x402-farm
REMOTE · API.X-402.ONLINE · SCANNED SEP 20
64 x402 tools: cheap LLM $0.002, web+news search, French residential-IP scraping, FR/UK/US data.
Available components
How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. How we score → Why this is hard to score →
Endpoint Security63
- The endpoint's TLS certificate is valid, in date, and uses a strong key. View diagnostics → Pass
- Authorisation not fully verified: no authorisation is required to call this server, and 63 tool(s) never declared a destructiveHint. The MCP spec treats an absent hint as destructive by default, so we cannot call this surface safe. See how to fix → View diagnostics → Unverified
- HTTPS is enforced; there's no plaintext access path. View diagnostics → Pass
- The HSTS (Strict-Transport-Security) header is present. View diagnostics → Pass
- DNSSEC check failed: this domain isn't protected by DNSSEC. See how to fix → View diagnostics → Fail
Transport & Reachability100
- Verified streamable-http transport via a live MCP handshake. View diagnostics → Pass
Schema Quality & AI Usability65
- AI-judged instruction clarity (good).Pass
- Context-footprint check failed: tool/resource definitions use about 7126 tokens (~113/item across 63 items; 63 tools + 0 resources), over budget; trim descriptions and params. See how to fix → Fail
- Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management91
- Stability check failed: schema churn in the 30 days we've observed: 0 tool removals, 10 breaking changes, 0 auth/transport breaks, 3 additions. See how to fix → Fail
Tool Coverage67
- 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
- 0% of tool parameters carry a description.Fail
Tool Safety75
- No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
- 0 of 6 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation; "extract" implies "send" and declares no destructiveHint at all, which the MCP spec reads as destructive by default. See how to fix → Fail
- An AI judge read all 64 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
- Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass
How do I install the x402-farm MCP server?
x402-farm is a hosted endpoint at https://api.x-402.online/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.
remote · api.x-402.online
claude mcp add --transport http online-x-402-mcp 'https://api.x-402.online/mcp'
{
"mcpServers": {
"online-x-402-mcp": {
"url": "https://api.x-402.online/mcp"
}
}
} {
"servers": {
"online-x-402-mcp": {
"type": "http",
"url": "https://api.x-402.online/mcp"
}
}
} [mcp_servers.online-x-402-mcp] url = "https://api.x-402.online/mcp"
{
"$schema": "https://opencode.ai/config.json",
"mcp": {
"online-x-402-mcp": {
"type": "remote",
"url": "https://api.x-402.online/mcp",
"enabled": true
}
}
} openclaw mcp add online-x-402-mcp --url 'https://api.x-402.online/mcp' --transport streamable-http
mcp_servers:
online-x-402-mcp:
url: "https://api.x-402.online/mcp" {
"McpServers": {
"online-x-402-mcp": {
"Transport": "http",
"Url": "https://api.x-402.online/mcp"
}
}
} assistant mcp add online-x-402-mcp -t streamable-http -u 'https://api.x-402.online/mcp'
{
"mcpServers": {
"online-x-402-mcp": {
"type": "http",
"url": "https://api.x-402.online/mcp"
}
}
} The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.
Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.
- 20 Sept 26 −1
- Stability: pass → fail ▼ security
- A breaking change shipped without a version bump: still 1.0.0 ▼ security
- “mobile-proxy_1gb” added a required parameter “exit”, so existing callers break ▼ functional
- “mobile-proxy_5gb” added a required parameter “exit”, so existing callers break ▼ functional
- “proxy_1gb” added a required parameter “exit”, so existing callers break ▼ functional
- “proxy_20gb” added a required parameter “exit”, so existing callers break ▼ functional
- “proxy_5gb” added a required parameter “exit”, so existing callers break ▼ functional
- “proxy_mobile_1gb” added a required parameter “exit”, so existing callers break ▼ functional
- “proxy_mobile_5gb” added a required parameter “exit”, so existing callers break ▼ functional
- “proxy_port_1d” added a required parameter “exit”, so existing callers break ▼ functional
- “proxy_port_30d” added a required parameter “exit”, so existing callers break ▼ functional
- “proxy_port_7d” added a required parameter “exit”, so existing callers break ▼ functional
- New tool “brief” functional
- New tool “solve” functional
- New tool “us_brief” functional
- 19 Sept 26 0
- Tool “fr_concurrents” rewrote its description, which is the text the model reads security
- Tool “fr_enrich” rewrote its description, which is the text the model reads security
- Tool “fr_entreprise-360_partial” rewrote its description, which is the text the model reads security
- Tool “fr_estimation-immo” rewrote its description, which is the text the model reads security
- Tool “fr_immo” rewrote its description, which is the text the model reads security
- Tool “fr_kyb_partial” rewrote its description, which is the text the model reads security
- Tool “fr_leboncoin” rewrote its description, which is the text the model reads security
- Tool “fr_marches-publics” rewrote its description, which is the text the model reads security
- Tool “fr_procedures-collectives” rewrote its description, which is the text the model reads security
- Tool “fr_qualified-leads” rewrote its description, which is the text the model reads security
- Tool “fr_reseau-dirigeant” rewrote its description, which is the text the model reads security
- Tool “fr_score-entreprise” rewrote its description, which is the text the model reads security
- Tool “fr_score-entreprise_partial” rewrote its description, which is the text the model reads security
- Tool “fr_seloger” rewrote its description, which is the text the model reads security
- Tool “fr_valorisation” rewrote its description, which is the text the model reads security
- Tool “fr_verif-artisan” rewrote its description, which is the text the model reads security
- Tool “links” rewrote its description, which is the text the model reads security
- Tool “maps” rewrote its description, which is the text the model reads security
- Tool “meta” rewrote its description, which is the text the model reads security
- Tool “mobile-proxy_1gb” rewrote its description, which is the text the model reads security
- Tool “mobile-proxy_5gb” rewrote its description, which is the text the model reads security
- Tool “proxy_1gb” rewrote its description, which is the text the model reads security
- Tool “proxy_20gb” rewrote its description, which is the text the model reads security
- Tool “proxy_5gb” rewrote its description, which is the text the model reads security
- Tool “proxy_mobile_1gb” rewrote its description, which is the text the model reads security
- Tool “proxy_mobile_5gb” rewrote its description, which is the text the model reads security
- Tool “proxy_port_1d” rewrote its description, which is the text the model reads security
- Tool “proxy_port_30d” rewrote its description, which is the text the model reads security
- Tool “proxy_port_7d” rewrote its description, which is the text the model reads security
- Tool “render” rewrote its description, which is the text the model reads security
- Tool “screenshot” rewrote its description, which is the text the model reads security
- Tool “search_news” rewrote its description, which is the text the model reads security
- Tool “sms_inbox” rewrote its description, which is the text the model reads security
- Tool “sms_number” rewrote its description, which is the text the model reads security
- Tool “transcribe” rewrote its description, which is the text the model reads security
- Tool “uk_company” rewrote its description, which is the text the model reads security
- Tool “uk_company-check” rewrote its description, which is the text the model reads security
- Tool “uk_officers” rewrote its description, which is the text the model reads security
- Tool “uk_psc” rewrote its description, which is the text the model reads security
- Tool “unblock” rewrote its description, which is the text the model reads security
- Tool “us_company” rewrote its description, which is the text the model reads security
- Tool “us_filings” rewrote its description, which is the text the model reads security
- Tool “us_financials” rewrote its description, which is the text the model reads security
- Tool “us_snapshot” rewrote its description, which is the text the model reads security
- 18 Sept 26 0
- Tool “guard” rewrote its description, which is the text the model reads security
- Tool “llm_pro” rewrote its description, which is the text the model reads security
- 30 Aug 26 +6
- Stability: fail → pass ▲ security
- 27 Aug 26 −1
No change was recorded against any check on this day. Stability & Change Management went from 60 to 55.
- 26 Aug 26 +1
- We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
- 24 Aug 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 53 to 56.
- 11 Aug 26 0
- We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.
Captured 20 Sept 2026 · Probed https://api.x-402.online/mcp
TLS valid
Negotiated TLS 1.3 with TLS_AES_128_GCM_SHA256 .
| Subject | Issuer | Valid from | Valid until | Key | Signature | Serial |
|---|---|---|---|---|---|---|
| CN=api.x-402.online | CN=YR2,O=Let's Encrypt,C=US | 21 Jul 2026 | 19 Oct 2026 | RSA 2048 | SHA256-RSA | 5261838868821a35e1ba50da0073a3e3c0f |
| SANs: api.x-402.online | ||||||
| CN=YR2,O=Let's Encrypt,C=US (CA) | CN=Root YR,O=ISRG,C=US | 3 Sept 2025 | 2 Sept 2028 | RSA 2048 | SHA256-RSA | 4ebd24947e24d394802d84a52fd5b319 |
| CN=Root YR,O=ISRG,C=US (CA) | CN=ISRG Root X1,O=Internet Security Research Group,C=US | 13 May 2026 | 2 Sept 2032 | RSA 4096 | SHA256-RSA | f24b6d17f9d9ad7cb1c9fea78782699f |
Background: What to check on a remote MCP endpoint →
DNSSEC insecure
Validation of api.x-402.online. — Not signed
| Zone | DS | Keys | Algorithms | Outcome |
|---|---|---|---|---|
| . | trust_anchor | 20326, 38696 | 8, 8 | Verified |
| online. | present | 30961 | 13 | Verified |
| x-402.online. | absent | Unsigned (proven) parent-signed NSEC/NSEC3 proves an unsigned delegation |
Authentication No authorisation required
The endpoint answered without asking for a token. Anyone who knows the URL can reach it.
| Result | No authorisation required |
|---|---|
| HTTP status | 200 |
| Header | Value |
|---|---|
| strict-transport-security | max-age=63072000 |
Background: How OAuth 2.1 works in the 2026 MCP spec →
Transports 2 probes
| Transport | URL | Outcome | Status | Location |
|---|---|---|---|---|
| streamable-http | https://api.x-402.online/mcp | Verified | 200 | |
| http (plaintext) | http://api.x-402.online/mcp | HTTPS enforced | 308 | https://api.x-402.online/mcp |
The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →
sms_number ~106
Rent a real mobile phone number to receive an SMS or a one-time password. The number is a physical SIM in a handset we operate, not a virtual or VoIP line, so it passes the carrier checks that reject disposable numbers. Returns the number and a session identifier; read arriving messages with /v1/sms/inbox. For agents that must complete a phone verification step autonomously. — $0.050002/call, paid per request via x402 (USDC).
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
solve ~150
One endpoint for any capability. Send a task in plain words, or name a capability and its input, and the gateway resolves which capability is needed, ranks the providers that can serve it by expected net margin and observed success rate, executes, falls back to the next provider on failure, and returns the result with the routing it used. The free companion endpoint POST /v1/solve/preview returns the plan, the normalized input and the price before you pay, and tells you when a direct route would be cheaper. GET /v1/capabilities lists what can be solved. — $0.012002/call, paid per request via x402 (USDC).
| Name | Type | Req | Description |
|---|---|---|---|
| task | string | – | – |
No output schema declared.
No examples provided.
transcribe ~120
Transcribe the actual audio of a YouTube, TikTok or Instagram video with Whisper large-v3. Not caption scraping: the audio is downloaded and run through speech recognition, so it works on videos with no subtitles, in any language, and on TikTok and Instagram where no caption track exists at all. Extraction runs from a real residential IP, reaching sources that refuse datacenter ranges. Returns full text plus sentence-level timestamps. — $0.020006/call, paid per request via x402 (USDC).
| Name | Type | Req | Description |
|---|---|---|---|
| url | string | yes | – |
No output schema declared.
No examples provided.
uk_company ~103
Full profile of a UK company from Companies House: registered name and number, company type, incorporation date, registered office address, SIC activity codes, accounts and confirmation-statement filing dates, and current status. The authoritative record rather than a scraped copy. For agents vetting British counterparties, onboarding suppliers or enriching a CRM with verified company data. — $0.020007/call, paid per request via x402 (USDC).
| Name | Type | Req | Description |
|---|---|---|---|
| q | string | yes | – |
No output schema declared.
No examples provided.
uk_company-check ~103
Consolidated risk check on a UK company in one call: registry identity and status, directors, persons with significant control, filing history and overdue filings, plus any insolvency indicator. Replaces four separate Companies House lookups and the work of reconciling them. For agents vetting a British supplier or client before a contract is signed. — $0.080006/call, paid per request via x402 (USDC).
| Name | Type | Req | Description |
|---|---|---|---|
| q | string | yes | – |
No output schema declared.
No examples provided.
uk_officers ~101
Directors and officers of a UK company from Companies House: names, roles, appointment and resignation dates, nationality, country of residence and occupation. Shows who currently runs the company and who has left, which matters as much as the present board when assessing stability. For agents running compliance checks, mapping decision-makers or detecting recent governance changes. — $0.020008/call, paid per request via x402 (USDC).
| Name | Type | Req | Description |
|---|---|---|---|
| number | string | yes | – |
No output schema declared.
No examples provided.
uk_psc ~98
Persons with significant control of a UK company from Companies House: the beneficial owners, the nature of their control, their ownership bands and the date each interest was registered. This is the ultimate-beneficial-owner record that anti-money-laundering checks require. For agents running KYB and compliance onboarding on British entities. — $0.030006/call, paid per request via x402 (USDC).
| Name | Type | Req | Description |
|---|---|---|---|
| number | string | yes | – |
No output schema declared.
No examples provided.
unblock ~103
Fetch a page that blocks you, and get the HTML back. The request is routed through a French residential IP with a real Chromium browser, resolving JavaScript and passing the defences that reject datacenter ranges and plain HTTP clients. Use it as a fallback whenever your own fetch returns a challenge page, an empty shell or an access-denied response. — $0.020009/call, paid per request via x402 (USDC).
| Name | Type | Req | Description |
|---|---|---|---|
| url | string | yes | – |
No output schema declared.
No examples provided.
us_brief ~150
Ask about any US public company and get the answer, not the raw filings. One call returns a summary where every claim cites where it came from, the key points, and the questions the SEC data does not settle — with the underlying identity, three years of annual figures and the recent filings alongside, so you can check the summary against them. Built on SEC EDGAR. Buying the identity, the financials and the filings separately costs $0.090024; this replaces the three. Pay per call in USDC over x402, no account, no API key. — $0.040004/call, paid per request via x402 (USDC).
| Name | Type | Req | Description |
|---|---|---|---|
| ticker | string | – | – |
No output schema declared.
No examples provided.
us_company ~96
Profile of a US public company from SEC EDGAR: legal name, central index key, ticker symbols, exchange listings, standard industrial classification, business address and filer status. The authoritative regulatory record rather than an aggregator's copy. For agents resolving a company name to its regulatory identity before pulling financials or filings. — $0.020010/call, paid per request via x402 (USDC).
| Name | Type | Req | Description |
|---|---|---|---|
| ticker | string | yes | – |
No output schema declared.
No examples provided.
us_filings ~107
Recent regulatory filings of a US public company from SEC EDGAR: form type, filing and reporting dates, accession number and a direct link to each document. Covers annual and quarterly reports, current reports and insider transactions. For agents monitoring disclosure, detecting material events as they are filed, or retrieving the source document behind a figure. — $0.020011/call, paid per request via x402 (USDC).
| Name | Type | Req | Description |
|---|---|---|---|
| ticker | string | yes | – |
| type | string | yes | – |
No output schema declared.
No examples provided.
us_financials ~101
Financial statements of a US public company from SEC EDGAR XBRL data: revenue, net income, assets, liabilities and equity across reported periods, as filed with the regulator. Structured numbers rather than a document to parse. For agents doing fundamental screening, comparing reported performance across periods, or feeding audited figures into a model. — $0.050003/call, paid per request via x402 (USDC).
| Name | Type | Req | Description |
|---|---|---|---|
| ticker | string | yes | – |
No output schema declared.
No examples provided.
us_snapshot ~99
One-call snapshot of a US public company combining SEC EDGAR identity, latest reported financials and most recent filings. Replaces three separate lookups and the work of joining them on the right identifiers. For agents that need a company's regulatory and financial position in a single structured answer, for screening or for briefing before deeper research. — $0.060001/call, paid per request via x402 (USDC).
| Name | Type | Req | Description |
|---|---|---|---|
| ticker | string | yes | – |
No output schema declared.
No examples provided.
What is the x402-farm MCP server?
x402-farm is an MCP server listed in the public MCP registry as online.x-402/mcp. 64 x402 tools: cheap LLM $0.002, web+news search, French residential-IP scraping, FR/UK/US data. This page covers its hosted endpoint (https://api.x-402.online/mcp).
Is the x402-farm MCP server safe to use?
x402-farm scores 74 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.
What tools does the x402-farm MCP server expose?
x402-farm exposes 63 tools: transcribe, proxy_1gb, proxy_5gb, proxy_20gb, proxy_port_30d, and 58 more. Their descriptions and schemas cost roughly 7,059 tokens of context every time the server is loaded.
Does the x402-farm MCP server require authentication?
No. We connected to x402-farm without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.
Is the x402-farm MCP server still maintained?
x402-farm is still listed as active in the MCP registry. We last reached this channel on 20 September 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.