Loop-friendly utilities for AI agents: package vulnerability checks (OSV), prompt-injection screening, PII redaction, Federal Register search, SEC EDGAR filings and scholarly paper search. JSON in, JSON out. Failed calls are not charged.
https://router.fluxapay.xyz/api/agent-tools-crowdsparkAudit a whole project before an agent installs or runs it: JSON body {manifest, type, readme}. manifest is package.json (npm) or requirements.txt (PyPI) text. Checks up to 25 dependencies against OSV.dev advisories, deprecation and latest versions, and screens the optional README for prompt injection. Returns one safe, caution or avoid verdict plus a ranked fix list.
Check a package before installing it: known vulnerabilities for one npm, PyPI, cargo, Go or Maven package version (OSV.dev), fixed-in version, latest version and release date, licence, deprecated flag, and a safe, caution or avoid verdict with reasons. Version defaults to latest. Also on https://agents.crowdspark.me/v1/dev/package-advisories with a free daily allowance (25 calls/day per IP, header X-Free-Call: 1 or ?free=1).
Recent SEC EDGAR filings for a US-listed company by ticker or CIK: form type, filing and report dates, 8-K item codes with plain labels, accession number and direct document links. Filter by form (8-K, 10-K, 10-Q, 4, 13F-HR, comma list), since date and limit. Raw public data, not investment advice. Also on https://agents.crowdspark.me/v1/finance/sec-filings with a free daily allowance (25 calls/day per IP, header X-Free-Call: 1 or ?free=1).
Search the US Federal Register: final rules, proposed rules, notices and presidential documents with title, agencies, publication date, effective date, comment deadline, docket IDs, abstract and links. Filter by keyword, type, agency slug and date range. Public domain data, no legal advice. Also on https://agents.crowdspark.me/v1/gov/federal-register with a free daily allowance (25 calls/day per IP, header X-Free-Call: 1 or ?free=1).
Scholarly paper search for research agents: keywords or a DOI in, matching papers out with title, authors, year, venue, DOI, citation count, open access PDF or page link, retraction flag and abstract. Filter by year range and open access, sort by relevance, citations or newest. Source OpenAlex, Crossref fallback. Also on https://agents.crowdspark.me/v1/research/papers with a free daily allowance (25 calls/day per IP, header X-Free-Call: 1 or ?free=1).
Rule-based prompt-injection screen for untrusted text such as scraped web pages, emails and tool output. JSON body {text} (max 50,000 chars). Detects instruction-override phrasing, role-spoofing tags, data-leak links and hidden Unicode in 6 languages. Returns verdict safe, suspicious or malicious, a 0-100 score and matched spans. Text is not stored. Also on https://agents.crowdspark.me/v1/text/injection-check with a free daily allowance (25 calls/day per IP, header X-Free-Call: 1 or ?free=1).
Scrub text before it goes to a model or a log: JSON body {text, mask} (max 100,000 chars). Finds emails, phones, SSNs, cards (Luhn), IBANs, IPs, MAC addresses, API keys, JWTs, private keys, wallet addresses. mask is label, hash or star. Returns redacted text and counts. Not stored. Also on https://agents.crowdspark.me/v1/text/pii-redact with a free daily allowance (25 calls/day per IP, header X-Free-Call: 1 or ?free=1).
Copy this prompt and paste it into your AI agent (like Claude, GPT-4, etc.) to enable automatic X-402 payment handling.
** Your task ** Call the API at: https://router.fluxapay.xyz/api/agent-tools-crowdspark Follow the steps below in order. ** Step 1 - Install FluxA Wallet CLI ** npm install -g @fluxa-pay/fluxa-wallet Or use without installing: npx fluxa-wallet <command> ** Step 2 - Register agent ** fluxa-wallet init --name "<YOUR_AGENT_NAME>" --client "<YOUR_CLIENT>" The response may include an authorization URL. Present the user with options: [Yes, open the link] [No, don't open]. If YES: run 'open "<URL>"' to open in their browser. Verify: fluxa-wallet status ** Step 3 - Discover endpoints ** curl https://router.fluxapay.xyz/api/agent-tools-crowdspark Returns JSON with: name, description, endpoints (paths, methods, descriptions, prices), paymentRequired, and networks. ** Step 4 - Choose payment method ** Ask the user: [On-chain USDC (Base)] or [FluxA Monetize Credits] If USDC: - --currency USDC - --amount in atomic units (6 decimals, e.g., 100000 = 0.10 USDC) If Credits (1 credit = 1 USDC): - --currency FLUXA_MONETIZE_CREDITS - --amount in 2-decimal units (e.g., 10 = 0.10 credits, 100 = 1.00 credits) ** Step 5 - Create an intent mandate ** x402 v3 uses intent mandates: the user pre-approves a spending plan (budget + time window), then the agent makes autonomous payments within those limits. fluxa-wallet mandate-create \ --desc "Spend up to <BUDGET> for <DESCRIPTION> valid for <DURATION>" \ --amount <BUDGET_IN_UNITS> \ --seconds <DURATION_IN_SECONDS> \ --currency <USDC or FLUXA_MONETIZE_CREDITS> Options: - --desc (required): Human-readable spending plan description - --amount (required): Budget in units for the chosen currency (see Step 4) - --seconds (optional, default 28800 = 8h): Duration in seconds - --currency (optional, default USDC): USDC or FLUXA_MONETIZE_CREDITS ** Step 6 - Get user to sign the mandate ** The response from Step 5 includes mandateId and authorizationUrl (TTL: 10 minutes). Present the user with options: [Yes, open the link] [No, don't open]. If YES: run 'open "<authorizationUrl>"' to open in their browser. ** Step 7 - Wait for mandate to be signed ** fluxa-wallet mandate-status --id <MANDATE_ID> Poll until mandate.status is "signed". The response also includes remainingAmount. Important: Use --id, not --mandate. ** Step 8 - Call the API ** curl https://router.fluxapay.xyz/api/agent-tools-crowdspark Optionally add the X-Agent-ID header for agent attribution (its value is the agent_id from 'fluxa-wallet status'): curl -H "X-Agent-ID: <YOUR_AGENT_ID>" https://router.fluxapay.xyz/api/agent-tools-crowdspark If it returns HTTP 402, continue to Step 9. ** Step 9 - Pay via x402 v3 ** Pass the complete HTTP 402 response body as --payload: fluxa-wallet x402-v3 \ --mandate <MANDATE_ID> \ --payload '$PAYLOAD_402' The payload must contain an accepts array. Do NOT extract individual fields - pass the entire 402 response JSON. The response includes xPaymentB64 (the payment token). ** Step 10 - Retry with payment token ** Retry the same request with the X-Payment header (optionally add X-Agent-ID for attribution): curl -H "X-Payment: <xPaymentB64>" <ORIGINAL_API_URL> Return the raw API response to the user without post-processing. ** Opening links for user ** Whenever you need to open a URL (authorization, approval, or any external link): 1. Present the user with a choice using your interactive options/menu capability (e.g., AskUserQuestion tool) 2. Options: [Yes, open the link] [No, don't open] 3. If YES: run 'open "<URL>"' to open in their default browser 4. If NO: ask how they would like to proceed ** Error handling ** - mandate_not_signed: User hasn't signed yet - ask them to open authorizationUrl - mandate_expired: Time window passed - create a new mandate - mandate_budget_exceeded: Budget too low - create a new mandate with a higher limit - agent_not_registered: No Agent ID - run 'fluxa-wallet init' first - Invalid payload: missing accepts array: Pass the full 402 response JSON