PulseFeed — verify before you pay or install
Verify before you pay or install. Checks whether an x402 payment endpoint is safe to pay (liveness, scam scan, on-chain receiver, trust score) and whether an npm/MCP package is saf…
Nikolife2016
@nikolife2016
Install
$ openclaw skills install @nikolife2016/pulsefeed-x402-trustPulseFeed — verify before you pay or install
Two irreversible actions an agent takes: paying an unknown endpoint, and installing unknown code. PulseFeed checks both, from a continuous independent audit (~5,600 x402 endpoints and ~950 MCP servers re-probed daily). All endpoints below are free and need no API key.
1. Before paying an x402 endpoint
curl -s "https://pulsefeed.dev/verify?endpoint=<URL>"
Returns verdict (safe / caution / avoid / unknown), score (0–100), flags, receiverStability, uptimePct, lastChecked.
Rule of thumb:
avoid→ do not pay. Dead, invalid, or flagged (hijacked receiver, bait-and-switch price, honeypot).caution→ readflagsfirst; pay only if the finding is acceptable.safe→ live and clean at last crawl.unknown→ not in the index; use the live deep check below.
Live deep check (probes the endpoint right now, adds on-chain receiver profile and full scam scan) — paid, $0.02 via x402:
curl -s "https://pulsefeed.dev/trust?endpoint=<URL>" # returns a 402 challenge; pay with any x402 client
Important x402 client gotcha: x402-fetch defaults to a 0.1 USDC client-side cap. Anything pricier is refused locally before the request is sent. Raise it explicitly:
const payingFetch = wrapFetchWithPayment(fetch, account, BigInt(1_000_000)); // 1 USDC
2. Before installing an MCP server or npm package
curl -s "https://pulsefeed.dev/mcp/verify?package=<npm-name>"
Returns verdict, score, and flags such as installScript (the package runs arbitrary code at npm i), abandoned, noRepo, noLicense, plus weeklyDownloads, license, repo, provenance.
Rule of thumb: treat installScript: true on a package with no repository to review as a red flag — that is unreviewable code execution on your machine. About 11% of audited MCP servers run an install script.
3. Current security incidents
curl -s "https://pulsefeed.dev/incidents.json"
Live incidents in the x402 economy — receiver hijacks (payTo swapped after you trusted it), bait-and-switch pricing, honeypot receivers, unverified receivers — each with an on-chain proof URL you can verify yourself on Base.
4. Ecosystem context
curl -s "https://pulsefeed.dev/status.json" # live/dead counts, catalog accuracy, risk map
curl -s "https://pulsefeed.dev/data/sample" # free sample of the full cross-domain dataset
Why this matters: ~74% of listed x402 endpoints are dead or invalid, and only about half of what catalogs call "healthy" actually returns a valid x402 challenge. Checking costs nothing; paying a dead or hijacked endpoint costs real USDC and is irreversible.
Also available
- MCP server (same checks as tools):
npx -y pulsefeed-x402-mcp - Guard SDK (blocks bad payments automatically):
npm i pulsefeed-x402-guard - A2A agent:
https://pulsefeed.dev/.well-known/agent-card.json - Methodology (how scores are computed): https://pulsefeed.dev/methodology
Independent, not affiliated with any x402 facilitator or MCP vendor.
Top skills in this category
Skill Vetter
@spclaudehomeSecurity-first skill vetting for AI agents. Use before installing any skill from ClawdHub, GitHub, or other sources. Checks for red flags, permission scope, and suspicious patterns.
Skill Vetter - Pre-Install Security Review
@donovanpankratz-delSecurity vetting protocol before installing any AI agent skill. Red flag detection for credential theft, obfuscated code, exfiltration. Risk classification L...
google-slides
@byungkyuGoogle Slides API integration with managed OAuth. Create presentations, add slides, insert content, and manage slide formatting. Use this skill when users want to interact with Google Slides. For other third party apps, use the api-gateway skill (https://clawhub.ai/byungkyu/api-gateway). Calls run through the `maton` CLI with OAuth login; default to read and list calls, and confirm every write or new connection with the user.
google-workspace-admin
@byungkyuGoogle Workspace Admin SDK integration with managed OAuth. This is a write-capable administrative integration for users, groups, organizational units, roles, and domain settings. Only connect with a least-privileged Google admin account, restrict OAuth scopes to the specific resources needed, and revoke the connection after use. All write operations require explicit user approval showing the exact HTTP method, endpoint path, and target resource identifier before execution. Use this skill only when users need Google Workspace administration. For other third party apps, use the api-gateway skill (https://clawhub.ai/byungkyu/api-gateway). Calls run through the `maton` CLI with OAuth login; default to read and list calls, and confirm every write or new connection with the user.
OpenClaw Token Optimizer
@asif2bdOpenClaw Token Optimizer v3.2.0 — practical cost-control toolkit for OpenClaw agents. Lazy context loading, Sonnet/Opus-aware routing, heartbeat scheduling,...