report","coverage":{"declared_members":609,"resolved_members":609,"scored_members":573,"agent_scored_members":573,"scored_share_pct":94,"unexamined_members":36,"enrichment_depth":{"mean_catalog_gap":79.4,"median_artifact_dirs":9,"n":573,"thinly_covered":542,"thinly_covered_of":573,"thin_coverage_note":"542 of 573 scored members had under half their catalog-attributable points satisfied at all (catalog_earned / catalog_max < 0.5). They are INCLUDED in the mean above. A large share here means the cohort mean is partly a measurement of how far our enrichment reached, not only of how these providers publish.","note":"Rubric points API Evangelist could add to the average member with no action by the providers, and the median count of artifact directories we hold on them. A cohort with a higher gap and thinner artifacts has been enriched less, so part of any difference between its mean and another cohort's is our coverage rather than the market. Compare two cohorts only when this figure is comparable. It is an upper bound on our backlog: it says who CAN close a gap, not who did."},"unexamined_note":"Excluded from the distribution: these carry a catalog-owned needs_work flag (never enriched, or no resolvable host). They are listed as members and keep their own page and score; they do not vote in the averages, because their score measures our coverage rather than their posture."},"sufficient":true,"kin_score":{"mean":22.8,"median":18.5,"min":0,"max":74.8,"stdev":16.2},"agent_readiness":{"mean":12.4,"median":2.5,"min":0,"max":65.4,"stdev":15.6},"band_distribution":{"exemplar":5,"strong":15,"developing":82,"thin":115,"emerging":174,"minimal":182},"facet_averages":{"discoverability":{"mean":59.2,"n":573},"contract_quality":{"mean":16.1,"n":573},"contract_governance":{"mean":6.5,"n":573},"operational_transparency":{"mean":11.8,"n":573},"developer_ergonomics":{"mean":23.5,"n":573},"access_clarity":{"mean":25.9,"n":573}},"adoption":{"mcp_pct":7,"mcp_first_party_pct":7,"mcp_note":"mcp_pct counts any mcp/ artifact including ones API Evangelist derived from the provider OpenAPI; mcp_first_party_pct counts only servers the provider publishes. Prefer the latter.","skills_pct":0,"scopes_pct":18,"security_pct":100,"arazzo_pct":2,"rules_pct":7}}},"b":{"kind":"region","slug":"greater-china","name":"Greater China","members":593,"stats":{"kind":"region","slug":"greater-china","name":"Greater China","tier":"report","coverage":{"declared_members":593,"resolved_members":593,"scored_members":483,"agent_scored_members":483,"scored_share_pct":81,"unexamined_members":109,"enrichment_depth":{"mean_catalog_gap":84.3,"median_artifact_dirs":5,"n":483,"thinly_covered":467,"thinly_covered_of":483,"thin_coverage_note":"467 of 483 scored members had under half their catalog-attributable points satisfied at all (catalog_earned / catalog_max < 0.5). They are INCLUDED in the mean above. A large share here means the cohort mean is partly a measurement of how far our enrichment reached, not only of how these providers publish.","note":"Rubric points API Evangelist could add to the average member with no action by the providers, and the median count of artifact directories we hold on them. A cohort with a higher gap and thinner artifacts has been enriched less, so part of any difference between its mean and another cohort's is our coverage rather than the market. Compare two cohorts only when this figure is comparable. It is an upper bound on our backlog: it says who CAN close a gap, not who did."},"unexamined_note":"Excluded from the distribution: these carry a catalog-owned needs_work flag (never enriched, or no resolvable host). They are listed as members and keep their own page and score; they do not vote in the averages, because their score measures our coverage rather than their posture."},"sufficient":true,"kin_score":{"mean":11,"median":5.2,"min":0,"max":58.3,"stdev":11.9},"agent_readiness":{"mean":4.2,"median":0,"min":0,"max":44.1,"stdev":9.3},"band_distribution":{"strong":5,"developing":21,"thin":33,"emerging":81,"minimal":343},"facet_averages":{"discoverability":{"mean":53.3,"n":483},"contract_quality":{"mean":5.3,"n":483},"contract_governance":{"mean":2,"n":483},"operational_transparency":{"mean":4.4,"n":483},"developer_ergonomics":{"mean":11.5,"n":483},"access_clarity":{"mean":9.8,"n":483}},"adoption":{"mcp_pct":4,"mcp_first_party_pct":3,"mcp_note":"mcp_pct counts any mcp/ artifact including ones API Evangelist derived from the provider OpenAPI; mcp_first_party_pct counts only servers the provider publishes. Prefer the latter.","skills_pct":0,"scopes_pct":5,"security_pct":99,"arazzo_pct":0,"rules_pct":3}}},"comparable":true,"delta":{"kin_score_mean":11.8,"kin_score_median":13.3,"agent_readiness_mean":8.2,"facets":{"discoverability":5.9,"contract_quality":10.8,"contract_governance":4.5,"operational_transparency":7.4,"developer_ergonomics":12,"access_clarity":16.1},"adoption":{"mcp_pct":3,"mcp_first_party_pct":4,"mcp_note":null,"skills_pct":0,"scopes_pct":13,"security_pct":1,"arazzo_pct":2,"rules_pct":4},"enrichment_depth":{"mean_catalog_gap":-4.9,"median_artifact_dirs":4}},"depth_confounded":true,"depth_note":"United Kingdom & Ireland scores 11.8 points higher than Greater China AND is the better-enriched cohort: 4.9 points less catalog_gap and 4 more artifact directories on the median member. The market difference and our coverage difference point the same way, so this delta cannot be attributed to the markets on its own. Close the enrichment gap, or report both figures together."}
Result read 2026-10-27. United Kingdom & Ireland and Greater China each have their own page with the full roster and leaderboard.
Run this comparison yourself
Everything above came from one call to compare_cohorts. Swap in any two tags, industries, regions, areas or VC portfolios and you get the same answer for your own shortlist. It is an Understanding tool, included in the Understanding and Influence plans, or pay per call.
https://apis.io/mcp:
{"name": "compare_cohorts", "arguments": {"a": "region:united-kingdom-ireland", "b": "region:greater-china"}}
Over the REST API:
curl "https://apis.io/api/v1/cohorts/compare?a=region:united-kingdom-ireland&b=region:greater-china" \
-H "X-API-Key: $APIS_IO_KEY"
See the Understanding plan
Connect the MCP server →
More comparisons
Stripe vs Adyen
81.1 vs 71.1 · compare_providers
Twilio vs Vonage
91.6 vs 71.3 · compare_providers
OpenAI vs Anthropic
84.5 vs 89 · compare_providers
Plaid vs MX Technologies
84.6 vs 64.9 · compare_providers
GitHub vs GitLab
79 vs 81 · compare_providers
Shopify vs BigCommerce
83 vs 82.5 · compare_providers
HubSpot vs Salesforce
93.2 vs 88.8 · compare_providers
Payments & Money Movement vs Banking & Open Banking
29.3 vs 25.4 average · compare_cohorts
North America vs Europe
17.8 vs 21.4 average · compare_cohorts
Y Combinator vs Andreessen Horowitz
21.8 vs 23.9 average · compare_cohorts
Healthcare vs Insurance
15.7 vs 18.9 average · compare_cohorts
Artificial Intelligence vs Machine Learning
22.9 vs 24.1 average · compare_cohorts
Cybersecurity & Identity vs Developer Tools & DevOps
31.1 vs 33.4 average · compare_cohorts
MCP vs AI Agents
42.6 vs 31.5 average · compare_cohorts
Work with this as data
Every comparison here is available over the APIs.io API and to AI agents over MCP.