Analytics
agenticfinancegraph.com
Provides tools to query a ledger of AI-agent money on Base, including market stats, agent lookup, rankings, payment records, and anomaly detections.
ENDPOINT 1
https://agenticfinancegraph.com/mcp
MCP server metadata
- Name
- agentic-finance-graph
- Version
- 1.1.0
Agentic Finance Graph is an independent ledger of money held and spent by AI agents, measured from the chain: Base in full, plus ERC-8004 registrations and owner payments on BNB Smart Chain, Ethereum, Arbitrum, OP Mainnet, Polygon and Solana. Every figure carries its measurement time and a definition id; call definition(id) before quoting a number. Read-only; nothing here can move funds.
Known tools 11
market_stateThe ledger's headline figures for AI-agent money, each with its value, unit, measurement time and definition id.
Inferred read-onlyfind_agentLook up one ERC-8004 agent by token id on Base, slug, or wallet address (0x.
Inferred read-onlyagent_recordThe free record of one ranked agent: rank with evidence, bindings, and its 25 newest payments with counterparties.
Inferred read-onlyranked_agentsThe top ranked agents (L7 and above: a bound wallet was seen paying a different address after registration), sorted by the ledger's default order.
Inferred read-onlydetectionsAnomalies our detectors logged, newest first: drain-shaped payments, retry storms, mint bursts, owner changes under a binding, delegation to unknown code.
Inferred read-onlydefinitionThe frozen definition of a metric: what it counts, the method, what it excludes and what it does not claim.
Inferred read-onlymetric_historyThe history of one measured metric from the ledger's archive (daily points, plus 5-minute points for the last 48 hours).
Inferred read-onlysince_lastOne measured figure with the stored sample it moved from: current, prior, delta, delta_ratio, both timestamps, definition id, unit, and whether the move is material under the published thresholds.
Inferred read-onlycounterparty_previewFor one receiving address on Base (or an x402 resource URL listed in the Bazaar): how many counted payments registered agents made into it, how many distinct agents and how many at L7 or above, first and last seen, and the routing hops excluded.
Inferred read-onlyagent_statementThe latest 3-hour statement for one ranked agent: payments out split into spend, routing hops and payments whose receipt is not read yet; what left its control; income; open flags; the hash of the previous statement; and a Merkle proof against the window's Ed25519-signed root.
Inferred read-onlyevidence_pack_quotePrice and how to buy a dated evidence pack over x402 (USDC on Base).
Inferred read-onlyCONNECT WITH APPROVAL
Client installation
Review this server and its permissions before adding it. Secret placeholders must be set locally.
Codex
~/.codex/config.toml
[mcp_servers.agentic-finance-graph]
url = "https://agenticfinancegraph.com/mcp"
enabled = true
Claude Code
.mcp.json
{
"mcpServers": {
"agentic-finance-graph": {
"type": "http",
"url": "https://agenticfinancegraph.com/mcp"
}
}
}
Claude Desktop
Settings → Connectors → Add custom connector
Name: agentic-finance-graph
Remote MCP URL: https://agenticfinancegraph.com/mcp
Add this remote URL as a custom connector in Claude Desktop. Availability depends on the user plan and workspace policy.
Cursor
.cursor/mcp.json
{
"mcpServers": {
"agentic-finance-graph": {
"url": "https://agenticfinancegraph.com/mcp"
}
}
}
Visual Studio Code
.vscode/mcp.json
Add to Visual Studio Code{
"servers": {
"agentic-finance-graph": {
"type": "http",
"url": "https://agenticfinancegraph.com/mcp"
}
}
}
Generic MCP
Client-specific MCP configuration
{
"name": "agentic-finance-graph",
"transport": "streamable-http",
"url": "https://agenticfinancegraph.com/mcp"
}
MCP Inspector
Run the official MCP Inspector locally and enter the indexed Streamable HTTP endpoint.
TRUST AND VERIFICATION EVIDENCE
Loading Trust v2 evidence…
Checking the associated registrable domain. The BuiltWith key remains server-side.
Evidence is source-attributed and does not guarantee that a third-party server is safe. Risk labels are conservative metadata heuristics.