Apis Io is an MCP server with 133 tools an agent can call, among them add_to_list, agent_readiness_dimensions, apis_io_search. It answers at https://apis.io/mcp over streamable HTTP, and it listed its tools to an anonymous client, so no sign-in was needed for that. Our probes reached it 6 of 6 times since 10 September 2026; the last check, on 19 October 2026, succeeded.
Discover, rate and compare APIs and providers in the APIs.io catalog; manage a listing you own.
Description as the publisher wrote it.
| Tool | What it does |
|---|---|
add_to_list | UNDERSTANDING — Add providers/APIs (by slug or aid) to one of your lists. Inputs: id, members, context |
agent_readiness_dimensions | UNDERSTANDING — diffusion: for each agent-readiness dimension, how many scored providers satisfy it, out of how many, as a share. The denominator every "the agent web is/is not here yet" claim needs and almost never has. Inputs: page, limit, context |
apis_io_search | START HERE. Federated overview of the APIs.io catalog for a query: the top matching APIs, providers, AND tags in one call, each with its total match count. Filter by tags, artifact types, industry, region, rating band. `limit` is per sectio Inputs: return, q, tags, match, providers, artifact_types |
check_status | INFLUENCE — the status of a check request by id: queued, in_review, running, done, rejected or needs_info, with any notes shared by the reviewer. The id identifies the request, but the Influence plan is now required to read it back. To repo Inputs: id, context |
claim_listing | INFLUENCE — ask to claim a listing as yours. Returns 202 with a token and the hosts it will be checked against: publish it as a DNS TXT record, or as a file at /.well-known/apis-io-challenge, and leave it up. A PERSON verifies it and emails Inputs: slug, context |
cohort_capabilities | UNDERSTANDING — what every member of a cohort actually publishes: artifact counts by type plus the agent-readiness dimensions each one satisfies. The capability matrix behind a market report. Large cohorts come back in byte-budgeted chunks: Inputs: kind, slug, cursor, context |
cohort_failures | UNDERSTANDING — what a whole market gets WRONG: the agent-readiness checks its members most commonly fail, ranked by what fixing each would move the cohort mean. The inverse of gap_analysis, which says where a market is under-served; this s Inputs: kind, slug, page, limit, context |
cohort_history | UNDERSTANDING — the SET-LEVEL time series: how a whole market's Kin Score and agent readiness moved, build by build. There was a per-provider series and a whole-dataset licence and nothing between them, so "how has banking moved over six mo Inputs: kind, slug, context |
cohort_rankings | UNDERSTANDING — the leaderboard for a market, on TWO axes: rank by Kin Score composite AND rank by agent readiness. The two orders differ, and the gap between a provider's two ranks is usually the story. Inputs: kind, slug, page, limit, context |
cohort_scores | UNDERSTANDING — facet-level scores for every member of a cohort, each with the cohort average and the delta against it. A 60 in governance means nothing until you know the market sits at 45; this is the endpoint that says so. Inputs: kind, slug, page, limit, context |
cohort_stats | UNDERSTANDING — the DISTRIBUTION for a whole market: Kin Score mean/median/min/max/stdev, agent-readiness spread, band split, per-facet averages, and artifact adoption rates. This is the market-stats sheet from a Trend Report, computed live Inputs: kind, slug, context |
company_gaps | UNDERSTANDING — A company's weakest investment dimensions — where it is thin and a vendor could sell in. Inputs: slug, context |
compare_cohorts | UNDERSTANDING — two markets side by side on one rubric: "is US payments further along than UK banking?" Returns both distributions plus the deltas on score, agent readiness, every facet and every adoption rate. A question a written report c Inputs: a, b, context |
compare_providers | UNDERSTANDING — Compare 2+ providers side by side: composite/band, per-facet leaders, and an artifact-coverage matrix. Inputs: providers, context |
correct_facts | INFLUENCE — propose corrections to what we say about you: name, description, url, industries, tags. Returns 202 and is applied by a person — an API that let an owner rewrite their own description unreviewed would be a marketing surface, not Inputs: slug, name, description, url, industries, tags |
create_list | UNDERSTANDING — Create a named, persistent list (a shortlist / stack you own) of providers or APIs. Requires an apis.io API key. Inputs: name, members, context |
delete_list | UNDERSTANDING — Delete a list you own. Inputs: id, context |
delete_saved_search | UNDERSTANDING — Delete a saved search you own. Inputs: id, context |
deprecated_operations | UNDERSTANDING — every provider publishing at least one operation marked deprecated in its own OpenAPI, ranked by how many. The lifecycle view of the catalog: 8,297 deprecated operations across 681 providers, which nothing could see before, Inputs: page, limit, context |
dispute_finding | INFLUENCE — "you say we lack X, here it is." Send the claim in words and a URL that evidences it. Returns 202; a person fetches your evidence, checks it against what we hold, and emails you either way. Open to any paying caller — you should Inputs: slug, claim, evidence_url, contact, context |
enrich_provider | One call, pick your field groups — resolves a slug OR any identifier and returns exactly the groups you ask for, instead of chaining get_provider + get_provider_rating + get_provider_artifacts + get_provider_onboarding. Groups: profile, onb Inputs: id, fields, context |
export_dataset | LICENCE (sold on the Influence plan) — the WHOLE dataset, not a 100-row page: `ratings` (every rated provider with facets, trend, rubric + provenance), `providers` (the catalog with coverage + score), or `history` (every provider's full sco Inputs: dataset, cursor, co_brand, context |
export_stack | UNDERSTANDING — Export a designed capability stack as an adoptable APIs.json document (with an Arazzo hint) the team can commit. Inputs: capabilities, region, context |
find_agent_readiness | UNDERSTANDING — the agent-readiness leaderboard across the whole catalog. Rank providers by agent readiness, and filter to those that DO satisfy (has) or do NOT satisfy (missing) specific dimensions — e.g. has="mcp_server,protected_resource Inputs: has, missing, band, min_score, sort, page |
find_apis | Paginated, sortable list of APIs across providers — filter by tag, provider, artifact type, industry, region, or rating band. Use apis_io_search first for a cross-type overview. Inputs: q, tags, match, resolve, providers, artifact_types |
find_apis_json | APIs.json indexes across the catalog. The APIs.json discovery documents themselves. Filter by q / tags / providers; include=["content"] inlines bodies. Use find_artifacts for cross-type search. Inputs: q, tags, providers, match, include, page |
find_arazzo | Arazzo workflows across the catalog. Multi-step API workflows chaining operations. Filter by q / tags / providers; include=["content"] inlines bodies. Use find_artifacts for cross-type search. Inputs: q, tags, providers, match, include, page |
find_areas | Browse the API Evangelist areas taxonomy (authentication, webhooks, payments, …) — curated, scored provider indexes. Search by text; sort by provider count. Inputs: q, sort, page, limit, context |
find_artifacts | Find artifacts of ANY one type across the catalog — the cross-type entry point. Each type also has a dedicated find_<type> tool (find_mcp, find_rules, find_scopes, …) with sorts and filters unique to that type; prefer those when you know th Inputs: type, q, tags, providers, include, page |
find_asyncapis | AsyncAPI (event-driven) specifications across the catalog. Event/streaming APIs. Filter by q / tags / providers; include=["content"] inlines bodies. Use find_artifacts for cross-type search. Inputs: q, tags, providers, match, include, page |
find_capabilities | START HERE for "what can a business do with these APIs". The business-capability model — 333 top-level capabilities across 28 industries — with how many catalog providers reach each one. Defaults to capabilities the catalog actually reaches Inputs: q, industry, all, page, limit, context |
find_channels | AsyncAPI event channels across the catalog. Individual event channels (topics/streams). Filter by q / tags / providers; include=["content"] inlines bodies. Use find_artifacts for cross-type search. Inputs: q, tags, providers, match, include, page |
find_cohorts | START HERE for market-level questions. Every scored population of providers in the catalog — tags, industries, regions, areas and VC portfolios — as one browsable index. Filter by kind, minimum population, or promotion tier (report/brief/da Inputs: kind, min_providers, tier, q, page, limit |
find_collections | Postman / Open collections across the catalog. Runnable request collections. Filter by q / tags / providers; include=["content"] inlines bodies. Use find_artifacts for cross-type search. Inputs: q, tags, providers, match, include, page |
find_company_insights | Browse profiled companies (Fortune 1000) by name or industry; ranked by overall technology-readiness signal. `industry` takes an insights industry NAME from insights_industries (e.g. "Industrial") — a different vocabulary from the catalog i Inputs: q, industry, page, limit, context |
find_countries | Browse the country dimension — the finest of the four place taxonomies, and the one a buyer usually names ("who is in Germany"). Peer to find_industries / find_regions / find_areas. Search by text; sort by provider count. Membership is deri Inputs: q, sort, page, limit, context |
find_examples | Example payloads across the catalog. Real request/response examples. Filter by q / tags / providers; include=["content"] inlines bodies. Use find_artifacts for cross-type search. Inputs: q, tags, providers, match, include, page |
find_extensions | Browse every OpenAPI `x-` specification extension harvested across the catalog, with the provenance the OpenAPI Initiative registry does not carry: who publishes it, in how many documents, where in the document it appears, and what shape th Inputs: q, sort, page, limit, context |
find_finops | FinOps / billing models across the catalog. How usage is metered and billed. Filter by q / tags / providers; include=["content"] inlines bodies. Use find_artifacts for cross-type search. Inputs: q, tags, providers, match, include, page |
find_graphql | GraphQL schemas across the catalog. GraphQL type systems. Filter by q / tags / providers; include=["content"] inlines bodies. Use find_artifacts for cross-type search. Inputs: q, tags, providers, match, include, page |
find_industries, find_investors, find_json_ld, find_json_schemas, find_json_structures, find_mcp, find_openapis, find_operations, find_plans, find_postman, find_providers, find_rate_limits, find_rating_movers, find_ratings, find_regions, find_rules, find_scopes, find_security, find_similar_apis, find_similar_providers, find_skills, find_tag_groups, find_tags, find_vcs, gap_analysis, generate_artifact, get_agent_readiness, get_api, get_api_artifacts, get_area, get_area_leaders, get_capability, get_capability_edges, get_cohort, get_company_insight, get_country, get_country_leaders, get_extension, get_industry, get_industry_leaders, get_list, get_openapi, get_playground_apis, get_provider, get_provider_apis, get_provider_artifacts, get_provider_business_capabilities, get_provider_capabilities, get_provider_evidence, get_provider_facets, get_provider_onboarding, get_provider_operations, get_provider_rating, get_provider_schema, get_provider_tools, get_rating_history, get_rating_rubric, get_region, get_region_leaders, get_tag, get_tag_group, get_vc, industry_gap_analysis, insights_adoption, insights_dimensions, insights_industries, insights_overview, list_lists, list_saved_searches, list_watches, match_providers, my_checks, my_workspace, readiness_gates, recommend_stack, report_correction, report_gap, request_check, resolve, run_saved_search, save_search, saved_search_net_new, set_visibility, simulate_fixes, story_leads, submit_artifact, submit_feedback, tag_group_tags, unwatch_listing, vc_portfolio, watch_listing, what_can_i_fix, whats_changed
Every block below points at https://apis.io/mcp. Pick your client and copy.
claude mcp add --transport http apis-io https://apis.io/mcp
{
"mcpServers": {
"apis-io": {
"command": "npx",
"args": ["-y", "mcp-remote", "https://apis.io/mcp"]
}
}
}{
"mcpServers": {
"apis-io": {
"url": "https://apis.io/mcp"
}
}
}{
"servers": {
"apis-io": {
"type": "http",
"url": "https://apis.io/mcp"
}
}
}{
"context_servers": {
"apis-io": {
"url": "https://apis.io/mcp"
}
}
}{
"mcpServers": {
"apis-io": {
"serverUrl": "https://apis.io/mcp"
}
}
}{
"mcpServers": {
"apis-io": {
"url": "https://apis.io/mcp"
}
}
}name: Apis Io
version: 0.0.1
schema: v1
mcpServers:
- name: Apis Io
type: streamable-http
url: https://apis.io/mcp{
"mcpServers": {
"apis-io": {
"httpUrl": "https://apis.io/mcp"
}
}
}{
"mcpServers": {
"apis-io": {
"type": "http",
"url": "https://apis.io/mcp"
}
}
}{
"mcpServers": {
"apis-io": {
"url": "https://apis.io/mcp"
}
}
}goose://extension?url=https%3A%2F%2Fapis.io%2Fmcp&type=streamable_http&id=apis-io&name=Apis%20Io
It answered our last check on 19 October 2026 in 217 ms. Over 6 checks since 10 September 2026 it answered 6. Status here comes from Neuronto's own probes, not from the publisher.
Yes. It is published by apis.io and served from apis.io, the vendor's own domain: https://apis.io/mcp.
133, as returned by the server's own tools/list on 12 September 2026: add_to_list, agent_readiness_dimensions, apis_io_search, check_status, claim_listing, cohort_capabilities, cohort_failures, cohort_history, and 125 more.
It answered our last check on 19 October 2026 in 217 ms. Over 6 checks since 10 September 2026 it answered 6.
Put the server under mcpServers in ~/.cursor/mcp.json with the URL https://apis.io/mcp. The exact JSON is above, with the same setup for Claude Code, Claude Desktop, VS Code, Windsurf, Zed, Gemini CLI and the rest.
It listed its tools to an anonymous client, so reading the tool list needs no key. Individual tools can still ask for credentials in their own inputs.
Publisher: io.apis. Endpoint host: apis.io. ARD identifier: urn:air:io.apis:mcp:apis-io.
First indexed 10 September 2026. The tools are exactly what the server returned; nothing on this page
is inferred from its name. Ranking in Neuronto search is never for sale.