MCP Server
The APIs.io catalog is also available to AI agents as a Model Context Protocol server over Streamable HTTP:
Code
It's generated from the same OpenAPI contract as the REST API, so the two never drift. Every tool is read-only.
Connect
Point any MCP-capable client at the endpoint. For example, in a client that takes a remote MCP URL:
Code
The server speaks JSON-RPC: initialize, tools/list / tools/call, prompts/list / prompts/get, and resources/list / resources/read. If your client shows prompts, start there β they chain the right tools for a job (see Prompts below).
Tools
apis_io_search is the power tool β find APIs, providers, or tags by free text, tags, providers,
artifact types, industry, region, and rating band. The full set (Pro-gated tools marked π):
Discovery
find_apis/get_api,find_providers/get_provider,find_tags/get_tagfind_artifactsβ artifacts of a given type (OpenAPI, AsyncAPI, Postman, β¦) across the catalogfind_similar_providers/find_similar_apis,get_provider_artifacts/get_api_artifactsget_openapi,get_provider_onboardingresolveβ turn any identifier (domain, URL,github.com/<org>) into the provider it belongs to (free)enrich_providerβ one call, pick field groups (profile,onboarding,artifactsfree;rating,insightsπ) instead of chaining severalget_provider*calls
Venture Capital (VC firms as a first-class entity + their portfolio graph β free)
find_vcsβ search VC firms by name, thesis tags, or category; sort by portfolio_on_network / portfolio_total / portfolio_ratingget_vcβ one firm: identity, fund facts, portfolio summary (band distribution + average rating);view=fullinlines the whole portfoliovc_portfolioβ a firm's portfolio companies, each network-matched + rated (filteris_provider=truefor only API providers, or by band / min_score)find_investorsβ the reverse edge: which VC firms back a given provider/company
Saved Workspace (a Pro dimension β persistent per-user state, requires a key) π
save_search/list_saved_searches/run_saved_search/delete_saved_searchsaved_search_net_newβ what newly matches your saved criteria since you last checked (the agent-native demand report)create_list/list_lists/get_list/add_to_list/delete_listβ build and keep named shortlists/stacks- These are the same capability as the REST API's
/me/*endpoints β the API and MCP share one implementation and one paywall, so they never drift.
Taxonomy β find_industries / get_industry, find_regions / get_region, find_areas / get_area are all free (browse + get); only the ranked get_industry_leaders / get_region_leaders / get_area_leaders are π
Ratings β get_rating_rubric (free); find_ratings / get_provider_rating / get_rating_history / find_rating_movers π
Synthesis β recommend_stack is freemium (free top pick per capability, Pro for the full stack + alternatives + APIs.json); compare_providers, gap_analysis, industry_gap_analysis, whats_changed, export_stack π
Per-type artifact discovery β a find_<type> for each artifact type (find_rules, find_mcp, find_plans, find_arazzo, find_asyncapis, find_channels, β¦), free except find_scopes / find_security π
Data products β export_dataset (the whole ratings/providers dataset in one pull, Business license, with co_brand) and story_leads (owner-only editorial rollup)
Insights (demand-side: what the Fortune 1000 + API providers build, buy, and hire for)
- Free:
find_company_insights,insights_dimensions,insights_adoption - Pro π:
get_company_insight(full 40-dimension profile),company_gaps,match_providers(the supplyβdemand join)
π tools require a Pro/Business key (Plans). Call tools/list for the authoritative, always-current set:
Code
Prompts
Prompts are guided flows β each one chains the right tools for a job, so you don't have to know the
tool names. Free prompts run for anyone; π prompts need a Pro/Business key and are listed for
everyone (they upsell on use). Call prompts/list for the always-current set, prompts/get to run one.
Discover & adopt β find_api, provider_overview, explain_artifact, integrate_provider,
api_readiness_check, agent_readiness_scan, best_in_class, explore_industry, explore_area,
rating_methodology, insights_landscape, demand_vs_supply
Improve a provider you own β improve_my_score; claim_and_improve π, benchmark_against_peers π
Sell & go to market β sell_upmarket π
Data & the "state of" story (media) β state_of_report π (Business), movers_briefing π,
category_leaderboard π
Decide β design_api_stack π, vendor_shortlist π, audit_api_estate π,
find_alternatives π, build_agent_toolset π, track_provider_changes π, company_readiness π
Sensemaking (owner) β story_leads, network_pulse π
Code
Resources
Attachable, readable context an agent can pin into a session. Free unless marked π.
apis://catalog,apis://ratings/rubric,apis://llms.txtβ the network root, the scoring rubric, and the machine-readable indexapis://changesπ β the recent catalog + rating movement feed- Templated:
apis://provider/{slug},apis://provider/{slug}/openapi,apis://tag/{slug}(free);apis://provider/{slug}/dossier,apis://industry|region|area/{slug},apis://stack/{capabilities}π
Call resources/list and resources/templates/list for the authoritative set.
See the API Reference for the underlying operations each tool maps to.

