agent402-mcp 0.13.1 → 0.13.3
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/README.md +6 -6
- package/index.js +4 -3
- package/package.json +6 -6
package/README.md
CHANGED
|
@@ -1,8 +1,8 @@
|
|
|
1
1
|
# agent402-mcp
|
|
2
2
|
|
|
3
|
-
MCP server for [Agent402](https://agent402.tools), the applied layer of [Agentic Finance](https://agent402.tools/agentic-finance) - a catalog of **500+: 400+ pay-per-call web tools +
|
|
3
|
+
MCP server for [Agent402](https://agent402.tools), the applied layer of [Agentic Finance](https://agent402.tools/agentic-finance) - a catalog of **500+: 400+ pay-per-call web tools + 80+ curated multi-tool skill packs** for AI agents (every one tested, priced, and settled on-chain; every one earns its place), paid per call in USDC via the [x402 protocol](https://www.x402.org), **with compute (proof-of-work)** when no wallet is configured, or **by card** through a prepaid credits key. (The hosted API is dual-stack: it also accepts [MPP](https://agent402.tools/what-is-mpp) clients on the same 402, settling on Base/Celo or natively on Tempo; this package pays via x402 or credits.) Built by [Havok Holdings LLC](https://github.com/MikeyPetrillo/Agent402).
|
|
4
4
|
|
|
5
|
-
Your agent gets browser rendering, screenshots, PDF text extraction, URL→markdown, live web search **+ web answers with citations**, live **financial/crypto/macro data** (
|
|
5
|
+
Your agent gets browser rendering, screenshots, PDF text extraction, URL→markdown, live web search **+ web answers with citations**, live **financial/crypto/macro data** (US equity quotes and daily bars from Databento, CoinGecko, FRED, ECB FX, World Bank, yield curve), **SEC EDGAR filings** (10-K/10-Q text, XBRL, insider, 13F, IPO calendar), **deterministic stats & forecasting** (Pearson correlation, OLS, Holt-Winters), **compression** (gzip/brotli), DNS/TLS/WHOIS + email-deliverability checks, wallet-keyed shared memory, and 200+ deterministic pure-CPU utilities - plus 100+ **skill packs** like `security-audit`, `trend-analysis`, `structured-scrape`, `decode-blob`, and `forecasting-bake-off` callable as MCP prompts, and the **report products** (deep research, company dossier, 13F fund report, domain audit, token risk, FDA recall, insider flow, market brief) as ordinary catalog slugs. Payment handled invisibly underneath the MCP calls. No signup, no API key.
|
|
6
6
|
|
|
7
7
|
## Quick start
|
|
8
8
|
|
|
@@ -15,7 +15,7 @@ wrapped with `mppx`'s `McpClient.wrap()` (USDC on Base/Celo, or native Tempo)
|
|
|
15
15
|
pays and retries on its own, receipt in `_meta`. For no rate limit, or to pay
|
|
16
16
|
over x402 or by card instead, run this package locally:
|
|
17
17
|
|
|
18
|
-
With a funded wallet (USDC on Base, Polygon, Arbitrum, Monad,
|
|
18
|
+
With a funded wallet (USDC on any EVM rail the server offers - Base, Polygon, Arbitrum, Monad, Celo, Avalanche, Sei, Optimism - or USDG on Robinhood Chain, or USDC on Solana via `SOLANA_AGENT_KEY`; the service also settles on Stellar and Algorand, which this package does not sign) - every tool available:
|
|
19
19
|
|
|
20
20
|
```json
|
|
21
21
|
{
|
|
@@ -76,8 +76,8 @@ caps, what's been spent, and what remains. With no wallet key and no credits key
|
|
|
76
76
|
the server runs in proof-of-work mode (pure-CPU tools stay free). Use dedicated
|
|
77
77
|
low-value wallets for `AGENT_KEY` / `SOLANA_AGENT_KEY`, funded only with what
|
|
78
78
|
you intend to spend. Most tools cost $0.001–$0.02. The routing tiers top out
|
|
79
|
-
at $
|
|
80
|
-
report products run $0.
|
|
79
|
+
at $3.30 (`route-execute-pro`); multi-tool skill packs run $0.003 to $0.119; and the
|
|
80
|
+
report products run $0.60 to $2.00 per report (domain-audit $0.60 up to the ticker pack at $2.00),
|
|
81
81
|
so set `AGENT402_MAX_PER_CALL` if you want a hard per-call ceiling.
|
|
82
82
|
|
|
83
83
|
## How it works
|
|
@@ -98,7 +98,7 @@ so set `AGENT402_MAX_PER_CALL` if you want a hard per-call ceiling.
|
|
|
98
98
|
| ≤ $0.50 | $0.55 | `POST /api/route/execute-max` |
|
|
99
99
|
|
|
100
100
|
A tool priced above the tier's ceiling returns a self-correcting 409 naming its direct route.
|
|
101
|
-
- **Report products** are catalog slugs like any other, so `catalog.call` runs them with a wallet or a credits key: `research` ($0.
|
|
101
|
+
- **Report products** are catalog slugs like any other, so `catalog.call` runs them with a wallet or a credits key: `research` ($0.60), `research-pro` ($0.85), `research-max` ($1.10), `market-brief` ($0.85), `dossier` ($0.85), `dossier-max` ($1.10), `fund-report` ($0.60), `fund-report-max` ($0.85), `domain-audit` ($0.60), `domain-audit-pro` ($0.85), `token-risk` ($0.60), `token-risk-pro` ($0.85), `token-brief` ($0.60), `recall-report` ($0.60), `insider-report` ($0.60), `filing-report` ($0.85), `ticker-pack` ($2.00); the live figures are always at https://agent402.tools/api/pricing. The same reports are sold to people by card at https://agent402.tools/reports for $2 to $5 depending on depth: the card price includes payment processing, and an agent paying per call pays the lower tool price for the same report. The recurring monitors (domain, SEC filing, token, fund, recall, insider, IPO, research - $5/month) are at https://agent402.tools/monitors.
|
|
102
102
|
|
|
103
103
|
## Workflows (skill packs)
|
|
104
104
|
|
package/index.js
CHANGED
|
@@ -72,7 +72,7 @@ let spentUsd = 0;
|
|
|
72
72
|
|
|
73
73
|
const DEFAULT_CURATED = [
|
|
74
74
|
// Flagship demand set — keep aligned with src/mcp-flagship.js FLAGSHIP_SLUGS.
|
|
75
|
-
// Search/answer is the front door; long tail stays behind
|
|
75
|
+
// Search/answer is the front door; long tail stays behind catalog.search/catalog.call.
|
|
76
76
|
"search", "answer", "search-news", "render",
|
|
77
77
|
"stock-quote", "transcribe", "memory-read", "memory-write",
|
|
78
78
|
];
|
|
@@ -139,6 +139,7 @@ function getPayFetch() {
|
|
|
139
139
|
const { x402Client } = await import("@x402/core/client");
|
|
140
140
|
const { wrapFetchWithPayment } = await import("@x402/fetch");
|
|
141
141
|
const client = new x402Client();
|
|
142
|
+
client.setSpendControls?.(false); // @x402/core 2.23+ defaults to a $1 pegged-assets-only cap; this package bounds spend itself
|
|
142
143
|
if (AGENT_KEY) {
|
|
143
144
|
const { registerExactEvmScheme } = await import("@x402/evm/exact/client");
|
|
144
145
|
const { privateKeyToAccount } = await import("viem/accounts");
|
|
@@ -811,14 +812,14 @@ try {
|
|
|
811
812
|
// Don't hard-exit: starting with an empty catalog still lets the server
|
|
812
813
|
// connect and answer introspection (tools/list) — required to pass directory
|
|
813
814
|
// health checks (e.g. Glama) and more resilient if the catalog endpoint is
|
|
814
|
-
// briefly unreachable.
|
|
815
|
+
// briefly unreachable. catalog.search/catalog.call just return nothing until the
|
|
815
816
|
// catalog is reachable again.
|
|
816
817
|
log(`Could not load the catalog from ${BASE}: ${err.message} — starting with an empty catalog`);
|
|
817
818
|
}
|
|
818
819
|
const requested = (process.env.AGENT402_TOOLS || DEFAULT_CURATED.join(","))
|
|
819
820
|
.split(",").map((s) => s.trim()).filter(Boolean);
|
|
820
821
|
curated = requested.map((slug) => catalog.get(slug)).filter(Boolean);
|
|
821
|
-
log(`catalog: ${catalog.size} tools from ${BASE}; ${curated.length} first-class, rest via
|
|
822
|
+
log(`catalog: ${catalog.size} tools from ${BASE}; ${curated.length} first-class, rest via catalog.search/catalog.call`);
|
|
822
823
|
log(
|
|
823
824
|
HAS_WALLET
|
|
824
825
|
? `payment: USDC via x402 (${[AGENT_KEY && "EVM", SOLANA_AGENT_KEY && "Solana"].filter(Boolean).join(" + ")} wallet configured; max/call ${MAX_PER_CALL === Infinity ? "unlimited" : `$${MAX_PER_CALL}`}, budget ${BUDGET === Infinity ? "unlimited" : `$${BUDGET}`})`
|
package/package.json
CHANGED
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
{
|
|
2
2
|
"name": "agent402-mcp",
|
|
3
|
-
"version": "0.13.
|
|
3
|
+
"version": "0.13.3",
|
|
4
4
|
"mcpName": "io.github.MikeyPetrillo/agent402",
|
|
5
5
|
"author": "Havok Holdings LLC <mike@agent402.tools> (https://agent402.tools)",
|
|
6
6
|
"homepage": "https://agent402.tools",
|
|
@@ -71,16 +71,16 @@
|
|
|
71
71
|
"dependencies": {
|
|
72
72
|
"@modelcontextprotocol/sdk": "^1.30.0",
|
|
73
73
|
"@solana/kit": "^5.1.0",
|
|
74
|
-
"@x402/core": "2.
|
|
75
|
-
"@x402/evm": "2.
|
|
76
|
-
"@x402/fetch": "2.
|
|
77
|
-
"@x402/svm": "2.
|
|
74
|
+
"@x402/core": "2.26.0",
|
|
75
|
+
"@x402/evm": "2.26.0",
|
|
76
|
+
"@x402/fetch": "2.26.0",
|
|
77
|
+
"@x402/svm": "2.26.0",
|
|
78
78
|
"viem": "^2.21.0"
|
|
79
79
|
},
|
|
80
80
|
"overrides": {
|
|
81
81
|
"qs": "6.16.0",
|
|
82
82
|
"ws": "^8.21.0",
|
|
83
|
-
"hono": "4.
|
|
83
|
+
"hono": "4.13.7",
|
|
84
84
|
"fast-uri": "3.1.7",
|
|
85
85
|
"body-parser": "2.3.0",
|
|
86
86
|
"@hono/node-server": "2.0.12",
|