Power your agent
คำสั่งของผู้เผยแพร่เอง ไม่ใช่เอนด์พอยต์ของ PlugMCP
Host a copy with our keys and logs.
npx -y @agent-score/[email protected]Claude Code ไม่มีลิงก์ติดตั้งสำหรับคำสั่งแบบโลคัล ให้คัดลอกคำสั่งด้านล่างแล้วรันในเทอร์มินัล
claude mcp add agent-score-sdk -- npx -y @agent-score/sdk@2.9.4รันในเทอร์มินัล
{ "mcpServers": { "agent-score-sdk": { "command": "npx", "args": [ "-y", "@agent-score/[email protected]" ] } }}claude_desktop_config.json
URL แบบรีโมตหรือคำสั่งบนเครื่องของคุณ? การติดตั้งสองแบบต่างกันอย่างไร
รันบน PlugMCP
A new server you create. It is not this listing's official endpoint. Use the publisher install when you want their URL and their credentials.
เปิดจากผู้เผยแพร่
The official TypeScript/Node.js client for AgentScore. Verify the human behind an agent (KYC, age, sanctions, jurisdiction) and gate payments, in a few lines.
TypeScript client for the AgentScore APIs
npm install @agent-score/sdk
# or
bun add @agent-score/sdk
import { AgentScore } from "@agent-score/sdk";
const client = new AgentScore({ apiKey: "as_live_..." });
// Identity gate with policy (paid)
const gated = await client.assess("0x1234...", {
policy: {
require_kyc: true,
require_sanctions_clear: true,
min_age: 21,
},
});
if (gated.decision === "deny") {
console.log(gated.decision_reasons); // ["kyc_required"]
console.log(gated.verify_url); // URL for operator verification
}
// Verification level of the operator behind the wallet
console.log(gated.operator_verification?.level); // "none" | "kyc_verified"
Agents without wallets can use operator credentials for identity:
// Assess with an operator credential instead of a wallet address
const result = await client.assess(null, { operatorToken: "opc_..." });
console.log(result.decision); // "allow" | "deny"
Bootstrap identity for first-time agents. The success body carries structured next_steps (with action: "deliver_verify_url_and_poll") and a cross-merchant agent_memory hint. Poll responses carry next_steps.action from the typed NextStepsAction union (continue_polling, retry_merchant_request_with_operator_token, use_stored_operator_token, create_new_session, verification_failed, contact_support).
// Create a session, returns a verify_url for the user and a poll_url for the agent
const session = await client.createSession();
console.log(session.verify_url, session.poll_url, session.poll_secret);
console.log(session.next_steps.action); // "deliver_verify_url_and_poll"
// Poll until the user completes verification
const status = await client.pollSession(session.session_id, session.poll_secret);
if (status.status === "verified") {
console.log(status.operator_token); // "opc_...", use for future requests
}
// Registration-only session: the buyer signs in with an AgentScore account, no identity documents.
await client.createSession({ kind: "sign_in" });
assess() responses include resolved_operator and linked_wallets[], all same-operator sibling wallets (claimed via SIWE or captured via prior associateWallet). The list may mix EVM addresses (0x... lowercased) and Solana addresses (base58, case-preserved) for cross-chain operators; merchants doing wallet-signer-match checks should accept a payment signed by any address in the list, regardless of chain. The address parameter on assess() accepts either format; the network is auto-detected from the address shape.
Pass signer: { address, network } on assess() to opt into server-side wallet-signer-match and OFAC SDN wallet-address screening on the same call. The response carries two new verdicts:
const result = await client.assess("0xclaimed...", {
signer: { address: "0xsigner...", network: "evm" },
policy: { require_sanctions_clear: true },
});
// signer_match: wallet-binding verdict
// kind: 'pass' | 'wallet_signer_mismatch' | 'wallet_auth_requires_wallet_signing'
// plus claimed_operator / signer_operator / expected_signer / actual_signer / linked_wallets / agent_instructions
if (result.signer_match?.kind === "wallet_signer_mismatch") {
// signer wallet resolves to a different operator than the claimed address
}
// signer_sanctions: OFAC SDN wallet-address verdict (discriminated union)
// { status: 'clear' } | { sanctioned: true, ofac_label, sdn_uid, listed_at } | { status: 'unavailable' }
if (result.signer_sanctions && "sanctioned" in result.signer_sanctions) {
console.log("OFAC hit:", result.signer_sanctions.ofac_label, result.signer_sanctions.sdn_uid);
}
Wallet-OFAC SDN enforcement on the signer block is unconditional whenever a signer is supplied; no policy.require_sanctions_clear opt-in is required. The API flips decision to deny when signer_sanctions is sanctioned: true OR status: 'unavailable', with decision_reasons including sanctions_flagged or sanctions_check_unavailable respectively (fail-closed; OFAC strict-liability). policy.require_sanctions_clear is the separate NAME-based screen on the resolved operator's KYC identity.
Pass signer.address: null for rails without a wallet signer (Stripe SPT, card-only). The API responds with signer_match.kind = 'wallet_auth_requires_wallet_signing' and a parsed agent_instructions block telling the agent to switch to X-Operator-Token auth, spread the block directly into a 403 body.
const cred = await client.createCredential({ label: "my-agent", ttl_days: 7 });
console.log(cred.credential); // shown once
const list = await client.listCredentials();
console.log(list); // active, non-expired credentials
await client.revokeCredential(cred.id);
After an agent authenticated via operator_token completes a payment, report the signer wallet so AgentScore can build a cross-merchant credential↔wallet profile. Fire-and-forget, first_seen is informational only. network is the key-derivation family: "evm" for any EVM chain (Base, Tempo, Ethereum, …) or "solana" for Solana.
await client.associateWallet({
operatorToken: "opc_...",
walletAddress: signerFromPayment, // e.g. EIP-3009 `from` or Tempo MPP DID address
network: "evm",
idempotencyKey: paymentIntentId, // optional, agent retries of the same payment no-op
});
import { AgentScore, AgentScoreError } from "@agent-score/sdk";
try {
await client.assess("0xinvalid");
} catch (err) {
if (err instanceof AgentScoreError) {
console.error(err.code, err.message, err.status);
}
}
AgentScoreError.details carries the rest of the response body (verify_url, linked_wallets, claimed_operator, actual_signer, expected_signer, reasons, agent_memory) so callers can branch on granular denial codes without re-parsing.
For status-code-specific recovery, the SDK throws typed subclasses of AgentScoreError. All inherit from AgentScoreError so existing catch (err) { if (err instanceof AgentScoreError) ... } still works.
import {
AgentScore, AgentScoreError, TokenExpiredError, QuotaExceededError, TimeoutError,
} from "@agent-score/sdk";
try {
await client.assess("0xabc...", { policy: { require_kyc: true } });
} catch (err) {
if (err instanceof TokenExpiredError) {
console.log("Verify at:", err.verifyUrl, "poll with:", err.pollSecret);
} else if (err instanceof QuotaExceededError) {
console.log("Account quota reached, surface to user; don't retry.");
} else if (err instanceof TimeoutError) {
console.log("Network timeout, retry with backoff.");
} else if (err instanceof AgentScoreError) {
console.error(err.code, err.message);
}
}
assess() responses include an optional quota field captured from X-Quota-Limit / X-Quota-Used / X-Quota-Reset response headers. Use it to monitor approach-to-cap proactively (warn at 80%, alert at 95%) before a 429:
const result = await client.assess("0xabc...", { policy: { require_kyc: true } });
if (result.quota && result.quota.limit && result.quota.used) {
const pct = (result.quota.used / result.quota.limit) * 100;
if (pct > 80) console.warn(`AgentScore quota at ${pct.toFixed(1)}%, resets ${result.quota.reset}`);
}
quota is undefined when the API doesn't emit the headers (Enterprise / unlimited tiers). On a 429 response the SDK throws QuotaExceededError / RateLimitedError instead of returning a body, so quota is only readable on successful calls; drive proactive alerting off the success-path field.
telemetrySignerMatch(payload) is a fire-and-forget POST to /v1/telemetry/signer-match so AgentScore can track aggregate signer-binding behavior across merchants. Used internally by @agent-score/commerce's gate; available directly for custom integrations that perform their own wallet-signer-match checks.
{ "mcpServers": { "agent-score-sdk": { "command": "npx", "args": [ "-y", "@agent-score/[email protected]" ] } }}เครื่องมือ
ยังไม่มีรายการเครื่องมือ เซิร์ฟเวอร์แบบรีโมตจะได้รายการหลังการตรวจสอบสถานะครั้งแรก
FAQ
คัดลอกคอนฟิก stdio สำหรับ Cursor, Claude Desktop, Claude Code หรือ VS Code ได้ในหน้านี้ คอนฟิกนี้ใช้การติดตั้งของผู้เผยแพร่ ไม่ใช่พร็อกซีของ PlugMCP
ระเบียนนี้ไม่ได้ระบุตัวแปรสภาพแวดล้อมที่จำเป็น
@agent Score/sdk ทำงานแบบโลคัลผ่าน stdio
ตรวจสอบล่าสุดเมื่อ 2026-11-08 TypeScript client for the AgentScore APIs