API examples: curl, Python, TypeScript

POST JSON-RPC 2.0 to https://exchange-production-9123.up.railway.app/mcp/core?c=docs with Content-Type: application/json and Accept: application/json, text/event-stream. A tool call is {"method":"tools/call","params":{"name":<tool>,"arguments":{...}}}. The answer arrives twice in result: parsed in structuredContent (every core tool declares an outputSchema) and as a JSON string in content[0].text, for clients that read only text.

detail: "compact" returns the resolved subject, the answer, the claims it rests on and counts, in under 2 KB. Leave it out for the full page.

research, compact

curl -s "https://exchange-production-9123.up.railway.app/mcp/core?c=docs" \
  -H "Content-Type: application/json" \
  -H "Accept: application/json, text/event-stream" \
  -d '{"jsonrpc":"2.0","id":2,"method":"tools/call","params":{"name":"research",
       "arguments":{"question":"Which BDCs lend to Auctane, and which of them are current lenders?",
                    "detail":"compact"}}}'

What production returned at 2026-10-11T20:21:43Z. result.structuredContent in full, re-indented. The same JSON also arrives as text in result.content[0].text.

{
 "dfx": {
  "capability": "research",
  "layer": "dfx_intelligence",
  "version": "1.0.0",
  "answered_at": "2026-10-11T20:21:43.373145+00:00"
 },
 "ok": true,
 "state": "OK",
 "schema": "dfx.research/2",
 "generated_at": "2026-10-11T20:21:43.373145+00:00",
 "answer_state": "OK",
 "detail": "compact",
 "identities": {
  "state": "RESOLVED",
  "subject": {
   "dfx_id": "dfx:pc:d071f992-5b4e-dffb-9f2c-22cb2204622b",
   "name": "Auctane Inc",
   "type": "borrower"
  }
 },
 "answer": {
  "text": "At 2026-06-30, 29 BDCs held positions in Auctane Inc on their own schedules of investments; the largest: Blackstone Private Credit Fund ($889.4M of debt at fair value over 2 tranches; principal $902.9M), Blackstone Secured Lending Fund ($277.3M of debt at fair value; principal $281.6M), ARES CAPITAL CORP ($241.6M of debt at fair value; principal $245.3M), Goldman Sachs Private Credit Corp. ($217.7M of debt at fair value; principal $221.0M), and 1 more on the next page (continue with page.continuation); 24 further BDC lenders are withheld for this access tier. Its debt on the tape matures from…",
  "basis": [
   "r1",
   "r2",
   "r3",
   "r4",
   "e1",
   "r6"
  ]
 },
 "claims": [
  {
   "claim_id": "clm_b09515e7250a04a0f9093e3b",
   "row": "r1",
   "predicate": "LENDER_TO",
   "claim_type": "VERIFIED_FACT"
  },
  {
   "claim_id": "clm_b124865cf2a38a3bd5a0d414",
   "row": "r1",
   "predicate": "LENDER_TO_AMOUNT_USD",
   "claim_type": "VERIFIED_FACT"
  },
  {
   "claim_id": "clm_87bbceed44972806f2371aad",
   "row": "r2",
   "predicate": "LENDER_TO",
   "claim_type": "VERIFIED_FACT"
  }
 ],
 "counts": {
  "facts": 1,
  "relationships": 5,
  "events": 0,
  "claims_total": 19,
  "rows_total": 14,
  "uncertainty": 0,
  "coverage_limits": 1
 },
 "withheld": {
  "access": "anonymous",
  "withheld_in_this_answer": {
   "rows": 24,
   "why": "rows whose names the access gate withheld are left out of this answer rather than shown masked"
  }
 },
 "more": "detail=research returns the facts, relationships, claims and limits in full"
}

Standard library only. The full answer pages whole claims at a time; pass page.continuation back as continue to get the next page. A continuation returns the next page of the same plan; it does not re-run the question.

research and continue

# Python 3.8+, standard library only. One research call, then its next page.
import json
import urllib.request

MCP = "https://exchange-production-9123.up.railway.app/mcp/core?c=docs"


def call(tool, arguments, rpc_id=1):
    body = json.dumps({
        "jsonrpc": "2.0", "id": rpc_id, "method": "tools/call",
        "params": {"name": tool, "arguments": arguments},
    }).encode()
    req = urllib.request.Request(MCP, data=body, headers={
        "Content-Type": "application/json",
        "Accept": "application/json, text/event-stream",
        "User-Agent": "my-research-agent/1.0",
    })
    with urllib.request.urlopen(req, timeout=60) as resp:
        result = json.load(resp)["result"]
    return result["structuredContent"]


page1 = call("research", {
    "question": "Which BDCs lend to Auctane, and which of them are current lenders?",
})
print(page1["answer_state"], "|", page1["answer"]["text"][:160])
for row in page1["relationships"]:
    print(" ", row["type"], "|", row["subject"]["name"], "| current:", row.get("current"), "|", row["claim_type"], "|", row["cite"]["url"])
print("page", page1["page"]["index"], "of", page1["page"]["pages"])

if page1["page"].get("continuation"):
    page2 = call("research", {"continue": page1["page"]["continuation"]}, rpc_id=2)
    for row in page2["relationships"]:
        print(" ", row["type"], "|", row["subject"]["name"], "| current:", row.get("current"), "|", row["claim_type"], "|", row["cite"]["url"])
    print("page", page2["page"]["index"], "of", page2["page"]["pages"])

What production returned at 2026-10-11T20:22:21Z. Standard output in full.

OK | At 2026-06-30, 29 BDCs held positions in Auctane Inc on their own schedules of investments; the largest: Blackstone Private Credit Fund ($889.4M of debt at fair
  BDC_SCHEDULE_HOLDING | Blackstone Private Credit Fund | current: True | VERIFIED_FACT | https://www.sec.gov/Archives/edgar/data/1803498/000180349826000048/bcred-20260630.htm
  BDC_SCHEDULE_HOLDING | Blackstone Secured Lending Fund | current: True | VERIFIED_FACT | https://www.sec.gov/Archives/edgar/data/1736035/000173603526000016/bxsl-20260630.htm
  BDC_SCHEDULE_HOLDING | ARES CAPITAL CORP | current: True | VERIFIED_FACT | https://www.sec.gov/Archives/edgar/data/1287750/000162828026050307/arcc-20260630.htm
  BDC_SCHEDULE_HOLDING | Goldman Sachs Private Credit Corp. | current: True | VERIFIED_FACT | https://www.sec.gov/Archives/edgar/data/1920145/000119312526340582/ck0001920145-20260630.htm
page 1 of 3
  BDC_SCHEDULE_HOLDING | ARES STRATEGIC INCOME FUND | current: True | VERIFIED_FACT | https://www.sec.gov/Archives/edgar/data/1918712/000162828026054923/asif-20260630.htm
  SPONSOR_OF_BORROWER | Thoma Bravo | current: True | REPORTED | https://www.thomabravo.com/press-releases/wwex-group-and-auctane-complete-merger-creating-leading-logistics-provider-shipstation-global
page 2 of 3

Two reads an agent can compose itself: resolve_name turns a name into a DFX id, and get_borrower_facilities with group_by: "lender" returns one row per BDC lender, each summed from that lender's own filing.

resolve_name, then get_borrower_facilities

// Node 18+ (built-in fetch). Save as lenders.mts and run: npx tsx lenders.mts
const MCP = "https://exchange-production-9123.up.railway.app/mcp/core?c=docs";

async function call(name: string, args: Record<string, unknown>, id = 1) {
  const res = await fetch(MCP, {
    method: "POST",
    headers: {
      "Content-Type": "application/json",
      Accept: "application/json, text/event-stream",
      "User-Agent": "my-research-agent/1.0",
    },
    body: JSON.stringify({ jsonrpc: "2.0", id, method: "tools/call", params: { name, arguments: args } }),
  });
  const { result } = await res.json();
  return result.structuredContent;
}

// 1. a name to a DFX id
const found = await call("resolve_name", { name: "Auctane" });
const borrower = found.results.find((r: any) => r.domain === "private_credit");
console.log(borrower.name, borrower.dfx_id);

// 2. one row per BDC lender, from each lender's own filing
const group = await call("get_borrower_facilities", { dfx_id: borrower.dfx_id, group_by: "lender", limit: 5 }, 2);
console.log(group.state, "| lenders:", group.total);
for (const r of group.results) {
  console.log(" ", r.lender.name, "|", r.as_of, "|", r.fair_value_usd, "|", r.claim_type, "|", r.cite_url);
}

What production returned at 2026-10-11T20:48:14Z. Standard output in full.

Auctane Inc dfx:pc:d071f992-5b4e-dffb-9f2c-22cb2204622b
OK | lenders: 29
  Blackstone Private Credit Fund | 2026-06-30 | 889367000 | VERIFIED_FACT | https://www.sec.gov/Archives/edgar/data/1803498/000180349826000048/bcred-20260630.htm
  Blackstone Secured Lending Fund | 2026-06-30 | 277347000 | VERIFIED_FACT | https://www.sec.gov/Archives/edgar/data/1736035/000173603526000016/bxsl-20260630.htm
  ARES CAPITAL CORP | 2026-06-30 | 241600000 | VERIFIED_FACT | https://www.sec.gov/Archives/edgar/data/1287750/000162828026050307/arcc-20260630.htm
  Goldman Sachs Private Credit Corp. | 2026-06-30 | 217685000 | VERIFIED_FACT | https://www.sec.gov/Archives/edgar/data/1920145/000119312526340582/ck0001920145-20260630.htm
  ARES STRATEGIC INCOME FUND | 2026-06-30 | 117539100 | VERIFIED_FACT | https://www.sec.gov/Archives/edgar/data/1918712/000162828026054923/asif-20260630.htm

changes_since with a domain, an optional dfx_id and an ISO since returns dated events. Each carries occurred_at (when it happened, and on what basis) and first_seen_at (when DFX first read it), and the answer counts them by novelty so a newly read old quarter is never presented as news. Pass cursor_hint.next_since as the next since to poll.

changes_since

curl -s "https://exchange-production-9123.up.railway.app/mcp/core?c=docs" \
  -H "Content-Type: application/json" \
  -H "Accept: application/json, text/event-stream" \
  -d '{"jsonrpc":"2.0","id":4,"method":"tools/call","params":{"name":"changes_since",
       "arguments":{"domain":"private_credit","dfx_id":"dfx:pc:d071f992-5b4e-dffb-9f2c-22cb2204622b",
                    "since":"2026-04-01"}}}'

What production returned at 2026-10-11T20:24:09Z. Fields excerpted from the answer; every value shown is verbatim.

{
 "state": "OK",
 "count": 1,
 "novelty_filter": {
  "returned_by_novelty": {
   "NEW_EVENT": 1
  }
 },
 "results": [
  {
   "cite_url": "https://www.sec.gov/Archives/edgar/data/1959604/000119312526345216/ck0001959604-20260630.htm",
   "cite_granularity": "document",
   "claim_type": "VERIFIED_FACT",
   "event_type": "NEW_LENDER",
   "subject": {
    "dfx_id": "dfx:pc:9ba07849-6ea0-3d70-60a3-ce0d407d8bab",
    "name": "Jefferies Credit Partners BDC Inc.",
    "entity_type": "bdc"
   },
   "related": {
    "dfx_id": "dfx:pc:d071f992-5b4e-dffb-9f2c-22cb2204622b",
    "name": "Auctane Inc",
    "entity_type": "borrower"
   },
   "headline": "Jefferies Credit Partners BDC Inc. joins Auctane Inc term loan (first lien) held by 24 other BDCs",
   "occurred_at": "2026-06-30",
   "occurred_basis": "filing",
   "first_seen_at": "2026-09-21T17:16:09.14437+00:00",
   "materiality": "market",
   "magnitude": 5913000,
   "magnitude_unit": "usd",
   "confidence": 0.9
  }
 ],
 "cursor_hint": {
  "next_since": "2026-10-11T20:24:09.781060+00:00",
  "note": "pass next_since as `since` on the next call to see only what DFX saw after this answer"
 }
}

For pipelines that call plain HTTP. https://dfxintel.com/api/data-factory/v1 lists every route. /search and /explore answer without a key; /forward, /changes and /universes need a signed-in session or a key.

GET /v1/search

curl -s "https://dfxintel.com/api/data-factory/v1/search?q=auctane&limit=3"

What production returned at 2026-10-11T20:24:08Z. The first of 3 hits; the records array that follows is left out.

{
 "version": "v1",
 "q": "auctane",
 "hits": [
  {
   "graph": "pc",
   "entityType": "borrower",
   "id": "d071f992-5b4e-dffb-9f2c-22cb2204622b",
   "name": "Auctane Inc",
   "matched": null,
   "matchKind": "name",
   "subclass": "Air Freight & Logistics",
   "classState": "PERFORMING",
   "city": null,
   "state": null,
   "context": "Thoma Bravo",
   "score": 1.37964,
   "href": "/private-credit/borrowers/d071f992-5b4e-dffb-9f2c-22cb2204622b",
   "tier": "observed",
   "also": [],
   "see": null,
   "capital": {
    "status": "CONFIRMED",
    "confidence": 0.95,
    "evidenceCount": 31,
    "lastRaise": "2026-06-30",
    "equitySold": null,
    "identity": "name_only"
   }
  }
 ]
}