solved.earth
Market intelligence for the agent economy
api & mcp reference

solved.earth data layer

solved.earth is the market-intelligence layer for the commercial agent economy. It tracks public AI agents, MCP servers and APIs across hundreds of niches β€” capabilities, integrations, observed pricing and how the market moves. Humans use the directory; agents and orchestrators use the MCP/API below to search, compare, route and procure.

MCP endpoint

Any MCP client can add solved.earth by URL. It speaks streamable-HTTP (JSON responses), protocol version 2025-03-26:

https://solved.earth/api/mcp

It is a read-only data oracle: no payments, no wallets, no account state β€” just intelligence.

tools

Public (no auth): get_agent, market_gaps. Partner (the rich evidence-scored ranking/search/profile data; gated by a Bearer key β€” request access): rank_agents_for_workflow, search_agents, get_agent_profile.

  • rank_agents_for_workflow β€” ranked agent candidates for each step of a business workflow, scored with reasons and cautions.
  • search_agents β€” filtered free-text search (industry, integrations, entity type, evidence quality).
  • get_agent_profile β€” full evidence-scored profile for one agent (capabilities, integrations, pricing, autonomy, evidence quality, last checked).
  • get_agent β€” the public directory card for one agent by handle or registration number.
  • market_gaps β€” under-served niches ranked by opportunity score.

examples

List the tools:

curl -X POST https://solved.earth/api/mcp \
  -H 'Content-Type: application/json' \
  -d '{"jsonrpc":"2.0","id":1,"method":"tools/list"}'

Find under-served niches in a sector (public):

curl -X POST https://solved.earth/api/mcp \
  -H 'Content-Type: application/json' \
  -d '{"jsonrpc":"2.0","id":1,"method":"tools/call",
       "params":{"name":"market_gaps","arguments":{"sector":"finance","limit":10}}}'

Fetch one agent (public):

curl -X POST https://solved.earth/api/mcp \
  -H 'Content-Type: application/json' \
  -d '{"jsonrpc":"2.0","id":1,"method":"tools/call",
       "params":{"name":"get_agent","arguments":{"handle":"openhands"}}}'

Partner tools take the same shape, with Authorization: Bearer <key>.

observed pricing

Where a public price was readable on the vendor’s site, agents carry a price object. This is observed public pricing β€” what we could read, evidence-scored β€” not a definitive vendor quote.

"price": {
  "observed": true,
  "billing": "freemium",          // subscription | freemium | usage | one-time | contact_sales | free
  "currency": "USD",
  "lowest_monthly_usd": 19,        // lowest paid monthly tier, normalized
  "summary": "Free tier; paid plans from $19/mo.",
  "confidence": "high",            // high | medium | low
  "source_url": "https://example.com/pricing",
  "checked_at": "2026-06-29T04:10:00Z"
}

When we checked and found no public price, observed is false with a billing of not_found / login_gated. A null price means we have not checked. Prices are re-scanned daily and a history is kept, so movement is trackable.

what we track per agent

Inputs, outputs, capabilities, vector support, integration type (MCP / API / SDK / web / …), observed pricing & price history, niche & category, evidence type and a confidence score, plus a source URL and last-checked date. Every field is evidence-scored, never invented.

list your agent

Building a commercial agent, MCP server or agent tool? Add it to the directory at /register. We list public, commercial agent products β€” not individual private instances.