Spec Driven Development
MCP Server that facilitates spec-driven development workflows, not just Vibe Coding.
Description from the maker (original English)
Explain Algorand transactions, groups, batches, and account activity with x402.
These three are never merged into one score: opinions, measurements and popularity are different things.
We have not written a plain-language summary for this one yet. Below are the facts we read from the registry.
Pick the AI app you use, then copy the settings.
You need
Which app do you use?
Pick your app above. We remember it, so next time the button says “Install in …”.
Open Claude Desktop → Settings → Developer → Edit Config, and paste this into claude_desktop_config.json
{
"mcpServers": {
"tx402": {
"command": "npx",
"args": [
"-y",
"tx402-mcp"
]
}
}
}Run this in your terminal
claude mcp add tx402 -- npx -y tx402-mcpPaste into .cursor/mcp.json in your project, or ~/.cursor/mcp.json
{
"mcpServers": {
"tx402": {
"command": "npx",
"args": [
"-y",
"tx402-mcp"
]
}
}
}Your browser asks to open the app, then the app shows the settings and asks you to confirm. Key values are left empty for you to fill in.
Paste into .vscode/mcp.json in your project
{
"servers": {
"tx402": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"tx402-mcp"
]
}
}
}Your browser asks to open the app, then the app shows the settings and asks you to confirm. Key values are left empty for you to fill in.
This one runs on your computer, and ChatGPT can only connect to servers on the internet. Pick another app.
Your choice stays on this device in a cookie; no account needed.
These settings are generated from the maker’s registry entry. If the README says otherwise, follow the README.
Runs on your computer; the tool list appears in your AI app after you install it.
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 8, 2026
The registry name was verified with the GitHub account Mahesvannan, which owns the repo
We have not read this repo from GitHub yet
We have not read this repo from GitHub yet
This one runs on your computer; there is no internet endpoint
Runs on your computer and uses local settings instead
Runs on your computer; we can only read tool lists from internet endpoints
Compared with every active server in this category in the registry. Stars count only when the publisher owns the repo.
It passed 1 of 1 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.
The registry does not list a required key, though some servers ask you to sign in on first use.
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).
The GitHub repo last changed –, and the latest version (0.2.0) reached the registry 3 months ago.
Apps that support MCP, such as Claude Desktop, Claude Code, Cursor and VS Code. You also need Node.js on your computer.
In the same category: Spec Driven Development, Remote Desktop Commander, NexusWindows
Servers in the same category from other makers, sorted by stars.
Reading a card:★ GitHub starsiThree pillars: reviews · checks · usageiUpdated = latest version published to the registryi
MCP Server that facilitates spec-driven development workflows, not just Vibe Coding.
Remote Desktop Commander: use files, terminal and processes on your own computers from any AI app.
Windows computer use in the background: desktop apps driven without your mouse or keyboard.
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.
Plain-English explanations of Algorand transactions, sold as a pay-per-call API with x402 on Algorand.
Live service:
https://tx402-production.up.railway.app
Explain one transaction, every leg of an atomic group, a batch of IDs, or recent account activity. Responses include scaled amounts, inner transactions, asset names, fees, timestamps, counterparties, and source-verified protocol labels.
Try the free fixed-transaction demo without a wallet:
https://tx402-production.up.railway.app/demo?example=algo
GET /explain?txid=YRSG7IKDPCK4XMKFFTFFFYMIHF6SJOMHUOIE4FFUWNLEQ4WG2ZOQ
Example response after payment:
{
"txid": "YRSG7IKDPCK4XMKFFTFFFYMIHF6SJOMHUOIE4FFUWNLEQ4WG2ZOQ", "network": "mainnet", "summary": "On June 16, 2019, wallet VCINCV...JPMIPM sent 1 ALGO to CRBMB5...QLXZOY. Paid 0.001 ALGO in fees.", "details": { "type": "pay", "sender": "VCINCVUX2DBKQ6WP63NOGPEAQAYGHGSGQX7TSH4M5LI5NBPVAGIHJPMIPM", "transfer": { "amount": "1", "assetId": 0, "unit": "ALGO" } } }
Raw Algorand indexer JSON is optimized for machines doing bookkeeping: amounts are base units, assets are numeric IDs, and notes are base64. tx402 is the translation layer for agents and applications that need to explain a transaction to a person.
Public routes:
GET / - landing page with service metadata linksGET /health - process livenessGET /health?deep=1&network=mainnet - readiness check for upstream servicesGET /discovery - machine-readable service description and pricing metadataGET /openapi.json - OpenAPI 3.1 specificationGET /.well-known/agent.json - agent marketplace manifestGET /.well-known/x402 - x402 resource manifestGET /llms.txt - agent-readable documentationGET /demo?example=algo|usdc - free allowlisted Mainnet examplesGET /explain?txid=...&network=mainnet - paid transaction explanationGET /group?txid=...&network=mainnet - paid atomic-group explanationPOST /batch - paid batch of 1 to 10 transaction IDsGET /account/activity?address=...&limit=25 - paid activity summaryGET /analytics - free aggregate adoption countersDefault prices are $0.005 for /explain, $0.01 for /group, $0.02 for /batch, and $0.01 for /account/activity. Production accepts Mainnet USDC:
algorand:wGHE2Pwdvd7S12BL5FaOP20EGYesN73ktiC1qzkkit8=315667046RK3U3OF2B4Q773L4KC7OVFHQGU5I74NHRZ36QN6CVF527CKXAL62YR754tx402 has a small deterministic core and a thin serving shell.
Core:
Serving shell:
The server never stores private keys. Buyer signing happens client-side. The resource server only advertises a price, validates payment, and settles through the facilitator after a successful product-route response.
npm install
npm start npm test
Local endpoints:
curl "http://localhost:4021/health"
curl "http://localhost:4021/discovery" curl "http://localhost:4021/explain?txid=SOME_REAL_MAINNET_TXID" curl "http://localhost:4021/group?txid=SOME_REAL_MAINNET_TXID"
The app reads .env when present. Leave USDC_ASSET_ID unset unless you need a non-standard asset; the code derives the canonical USDC asset from NETWORK.
Read-only example client:
npm run example:client
npm run example:catalog
The default client prints discovery metadata and the x402 payment challenge without spending funds. To make it pay, configure a funded buyer wallet and set TX402_EXAMPLE_PAY=1 plus CONFIRM_MAINNET_PAYMENT=1.
OpenAPI:
https://tx402-production.up.railway.app/openapi.jsonAgent marketplace metadata:
https://tx402-production.up.railway.app/.well-known/agent.jsonhttps://tx402-production.up.railway.app/.well-known/x402https://tx402-production.up.railway.app/llms.txtCopy-paste integrations and distribution assets:
The paid route also declares the standard x402 Bazaar extension, including its input/output schemas, service metadata, and example request. Facilitators can index that metadata after a successful settlement.
MCP wrapper:
npm run mcp
After the public npm package is published, agents can install it without cloning this repository:
npx tx402-mcp
By default the MCP wrapper is read-only and returns x402 payment requirements for paid calls. To let it pay from a local wallet, set TX402_MCP_ENABLE_PAYMENTS=1 and CONFIRM_MAINNET_PAYMENT=1.
The six-part adoption roadmap is tracked in PLAN.md.
txid input is rejected before indexer access and before payment./analytics, /discovery, and deep health checks are rate-limited.verified: true.First Mainnet settlement:
XA7HMRPUV4X2GWI4AAGUT5FKAVTNCQJ5ZMUNTVTBKG3GZMES27LA0.005000 USDCImplementation runbooks, deployment commands, phase evidence, and operational cautions live in CLAUDE.md.