Spec Driven Development
MCP Server that facilitates spec-driven development workflows, not just Vibe Coding.
Description from the maker (original English)
Pay per call, solves one question. Raw public readings on AI agents and 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 …”.
Works in Claude on the web, desktop and mobile:
https://mcp.agentweather.io/mcpRun this in your terminal
claude mcp add --transport http agent-weather https://mcp.agentweather.io/mcpPaste into .cursor/mcp.json in your project, or ~/.cursor/mcp.json
{
"mcpServers": {
"agent-weather": {
"url": "https://mcp.agentweather.io/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": {
"agent-weather": {
"type": "http",
"url": "https://mcp.agentweather.io/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.
ChatGPT connects only to servers on the internet:
https://mcp.agentweather.io/mcpMenu names can differ slightly by plan and over time.
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.
Tool names and descriptions exactly as the server reported them on Nov 6, 2026. The maker wrote them, not us; we show them as plain text.
get_service_statusFree. Returns whether the Agent Weather API and its XRPL payment facilitator are reachable, the API version, and the list of paid routes with their prices and accepted assets (from /.well-known/x402). Returns no report data. No inputs.
list_modelsFree. Day-old index of the Agent Weather AI model directory: model id, name, vendor and categories only (models first seen at least 24 h ago; flagged in `snapshot`). Live prices, context length, vendor status, 24h/7d changes, job cost and events are in the paid get_model_report a
paycheck_demoFree. A full Pay Radar example for Agent Weather's own /v1/pulse/facilitator: raw checks first (reachable, latency, tls, x402 shape, asset, payTo fields), then reasons and a summary of signals. Cached up to 10 minutes. No inputs.
payradar_demoFree. A full Pay Radar example for Agent Weather's own /v1/pulse/facilitator: raw checks first (reachable, latency, tls, x402 shape, asset, payTo fields), then reasons and a summary of signals. Cached up to 10 minutes. No inputs.
get_sample_yesterdayFree. Returns a day-old sample of the conditions report (previous calendar day, America/Chicago) so you can inspect the report format before paying. Not live data. No inputs.
get_models_sample_yesterdayFree. Returns the day-old change summary of the AI model directory (previous calendar day, America/Chicago): listing, price and status changes as declared by public sources. Not live data. No inputs.
decide_provider_healthPaid: 0.005 RLUSD per call via x402 on XRPL mainnet (xrpl:0), or 0.005 USDC on Base (eip155:8453). Pay per call, solves one question: What does this AI provider's status page and our last 24h record show? Raw indicator, incidents, and disturbed-check share with sources and timest
get_current_conditionsPaid: 0.007 RLUSD per call via x402 on XRPL mainnet (xrpl:0), or 0.007 USDC on Base (eip155:8453). Pay per call, solves one question: What do latest public readings show for AI-agent and x402 conditions? Raw status-page, XRPL x402, GitHub/npm/MCP readings with sources and timesta
get_merchant_readingsPaid: 0.02 RLUSD per call via x402 on XRPL mainnet (xrpl:0), or 0.02 USDC on Base (eip155:8453). Pay per call, solves one question: What x402 payment readings does this XRPL payee show? Raw 24h payments, payers, account fields, and endpoint 402 readings with sources and timestamp
get_merchant_profileDeprecated: use get_merchant_readings. Paid: 0.02 RLUSD per call via x402 on XRPL mainnet (xrpl:0), or 0.02 USDC on Base (eip155:8453). Pay per call, solves one question: What x402 payment readings does this XRPL payee show? Raw 24h payments, payers, account fields, and endpoint
get_access_policy_readingPaid: 0.003 RLUSD per call via x402 on XRPL mainnet (xrpl:0), or 0.003 USDC on Base (eip155:8453). Pay per call, solves one question: What public crawler/agent-access files does this domain serve? Raw robots.txt groups, Content-Signal, llms.txt, well-known JSON, security.txt, TDM
get_access_policy_changesPaid: 0.01 RLUSD per call via x402 on XRPL mainnet (xrpl:0), or 0.01 USDC on Base (eip155:8453). Pay per call, solves one question: Which tracked domains changed their public agent-access files since a time? Raw domain, path, times, hashes, HTTP status, and robots.txt group delta
get_fim2026_schemaPaid: 0.01 RLUSD per call via x402 on XRPL mainnet (xrpl:0), or 0.01 USDC on Base (eip155:8453). Pay per call, solves one question: What does the FIM 2026 guidance schema list as two-way duties and self-checks? Raw duty definitions, self-checks, and measurable indicators (not leg
get_fim2026_ledger_templatePaid: 0.005 RLUSD per call via x402 on XRPL mainnet (xrpl:0), or 0.005 USDC on Base (eip155:8453). Pay per call, solves one question: What blank two-way ledger template does FIM 2026 provide for an engagement? Raw parties, per-duty owed items with open/met/unmet status fields, an
get_pulse_stormPaid: 0.001 RLUSD per call via x402 on XRPL mainnet (xrpl:0), or 0.001 USDC on Base (eip155:8453). Pay per call, solves one question: What is the worst current level across status pages, facilitator reachability, and recent changes? Raw storm/level/reason plus observed_* samples
get_pulse_facilitatorPaid: 0.001 RLUSD per call via x402 on XRPL mainnet (xrpl:0), or 0.001 USDC on Base (eip155:8453). Pay per call, solves one question: Is the XRPL x402 facilitator reachable and are known endpoints answering 402? Raw reachability, on-ledger success samples, and valid-402 probe rat
get_pulse_providersPaid: 0.001 RLUSD per call via x402 on XRPL mainnet (xrpl:0), or 0.001 USDC on Base (eip155:8453). Pay per call, solves one question: What do public AI-provider status pages show right now? Raw per-provider indicators, reason, asOf, and observed_uptime_7d samples with attribution
get_model_reportPaid: 0.01 RLUSD per call via x402 on XRPL mainnet (xrpl:0), or 0.01 USDC on Base (eip155:8453). Pay per call, solves one question: What price, limit, and vendor-status readings does models.dev list for this model? Raw prices, limits, modalities, events, and status with sources a
get_model_categoryPaid: 0.01 RLUSD per call via x402 on XRPL mainnet (xrpl:0), or 0.01 USDC on Base (eip155:8453). Pay per call, solves one question: What price and listing readings sit in this models.dev category? Raw counts, 24h price changes, new/removed listings, and vendor disturbances with s
decide_cheapest_modelPaid: 0.003 RLUSD per call via x402 on XRPL mainnet (xrpl:0), or 0.003 USDC on Base (eip155:8453). Pay per call, solves one question: Which listed models.dev prices meet these filters, lowest first? Raw lowest and next-vendor prices with reasons, exclusions, and status-page readi
get_model_identityPaid: 0.003 RLUSD per call via x402 on XRPL mainnet (xrpl:0), or 0.003 USDC on Base (eip155:8453). Pay per call, solves one question: What identity and change readings does models.dev record for this model? Raw canonical id, cutoff, limits, and change events with timestamps. With
get_x402_health_reportPaid: 0.01 RLUSD per call via x402 on XRPL mainnet (xrpl:0), or 0.01 USDC on Base (eip155:8453). Pay per call, solves one question: Which known XRPL x402 endpoints answer a valid 402? Raw per-endpoint liveness, price/asset/payTo deltas, and facilitator readings with sources. With
get_price_indexPaid: 0.005 RLUSD per call via x402 on XRPL mainnet (xrpl:0), or 0.005 USDC on Base (eip155:8453). Pay per call, solves one question: What prices are live XRPL x402 resources advertising right now? Raw per-endpoint prices, rails, category lows, and change deltas with sources and
get_x402_activityPaid: 0.01 RLUSD per call via x402 on XRPL mainnet (xrpl:0), or 0.01 USDC on Base (eip155:8453). Pay per call, solves one question: What x402 payment volume and merchant activity did our XRPL scan record? Raw payments/volume series, unique payers/merchants, and sample txs with so
paycheckPaid: 0.003 RLUSD per call via x402 on XRPL mainnet (xrpl:0), or 0.003 USDC on Base (eip155:8453). Pay per call, solves one question: Is this x402 endpoint answering right now, and what does its unpaid 402 show? Raw 402 shape, network, asset, payTo ledger fields, TLS, latency, an
payradarPaid: 0.003 RLUSD per call via x402 on XRPL mainnet (xrpl:0), or 0.003 USDC on Base (eip155:8453). Pay per call, solves one question: Is this x402 endpoint answering right now, and what does its unpaid 402 show? Raw 402 shape, network, asset, payTo ledger fields, TLS, latency, an
get_end_of_supportPaid: 0.003 RLUSD per call via x402 on XRPL mainnet (xrpl:0), or 0.003 USDC on Base (eip155:8453). Pay per call, solves one question: What published end-of-support and end-of-life dates are listed for this release line? Raw dates with source URLs and retrieval timestamps (primary
get_discovery_feedPaid: 0.003 RLUSD per call via x402 on XRPL mainnet (xrpl:0), or 0.003 USDC on Base (eip155:8453). Pay per call, solves one question: How are clients finding and probing Agent Weather discovery files and paid routes? Raw first-party counts, UA families, 402-to-paid tallies, docs-
dns_recordsPaid: 0.001 RLUSD per call via x402 on XRPL mainnet (xrpl:0), or 0.001 USDC on Base (eip155:8453). Pay per call, solves one question: What DNS records does this name return right now? Raw answers for the given FQDN and types (A, AAAA, MX, TXT, NS, CNAME, SOA, CAA), plus resolver
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 7, 2026
The registry lists no source repo, so we cannot match the publisher (agentweather.io) to the code
We have not read this repo from GitHub yet
We have not read this repo from GitHub yet
Responded in 733 ms (HTTP 200)
No sign-in needed
Read 29 tool descriptions and found no hidden instructions to the AI
Compared with every active server in this category in the registry. Stars count only when the publisher owns the repo.
It passed 2 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.
The registry does not list a required key, though some servers ask you to sign in on first use.
It runs in the maker’s cloud. Connect over the internet with nothing to install, but what you send passes through the maker’s servers.
The GitHub repo last changed –, and the latest version (0.4.11) reached the registry 5 days ago.
Apps that support MCP, such as Claude Desktop, Claude Code, Cursor and VS Code. It connects by URL, so apps that accept remote MCP servers work too, such as ChatGPT in developer mode.
In the same category: Spec Driven Development, Remote Desktop Commander, Microsoft Exchange Online MCP
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.
Exchange Online admin for MSPs: forwarding audits, EWS posture and offboarding, no PowerShell
No README found in the repo