Card snapshot

This is a frozen copy of the agent's agent-card.json as we observed it at the timestamp above. We capture a new snapshot every time the card's content hash changes. Useful for: forensic drift analysis, verifying downstream callers see the right version, reproducing routing decisions made historically.

{
  "protocolVersion": "0.3.0",
  "name": "DFX Intelligence",
  "description": "Evidence-backed private markets intelligence for AI agents, 134 read-only MCP tools across private credit and BDC portfolios; private equity firms, funds and deals; venture capital; family offices; RIAs and advisor moves; independent sponsors; allocators and LP commitments; real estate funds; US real estate debt and property records. Facts carry their source and observation date, and every answer states OK, NO_MATCH, NOT_COVERED or UNKNOWN rather than guessing. 129 of 134 tools are free to call with no key; 5 save an account's own research watches and need an account key. Without a DFX plan, list answers name the first rows and count the rest, and contact values are never returned. REAL ESTATE COVERAGE. NATIONAL: federal programme debt with maturity dates across 52 states, LIHTC compliance period endings, HUD subsidy contract expiries, distress and foreclosure flags, and commercial tenancy: who occupies a building, how much of it, and when the lease expires. MASSACHUSETTS ONLY: parcels, ownership and management relationships, and recorded sales. Building permits and certificates of occupancy are Boston only. Call dfx_coverage for the measured grid of every event family and the states each one covers. Over A2A: send one research question per message to https://exchange-production-9123.up.railway.app/a2a (JSON-RPC; A2A 1.0 and 0.3 methods). Without a DFX plan, list answers name the first rows and count the rest, and contact values are never returned. Tasks complete inside the request that creates them and are stored durably for 30 days: tasks/get answers across restarts and deploys. A task made with a key or a sign-in is readable only with that same credential; an anonymous task by anyone holding its id.",
  "version": "0.16.0",
  "url": "https://exchange-production-9123.up.railway.app/a2a",
  "preferredTransport": "JSONRPC",
  "additionalInterfaces": [
    {
      "url": "https://exchange-production-9123.up.railway.app/a2a",
      "transport": "JSONRPC"
    }
  ],
  "supportedInterfaces": [
    {
      "url": "https://exchange-production-9123.up.railway.app/a2a",
      "protocolBinding": "JSONRPC",
      "protocolVersion": "1.0"
    },
    {
      "url": "https://exchange-production-9123.up.railway.app/a2a",
      "protocolBinding": "JSONRPC",
      "protocolVersion": "0.3"
    }
  ],
  "provider": {
    "organization": "DFX Intelligence",
    "url": "https://dfxintel.com/agents"
  },
  "documentationUrl": "https://dfxintel.com/agents",
  "iconUrl": "https://exchange-production-9123.up.railway.app/icon.png",
  "capabilities": {
    "streaming": false,
    "pushNotifications": false,
    "stateTransitionHistory": false
  },
  "securitySchemes": {
    "dfx_account_key": {
      "type": "apiKey",
      "in": "header",
      "name": "X-API-Key",
      "description": "Optional. A DFX account key (dfx_live_...); also accepted as Authorization: Bearer. Without one the call is anonymous."
    }
  },
  "defaultInputModes": [
    "text/plain",
    "application/json"
  ],
  "defaultOutputModes": [
    "application/json",
    "text/plain"
  ],
  "skills": [
    {
      "id": "research",
      "name": "Research one question in one call",
      "description": "One private-markets question in one call: resolved entities, a direct answer built only from cited claims, facts, relationships, dated events, coverage limits and withheld counts. Plans its reads: a lender's position in a borrower at each date named, a borrower's BDC holders, a team's members, an advisor's registrations, plan commitments, Form ADV fields. Paged, never cut. No model inside. Send the question as a text part; a data part may carry the tool's arguments (as_of, continue, depth, detail, entity, question, since, workflow). The task's artifact is the dfx.research/2 object as a data part beside a short text summary.",
      "tags": [
        "private-markets",
        "private-credit",
        "bdc",
        "private-equity",
        "venture-capital",
        "vc",
        "family-offices",
        "ria",
        "wealth-management",
        "independent-sponsors",
        "allocators",
        "limited-partners",
        "real-estate-funds",
        "real-estate",
        "commercial-real-estate",
        "loan-maturity",
        "lihtc",
        "evidence",
        "a2a"
      ],
      "examples": [
        "Which lenders finance Thoma Bravo's portfolio companies, and which of them are current lenders?",
        "Who lends to Kaseya? Separate current lenders from former lenders.",
        "Which advisors joined Rockefeller Capital Management in the last 90 days?",
        "Which funds did CalPERS commit to in 2025, and for how much?"
      ],
      "inputModes": [
        "text/plain",
        "application/json"
      ],
      "outputModes": [
        "application/json",
        "text/plain"
      ]
    },
    {
      "id": "research.credit_by_sponsor",
      "name": "Credit by sponsor",
      "description": "BDC lenders, positions, facilities and sponsors. Ask in plain language, or pin the plan with a data part {\"workflow\": \"credit_by_sponsor\", \"question\": \"...\"}.",
      "tags": [
        "private-credit",
        "bdc",
        "private-equity",
        "evidence"
      ],
      "examples": [
        "Which lenders finance Thoma Bravo's portfolio companies, and which of them are current lenders?",
        "Who lends to Kaseya? Separate current lenders from former lenders."
      ],
      "inputModes": [
        "text/plain",
        "application/json"
      ],
      "outputModes": [
        "application/json",
        "text/plain"
      ]
    },
    {
      "id": "research.advisor_movement",
      "name": "Advisor movement",
      "description": "IAPD registration moves, people and teams. Ask in plain language, or pin the plan with a data part {\"workflow\": \"advisor_movement\", \"question\": \"...\"}.",
      "tags": [
        "ria",
        "wealth-management",
        "evidence"
      ],
      "examples": [
        "Which advisors joined Rockefeller Capital Management in the last 90 days?"
      ],
      "inputModes": [
        "text/plain",
        "application/json"
      ],
      "outputModes": [
        "application/json",
        "text/plain"
      ]
    },
    {
      "id": "research.allocator_to_company",
      "name": "Allocator to company",
      "description": "Plan commitments and capital paths. Ask in plain language, or pin the plan with a data part {\"workflow\": \"allocator_to_company\", \"question\": \"...\"}.",
      "tags": [
        "allocators",
        "limited-partners",
        "private-equity",
        "evidence"
      ],
      "examples": [
        "Which funds did CalPERS commit to in 2025, and for how much?"
      ],
      "inputModes": [
        "text/plain",
        "application/json"
      ],
      "outputModes": [
        "application/json",
        "text/plain"
      ]
    }
  ]
}