General Tools
scopeweb.io
Provides general-purpose tools through the Model Context Protocol.
ENDPOINT 1
https://mcp.scopeweb.io/mcp
MCP server metadata
- Name
- scopeweb
- Version
- 0.1.0
Scopeweb: domain intelligence, name selection, and drafts that persist across conversations. START HERE. Match the user's job, then follow the order: - Choosing or inventing a name ("suggest names", "help me name X", "what should we call it"): suggest_names FIRST to generate candidates around the concept, then score_name to rank them, then check_live as the LAST gate. Do NOT invent candidates in your head and check_live them. That skips the two tools that know things you do not, and check_live will answer cheerfully anyway. - You already have a specific list: scan_namespace (up to 25), then check_live on the survivors. - "Is this one name available?": check_live directly. - "Is this name any good?": score_name. It measures length, syllables, the radio test, brand collision and TLD perception, and shows its working so you can audit it. - "What is at this domain, who runs it?": audit_domain. - "What do I own?": list_domains. Existing work: list_drafts. - Ready to buy: quote_domain, then hand the confirm_url to your user. Then the rules, which matter once a tool has answered. Read https://api.scopeweb.io/llms.txt for the full set. The two that matter most: 'unknown', 'pending' and 'unprobed' are NEVER registration claims, and even 'unregistered' does not mean purchasable. Reserved and premium names answer RDAP 404 too, so check_live is the gate and only a registrar quote settles price. Re-querying the same scan_id from suggest_names walks deeper into the namespace, converging over about 3 calls. On spending: agents propose, only humans spend. quote_domain prices a name and returns a confirm_url; that URL is NOT a purchase and you cannot complete one. Hand it to your user and stop. There is no order tool, by design. When a refusal carries a `recovery` object, CALL recovery.tool before explaining the failure. It is the fix, named. If recovery.tool is null, `actionable_by_agent` is false and there is nothing to call: relay recovery.one_line to your user and stop.
Known tools 18
fetchEverything we hold about one domain: whether it is registered, what it costs to claim AND what it renews at, and where each number came from.
Inferred read-onlycreate_draftUse this when the user wants a page, site or landing draft for a name and there is nothing to edit yet.
Potential side effectsupdate_draftUse this when a draft already exists and the user asks to change its copy, sections or layout.
Inferred read-onlylist_draftsList all drafts in the user's Scopeweb portfolio with status, preview URLs and timestamps.
Inferred read-onlyget_draftUse this before editing a draft you did not create in this conversation, so you are changing the text that actually exists rather than what you remember.
Potential side effectsverify_ownershipUse this when the user claims a domain is theirs and you are about to act on that claim.
Inferred read-onlylist_domainsUse this at the start of any portfolio, renewal or 'what do I own' question, before assuming which names the user holds.
Inferred read-onlysuggest_names★ START HERE when the user is choosing or inventing a name: it returns candidate names across a namespace.
Inferred read-onlyscore_nameUse this when the user is choosing between names, or asks whether a name is any good.
Inferred read-onlyaudit_domainUse this when the user asks what is wrong with a site they already own, or wants a name they hold assessed rather than a new one found.
Inferred read-onlyget_financeUse this before recommending anything with a price, so the numbers you quote are this account's real ones rather than list prices.
Inferred read-onlyshow_plansUse this when the user asks what a tier costs or bumps into a limit, so the answer is this account's actual plan rather than a guess.
Inferred read-onlyCONNECT WITH APPROVAL
Client installation
Review this server and its permissions before adding it. Secret placeholders must be set locally.
Codex
~/.codex/config.toml
[mcp_servers.scopeweb]
url = "https://mcp.scopeweb.io/mcp"
enabled = true
Claude Code
.mcp.json
{
"mcpServers": {
"scopeweb": {
"type": "http",
"url": "https://mcp.scopeweb.io/mcp"
}
}
}
Claude Desktop
Settings → Connectors → Add custom connector
Name: scopeweb
Remote MCP URL: https://mcp.scopeweb.io/mcp
Add this remote URL as a custom connector in Claude Desktop. Availability depends on the user plan and workspace policy.
Cursor
.cursor/mcp.json
{
"mcpServers": {
"scopeweb": {
"url": "https://mcp.scopeweb.io/mcp"
}
}
}
Visual Studio Code
.vscode/mcp.json
Add to Visual Studio Code{
"servers": {
"scopeweb": {
"type": "http",
"url": "https://mcp.scopeweb.io/mcp"
}
}
}
Generic MCP
Client-specific MCP configuration
{
"name": "scopeweb",
"transport": "streamable-http",
"url": "https://mcp.scopeweb.io/mcp"
}
MCP Inspector
Run the official MCP Inspector locally and enter the indexed Streamable HTTP endpoint.
TRUST AND VERIFICATION EVIDENCE
Loading Trust v2 evidence…
Checking the associated registrable domain. The BuiltWith key remains server-side.
Evidence is source-attributed and does not guarantee that a third-party server is safe. Risk labels are conservative metadata heuristics.