Prototype · Preview: every server in the official registry, synced every 30 minutes. Sign in with Google to write reviews.
PopNx MCPMCP servers for people who use AI · explained in plain words

TensorFeed x402 Base Reader

by RipperMercsversion 0.2.1i★ 2iRuns on your computer
Registry nameai.tensorfeed/x402-base-mcp

How to install

Overview

Description from the maker (original English)

Read-only Base mainnet reader. Verifies x402 payment settlements + AFTA federation status.

What you can do with it

We have not written a plain-language summary for this one yet. Below are the facts we read from the registry.

  • Connection: Runs on your computer
  • Transport: stdio
  • Category: Online shops & payments
  • You need to fill in: TENSORFEED_RPC_URL

Install

Pick the AI app you use, then copy the settings.

Passed 3/3 checks · Runs on your computer

First: which AI do you use?

Pick your app and the steps appear below.

Works with Claude, with some setup first

You need a TensorFeed x402 Base Reader key (sign up on the maker’s site, may cost money) · Install Node.js on your computer first (one time) · Only the Claude desktop app (Windows or Mac), not the web or phone

  1. Install Node.js

    One time only; it works for every server that needs Node.js

    Open the Node.js download page ↗

  2. Sign up and create a TensorFeed x402 Base Reader key

    Open the maker’s site, sign up and create an API key for the next step. It may cost money.

    Open the TensorFeed x402 Base Reader site ↗

  3. Open the Claude desktop app’s settings file

    SettingsDeveloperEdit Config

  4. Paste these settings and save the file

    {
      "mcpServers": {
        "x402-base": {
          "command": "npx",
          "args": [
            "-y",
            "@tensorfeed/x402-base-mcp"
          ],
          "env": {
            "TENSORFEED_RPC_URL": "your-value"
          }
        }
      }
    }

    Paste the key only into the app’s field, never into a chat or to anyone

  5. Quit Claude and open it again

  6. Try it

    Use TensorFeed x402 Base Reader and tell me what you can do for me, then show me one thing

    ✓ If Claude says it is using TensorFeed x402 Base Reader or shows a TensorFeed x402 Base Reader tool in the answer, you are connected

Menu names checked against Anthropic’s help page on Nov 11, 2026 · your screen may differ slightly by app version

ChatGPT cannot connect TensorFeed x402 Base Reader yet

TensorFeed x402 Base Reader runs on your computer, but ChatGPT can only connect servers that run on the web

What you can do instead

A · Use an app that can connect TensorFeed x402 Base Reader

  • You need a TensorFeed x402 Base Reader key (sign up on the maker’s site, may cost money) · Install Node.js on your computer first (one time) · Only the Claude desktop app (Windows or Mac), not the web or phone
  • You need a TensorFeed x402 Base Reader key (sign up on the maker’s site, may cost money) · Install Node.js on your computer first (one time)
  • You need a TensorFeed x402 Base Reader key (sign up on the maker’s site, may cost money) · Install Node.js on your computer first (one time)
  • You need a TensorFeed x402 Base Reader key (sign up on the maker’s site, may cost money) · Install Node.js on your computer first (one time)

B · Others in Online shops & payments that work with ChatGPT

Picked from the most used in the same category, only ones that connect by address with no key

Works with Claude Code, with some setup first

You need a TensorFeed x402 Base Reader key (sign up on the maker’s site, may cost money) · Install Node.js on your computer first (one time)

  1. Install Node.js

    One time only; it works for every server that needs Node.js

    Open the Node.js download page ↗

  2. Sign up and create a TensorFeed x402 Base Reader key

    Open the maker’s site, sign up and create an API key for the next step. It may cost money.

    Open the TensorFeed x402 Base Reader site ↗

  3. Open Terminal

    Mac: press Command+Space and type Terminal · Windows: open PowerShell

  4. Paste this command and press Enter

    claude mcp add x402-base --env TENSORFEED_RPC_URL=your-value -- npx -y @tensorfeed/x402-base-mcp

    Replace “your-value” with your key before pressing Enter

    Paste the key only into the app’s field, never into a chat or to anyone

  5. Type /mcp in Claude Code

    You should see TensorFeed x402 Base Reader listed as connected

  6. Try it

    Use TensorFeed x402 Base Reader and tell me what you can do for me, then show me one thing

    ✓ If Claude Code says it is using TensorFeed x402 Base Reader or shows a TensorFeed x402 Base Reader tool in the answer, you are connected

Menu names checked against Anthropic’s help page on Nov 11, 2026 · your screen may differ slightly by app version

Works with Cursor, with some setup first

You need a TensorFeed x402 Base Reader key (sign up on the maker’s site, may cost money) · Install Node.js on your computer first (one time)

  1. Install Node.js

    One time only; it works for every server that needs Node.js

    Open the Node.js download page ↗

  2. Sign up and create a TensorFeed x402 Base Reader key

    Open the maker’s site, sign up and create an API key for the next step. It may cost money.

    Open the TensorFeed x402 Base Reader site ↗

  3. Click this button to open Cursor

    Open in Cursor

    Cursor asks you to confirm; click Install

  4. Fill in your key

    In the TensorFeed x402 Base Reader settings, TENSORFEED_RPC_URL is empty; add your key and save

    Paste the key only into the app’s field, never into a chat or to anyone

  5. Open the AI chat in Cursor in Agent mode

  6. Try it

    Use TensorFeed x402 Base Reader and tell me what you can do for me, then show me one thing

    ✓ If Cursor says it is using TensorFeed x402 Base Reader or shows a TensorFeed x402 Base Reader tool in the answer, you are connected

Menu names checked against Cursor’s help page on Nov 11, 2026 · your screen may differ slightly by app version

Works with VS Code, with some setup first

You need a TensorFeed x402 Base Reader key (sign up on the maker’s site, may cost money) · Install Node.js on your computer first (one time)

  1. Install Node.js

    One time only; it works for every server that needs Node.js

    Open the Node.js download page ↗

  2. Sign up and create a TensorFeed x402 Base Reader key

    Open the maker’s site, sign up and create an API key for the next step. It may cost money.

    Open the TensorFeed x402 Base Reader site ↗

  3. Click this button to open VS Code

    Open in VS Code

    VS Code asks you to confirm; click Install

  4. Fill in your key

    In the TensorFeed x402 Base Reader settings, TENSORFEED_RPC_URL is empty; add your key and save

    Paste the key only into the app’s field, never into a chat or to anyone

  5. Open the AI chat in VS Code in Agent mode

  6. Try it

    Use TensorFeed x402 Base Reader and tell me what you can do for me, then show me one thing

    ✓ If VS Code says it is using TensorFeed x402 Base Reader or shows a TensorFeed x402 Base Reader tool in the answer, you are connected

Menu names checked against VS Code’s help page on Nov 11, 2026 · your screen may differ slightly by app version

Other apps that use MCP, such as Windsurf, Zed or Gemini CLI, each add servers differently. See how in the app list.

See every app that uses MCP →

JSON settings are under “For developers” below

Stuck? Ask people who use TensorFeed x402 Base Reader💬 Discussion →
For developers: Terminal commands and JSON settings

Installed on your computer

Claude Code

claude mcp add x402-base --env TENSORFEED_RPC_URL=your-value -- npx -y @tensorfeed/x402-base-mcp

Claude Desktop (claude_desktop_config.json)

{
  "mcpServers": {
    "x402-base": {
      "command": "npx",
      "args": [
        "-y",
        "@tensorfeed/x402-base-mcp"
      ],
      "env": {
        "TENSORFEED_RPC_URL": "your-value"
      }
    }
  }
}

Cursor (~/.cursor/mcp.json)

{
  "mcpServers": {
    "x402-base": {
      "command": "npx",
      "args": [
        "-y",
        "@tensorfeed/x402-base-mcp"
      ],
      "env": {
        "TENSORFEED_RPC_URL": "your-value"
      }
    }
  }
}

VS Code (mcp.json)

{
  "servers": {
    "x402-base": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "@tensorfeed/x402-base-mcp"
      ],
      "env": {
        "TENSORFEED_RPC_URL": "your-value"
      }
    }
  }
}

Values you fill in

  • TENSORFEED_RPC_URL secret env
    Optional Base mainnet RPC endpoint (Alchemy, Infura, etc) for higher rate limits. Must match the allowlist in src/rpc/allowlist.ts; non-allowlisted URLs fall back to public Base RPC with a stderr war…

These settings are generated from the maker’s registry entry. If the README says otherwise, follow the README.

At a glance

Downloads per weeki
120/wk
Verified domain
✓ tensorfeed.ai
Connection
Runs on your computer
Latest versioni
0.2.1
Published to registryi
May 28, 2026
Code last changedi
Oct 14, 2026
Maker
RipperMercs
Packages
npm: @tensorfeed/x402-base-mcp
Registry status
Active

Which apps can use it

Based on how this server connects and on each app’s own docs, checked Nov 10, 2026.

Run on your computer in

ClaudeGooseLM StudioMsty StudioCherry StudioCursorVS Code + GitHub CopilotVisual StudioWindsurf (Devin Desktop)ZedKiroClineContinueJetBrains AI AssistantClaude CodeCodex CLIGemini CLIOpenCodenodecodeWarpLibreChatRaycast

All apps, with pros and cons →

Related guides

What it can do

Runs on your computer; the tool list appears in your AI app after you install it.

Basic checksi

We check information anyone can see; we have not read the code. Checks that do not apply are left out of the count. · Checked Nov 11, 2026

  • ✓ Pass

    Maker matches the repo

    The registry name was verified against the domain tensorfeed.ai (the registry checks domain ownership)

  • ✓ Pass

    Still maintained

    Code last changed 28 days ago

  • ✓ Pass

    Has a licence

    Uses MIT

  • – Not applicable

    Endpoint responds

    This one runs on your computer; there is no internet endpoint

  • – Not applicable

    Sign-in with OAuth

    Runs on your computer and uses local settings instead

  • … Not checked yet

    No hidden instructions in tool descriptions

    Runs on your computer; we can only read tool lists from internet endpoints

Discussion

Ask, share a tip or report that it does not work. Sorted by what people marked helpful.

No posts yet. Be the first to ask or share.

Posts here are written by users, not the PopNx team.

Sign in with Google to post

User reviews

No reviews yet

Sign in with Google to write a review

Compared with others in Online shops & paymentsi

  • More stars than 94% of the other 2702 servers in this category
  • Published to the registry more recently than 9% of the other 2702 servers in this category
  • Basic checks equal to or better than 100% of the other 2702 servers in this category

Compared with every active server in this category in the registry. Stars count only when the publisher owns the repo.

Common questions

Is TensorFeed x402 Base Reader safe?

It passed 3 of 3 applicable basic checks. We have not read the code. Before adding a key or token, see what access the server asks for and use a key with only the permissions you need.

What keys or codes does it need?

You need to fill in: TENSORFEED_RPC_URL

Does it run on my computer or in the cloud?

It runs on your computer. Your AI app starts it when needed, and data does not pass through the maker’s servers (unless it calls an online service itself).

Is it still maintained?

The GitHub repo last changed 28 days ago, and the latest version (0.2.1) reached the registry 6 months ago.

Which apps can use it?

Apps that support MCP, such as Claude Desktop, Claude Code, Cursor and VS Code. You also need Node.js on your computer.

What can I use instead?

In the same category: Spree Commerce developer docs for AI agents, Stripe MCP, Sessy — Amazon SES observability

Alternatives

Servers in the same category from other makers, sorted by stars.

Reading a card:↓ Downloads per weeki★ GitHub starsiThree pillars: reviews · checks · usageiUpdated = latest version published to the registryi

Spree Commerce developer docs for AI agents

Spree Commerce docs for AI coding agents: build headless B2B and marketplace ecommerce on its APIs.

by spreeWidely used★ 15.8K Stars for the whole repoUpdated 12 days ago

Runs in the cloud

Stripe MCP

Stripe’s official server lets AI view and manage customers, products, payments and invoices. Connect to Stripe’s cloud and sign in with OAuth.

by stripeWidely used★ 2.1KUpdated 13 months ago

Runs in the cloud✓ stripe.com

Sessy — Amazon SES observability

Read-only Amazon SES observability: search events, inspect bounces, pull delivery stats.

by marckohlbruggeGrowing★ 945Updated 3 months ago

Runs in the cloud

README from the maker

Open the README

Copied from the maker’s repo as written. PopNx MCP has not reviewed or endorsed it. HTML, images and scripts are removed. Links lead off this site.

@tensorfeed/x402-base-mcp

Read-only MCP server for verifying x402 USDC settlements on Base mainnet. Drop it into any MCP-compatible agent (Claude Desktop, Claude Code, Cursor, ChatGPT) to independently audit x402 payment receipts on-chain, parse publisher .well-known/x402 manifests, and check AFTA federation status. No private keys, no signing, no broadcasts.

npm install -g @tensorfeed/x402-base-mcp

Relationship to Coinbase Base MCP

Coinbase shipped Base MCP (the official mcp.base.org server, launched May 2026) as the *transact-side* MCP: it connects an agent to a Base Account and lets the agent propose swaps, transfers, and x402 payments that the user approves in-wallet.

This package, @tensorfeed/x402-base-mcp, is the *verify-side* MCP. Once an x402 payment has been made (by Base MCP, by a server-side @coinbase/x402 middleware, or by any other x402 client), this server lets the calling agent independently check the on-chain settlement, parse the publisher's /.well-known/x402 manifest, and audit the receipt. Read-only chain visibility, no wallet.

The two are complementary, not competing. Use Base MCP to pay. Use this MCP to verify.

Why a separate verify MCP

x402 is a payment protocol where agents pay merchants in USDC on Base for paid API responses. When an agent receives a payment receipt back, it has two options for confirming that the settlement actually happened the way the receipt claims:

  1. Trust the merchant
  2. Read the on-chain Transfer event itself

Most existing EVM MCP servers either require a private key (so the agent can also send transactions, which is operationally risky and unnecessary for verification), or are generic multi-chain readers that don't speak x402. This server is the read-only, x402-aware option. Drop it into a Claude Desktop or Claude Code session and any agent can verify x402 payments without operating a wallet.

The TensorFeed-flavor tools (verify_afta_federation, tf_payment_lookup) compose the same primitives against TF's canonical surfaces and demonstrate the pattern. Use them or ignore them; the generic tools work fine on their own.

Installation

Claude Desktop

Add to claude_desktop_config.json:

{

"mcpServers": { "tensorfeed-x402-base": { "command": "npx", "args": ["-y", "@tensorfeed/x402-base-mcp"] } } }

Claude Code
claude mcp add tensorfeed-x402-base -- npx -y @tensorfeed/x402-base-mcp
Optional: bring your own RPC

The server defaults to the public Base RPC (https://mainnet.base.org), which is fine for casual use. For heavier workloads, set an Alchemy or Infura URL via TENSORFEED_RPC_URL. The URL must match the allowlist in src/rpc/allowlist.ts; anything else falls back to the public endpoint and logs a warning to stderr.

export TENSORFEED_RPC_URL="https://base-mainnet.g.alchemy.com/v2/YOUR_KEY"

Affiliate links if you don't already have an account:

  • Alchemy: https://www.alchemy.com/
  • Infura: https://www.infura.io/

Tools

Generic Base reads
ToolDescription
balanceNative ETH balance for an address
usdc_balanceUSDC (Circle native bridged) balance for an address
block_numberLatest Base block number
get_tx_receiptFull tx receipt with status, gas, and logs summary
callRead-only contract call (eth_call, never broadcasts)
recent_transfersUSDC Transfer events involving an address over N blocks
x402-native verification
ToolDescription
verify_x402_settlementGiven a tx hash, expected recipient, and expected USDC amount, returns a structured verdict on whether the on-chain Transfer event matches.
parse_x402_manifestFetches https://{domain}/.well-known/x402.json, returns the structured manifest.
usdc_recent_payments_toUSDC transfers TO an address over N blocks; the merchant-side view.
probe_x402_endpointProbes any https URL and reports whether it returns a canonical x402-paid 402 response with accepts[].
decode_x402_payment_payloadOffline decode of a base64 X-PAYMENT header (Coinbase x402 V2): returns scheme, network, version, EIP-3009 authorization, signature.
TensorFeed flavor
ToolDescription
verify_afta_federationCalls TensorFeed's AFTA certification endpoint for a domain, returns a scored checklist.
tf_payment_lookupChecks whether a tx hash is a USDC payment to TensorFeed's canonical wallet on Base.
x402_publisher_healthReturns current outcome + 24h/7d uptime + recent series for a domain monitored by TensorFeed's hourly x402 status probe.
afta_federation_membersReturns the canonical curated list of confirmed AFTA federation members (TF origin + federated members).

Examples

Verify an x402 settlement (works on TensorFeed's first canonical V2 payment):

verify_x402_settlement({

tx_hash: "0xe20c57d8aa6df63f75ce7a4e4c0cab492eb7fa672a23cd8fd59967eb6b66bd67", expected_recipient: "0x549c82e6bFC54bdaE9A2073744CBC2AF5D1FC6D1", expected_amount_usdc: "0.02" }) // returns { ok: true, verified: true, matches: [...] }

Inspect a publisher's x402 manifest:

parse_x402_manifest({ domain: "tensorfeed.ai" })

Check AFTA certification:

verify_afta_federation({ domain: "tensorfeed.ai" })

Threat model

Read-only chain-visibility MCP. The full picture is in SECURITY.md; the short version:

  • No private keys, no signing, no broadcasts. The server cannot move funds.
  • Input validators on every tool reject malformed inputs (bad checksums, malformed hashes, URL-shaped domains, private/loopback hostnames).
  • Output sanitization strips C0/C1 control characters and zero-width / direction-override marks from every string returned to the calling agent.
  • External strings carry an _origin: "external" marker so the calling agent knows the value came from a third party.
  • 50 KB response cap on serialized tool output; oversized responses collapse to a structured stub.
  • RPC allowlist limits self-hosters to known endpoints; arbitrary URLs are rejected and fall back to public Base RPC.
  • No telemetry, no phone-home, no analytics.
  • Provenance: npm releases are published via GitHub Actions OIDC with cryptographic provenance attestations. Verify with npm audit signatures.

Report security issues to security@tensorfeed.ai. Please do not file a public issue or CVE for an unfixed vulnerability.

License

MIT

Related

  • Coinbase Base MCP - the official transact-side MCP for Base. Pair with this package for a full pay + verify loop: Base MCP signs the x402 payment, this package independently confirms the settlement on-chain.
  • @tensorfeed/mcp-server - companion package, the TensorFeed data MCP (news, status, models, benchmarks, premium endpoints). Complementary role: this server verifies x402 payments on-chain; mcp-server wraps the TF data API as MCP tools.
  • TensorFeed - AI ecosystem data layer
  • TensorFeed developers - free + premium API for AI agents
  • Agent Fair-Trade Agreement (AFTA) - open standard for honest agent commerce
  • x402 spec - the payment protocol this MCP verifies