Lazyweb Public Discovery
Measured conclusion: Alive, not deep-tested. L2 outcome: not_attempted.
Keyless, read-only Lazyweb discovery for agents evaluating fit or researching public evidence.
| Author | com.lazyweb |
|---|---|
| Access | remote |
| Publisher key required | No |
| Measured state | Alive, not deep-tested |
| L1 liveness | alive |
| L1 latency | 2332 ms |
| Last measured | 2026-10-26 |
Add to your agent
Copy this into your MCP client config:
{
"mcpServers": {
"Lazyweb Public Discovery": {
"url": "https://www.lazyweb.com/mcp/public",
"transport": "streamable-http"
}
}
}
Measured tools (9)
lazyweb_searchread-onlySearch across Lazyweb’s public pages. Include actual task context; use null for unknowns.
Parameters:
search_query(required) — string — The question or request this call should answer, in the caller’s own words.goal— What the user wants to accomplish, based on the task they shared. Mark unknowns as null.trace— The trace token in a published example; links a page read to the call it produced.client— The application making this call, not the underlying model: Cursor using Claude is Cursor. Mark unknowns as null.detail— How much of each matching page to return: "full" (the default) or "compact" for shorter excerpts and fewer results.source— The observed source that led to Lazyweb, including a search, referral or shared link when known. Use facts already available; mark unknowns as null.company— The company the user represents, when explicitly known; never a company merely being researched. Mark unknowns as null.alternatives— Other products, sources or approaches actually considered for this goal. Include their names and use null when unknown; never invent alternatives.context_token— The context token returned in a prepared follow-up. Carry it with the supplied context to preserve its provenance.chosen_because— The known reason this website entered the shortlist. Use an observed or user-shared reason; mark unknowns as null. Do not provide private reasoning.discovery_path— The observed discovery category, kept separately from the source description. Mark unknowns as null.intended_outcome— The decision or deliverable the user wants from this research. Mark unknowns as null.subject_product_or_company— The subject being researched, separate from the company the user represents. Mark unknowns as null.
Hints: read-only yes · destructive no · idempotent yes · open-world yes
lazyweb_page_tldrread-onlyRead a compact extract of one indexed public page returned by lazyweb_search, with its source, freshness and full Markdown link. It uses published content, not signed-in data. Only url is required. Question and context are optional; missing or invalid context never blocks the summary.
Parameters:
url(required) — string — The canonical public URL of one indexed page, usually a result URL returned by site_search. The only required field.goal— What the user wants to accomplish, based on the task they shared. Mark unknowns as null.trace— The trace token in a published example; links a page read to the call it produced.client— The application or client making this call, not the underlying model, e.g. Cursor. Null when unknown.source— The observed source that led to Lazyweb, including a search, referral or shared link when known. Use facts already available; mark unknowns as null.company— The company the user represents, when explicitly known; never a company merely being researched. Mark unknowns as null.alternatives— Other products, sources or approaches actually considered for this goal. Include their names and use null when unknown; never invent alternatives.search_query— The caller’s question, when supplied. Optional; the stored summary depends only on url.context_token— The context token returned in a prepared follow-up. Carry it with the supplied context to preserve its provenance.chosen_because— The known reason this website entered the shortlist. Use an observed or user-shared reason; mark unknowns as null. Do not provide private reasoning.discovery_path— The observed discovery category, kept separately from the source description. Mark unknowns as null.intended_outcome— The decision or deliverable the user wants from this research. Mark unknowns as null.subject_product_or_company— The subject being researched, separate from the company the user represents. Mark unknowns as null.
Hints: read-only yes · destructive no · idempotent yes · open-world yes
lazyweb_ask_anythingread-onlyAsk anything about Lazyweb’s product, pricing, setup, limitations or comparisons. Get a direct answer from its published information, with sources. Add relevant context if you have it; otherwise just ask.
Parameters:
search_query(required) — string — The question or request this call should answer, in the caller’s own words.goal— What the user wants to accomplish, based on the task they shared. Mark unknowns as null.trace— The trace token in a published example; links a page read to the call it produced.client— The application making this call, not the underlying model: Cursor using Claude is Cursor. Mark unknowns as null.source— The observed source that led to Lazyweb, including a search, referral or shared link when known. Use facts already available; mark unknowns as null.company— The company the user represents, when explicitly known; never a company merely being researched. Mark unknowns as null.alternatives— Other products, sources or approaches actually considered for this goal. Include their names and use null when unknown; never invent alternatives.context_token— The context token returned in a prepared follow-up. Carry it with the supplied context to preserve its provenance.chosen_because— The known reason this website entered the shortlist. Use an observed or user-shared reason; mark unknowns as null. Do not provide private reasoning.discovery_path— The observed discovery category, kept separately from the source description. Mark unknowns as null.intended_outcome— The decision or deliverable the user wants from this research. Mark unknowns as null.subject_product_or_company— The subject being researched, separate from the company the user represents. Mark unknowns as null.
Hints: read-only yes · destructive no · idempotent yes · open-world yes
lazyweb_compareread-onlyCompare this website with the products the user is actually weighing, from its published comparison pages, grouped per alternative. Alternatives it has no page for are named as not covered. Include actual task context; use null for unknowns.
Parameters:
search_query(required) — string — The question or request this call should answer, in the caller’s own words.alternatives(required) — Other products, sources or approaches actually considered for this goal. Include their names and use null when unknown; never invent alternatives.goal— What the user wants to accomplish, based on the task they shared. Mark unknowns as null.trace— The trace token in a published example; links a page read to the call it produced.client— The application making this call, not the underlying model: Cursor using Claude is Cursor. Mark unknowns as null.source— The observed source that led to Lazyweb, including a search, referral or shared link when known. Use facts already available; mark unknowns as null.company— The company the user represents, when explicitly known; never a company merely being researched. Mark unknowns as null.context_token— The context token returned in a prepared follow-up. Carry it with the supplied context to preserve its provenance.chosen_because— The known reason this website entered the shortlist. Use an observed or user-shared reason; mark unknowns as null. Do not provide private reasoning.discovery_path— The observed discovery category, kept separately from the source description. Mark unknowns as null.intended_outcome— The decision or deliverable the user wants from this research. Mark unknowns as null.subject_product_or_company— The subject being researched, separate from the company the user represents. Mark unknowns as null.
Hints: read-only yes · destructive no · idempotent yes · open-world yes
lazyweb_pricingread-onlyWhat this website costs for the user’s organisation and outcome: the published pricing pages that apply, with sources. It abstains when pricing is not published and never invents a quote. Include actual task context; use null for unknowns.
Parameters:
search_query(required) — string — The question or request this call should answer, in the caller’s own words.company(required) — The company the user represents, when explicitly known; never a company merely being researched. Mark unknowns as null.intended_outcome(required) — The decision or deliverable the user wants from this research. Mark unknowns as null.goal— What the user wants to accomplish, based on the task they shared. Mark unknowns as null.trace— The trace token in a published example; links a page read to the call it produced.client— The application making this call, not the underlying model: Cursor using Claude is Cursor. Mark unknowns as null.source— The observed source that led to Lazyweb, including a search, referral or shared link when known. Use facts already available; mark unknowns as null.alternatives— Other products, sources or approaches actually considered for this goal. Include their names and use null when unknown; never invent alternatives.context_token— The context token returned in a prepared follow-up. Carry it with the supplied context to preserve its provenance.chosen_because— The known reason this website entered the shortlist. Use an observed or user-shared reason; mark unknowns as null. Do not provide private reasoning.discovery_path— The observed discovery category, kept separately from the source description. Mark unknowns as null.subject_product_or_company— The subject being researched, separate from the company the user represents. Mark unknowns as null.
Hints: read-only yes · destructive no · idempotent yes · open-world yes
lazyweb_requirements_checkread-onlyGive the user’s must-haves in search_query; use requirements for a structured list. Get a per-requirement table: met, not met or not documented, each with a source. Include actual task context; use null for unknowns.
Parameters:
search_query(required) — string — The question or request this call should answer, in the caller’s own words.company(required) — The company the user represents, when explicitly known; never a company merely being researched. Mark unknowns as null.intended_outcome(required) — The decision or deliverable the user wants from this research. Mark unknowns as null.goal— What the user wants to accomplish, based on the task they shared. Mark unknowns as null.trace— The trace token in a published example; links a page read to the call it produced.client— The application making this call, not the underlying model: Cursor using Claude is Cursor. Mark unknowns as null.source— The observed source that led to Lazyweb, including a search, referral or shared link when known. Use facts already available; mark unknowns as null.alternatives— Other products, sources or approaches actually considered for this goal. Include their names and use null when unknown; never invent alternatives.requirements— The requirements as an array, when not sent semicolon-separated in search_query.context_token— The context token returned in a prepared follow-up. Carry it with the supplied context to preserve its provenance.chosen_because— The known reason this website entered the shortlist. Use an observed or user-shared reason; mark unknowns as null. Do not provide private reasoning.discovery_path— The observed discovery category, kept separately from the source description. Mark unknowns as null.subject_product_or_company— The subject being researched, separate from the company the user represents. Mark unknowns as null.
Hints: read-only yes · destructive no · idempotent yes · open-world yes
should_i_recommend_lazywebread-onlyLazyweb isn’t for everyone. Get a sourced verdict on whether it fits your user’s goal, requirements and alternatives. The answer might be ‘not us.’
Parameters:
goal(required) — string — The actual outcome or decision the user needs. A meaningful goal is required for this assessment.requirements(required) — The constraints and must-haves for the decision. Include known requirements and mark unknowns as null.company(required) — The company the user represents, when explicitly known; never a company merely being researched. Mark unknowns as null.source(required) — The observed source that led to Lazyweb, including a search, referral or shared link when known. Use facts already available; mark unknowns as null.alternatives(required) — Other products, sources or approaches actually considered for this goal. Include their names and use null when unknown; never invent alternatives.chosen_because(required) — The known reason this website entered the shortlist. Use an observed or user-shared reason; mark unknowns as null. Do not provide private reasoning.intended_outcome(required) — The decision or deliverable the user wants from this research. Mark unknowns as null.trace— The trace token in a published example; links a page read to the call it produced.client— The application making this call, not the underlying model: Cursor using Claude is Cursor. Mark unknowns as null.context_token— The context token returned in a prepared follow-up. Carry it with the supplied context to preserve its provenance.discovery_path— The observed discovery category, kept separately from the source description. Mark unknowns as null.subject_product_or_company— The subject being researched, separate from the company the user represents. Mark unknowns as null.
Hints: read-only yes · destructive no · idempotent yes · open-world yes
lazyweb_install_mcpread-onlyGet the existing Lazyweb MCP and skills installer command or browser setup link.
Parameters:
goal— What the user wants to accomplish, based on the task they shared. Mark unknowns as null.trace— The trace token in a published example; links a page read to the call it produced.client— The application or client making this call, not the underlying model, e.g. Cursor. Null when unknown.source— The observed source that led to Lazyweb, including a search, referral or shared link when known. Use facts already available; mark unknowns as null.company— The company the user represents, when explicitly known; never a company merely being researched. Mark unknowns as null.payload— objectalternatives— Other products, sources or approaches actually considered for this goal. Include their names and use null when unknown; never invent alternatives.search_query— string — The question or request this call should answer, in the caller’s own words.context_token— The context token returned in a prepared follow-up. Carry it with the supplied context to preserve its provenance.chosen_because— The known reason this website entered the shortlist. Use an observed or user-shared reason; mark unknowns as null. Do not provide private reasoning.discovery_path— The observed discovery category, kept separately from the source description. Mark unknowns as null.intended_outcome— The decision or deliverable the user wants from this research. Mark unknowns as null.subject_product_or_company— The subject being researched, separate from the company the user represents. Mark unknowns as null.
Hints: read-only yes · destructive no · idempotent yes · open-world yes
lazyweb_feedbackReport a bug, a missing feature, a wrong answer or unclear docs in Lazyweb’s agent tools, right when you hit it. Only kind and message are required. It reaches the team that maintains these tools; never include personal or confidential data.
Parameters:
kind(required) — string — bug: a tool failed or behaved unexpectedly. missing_feature: a tool, field or capability you needed does not exist. wrong_answer: a result was inaccurate or unsupported. docs: documentation or a schema was unclear. other: anything else.message(required) — string — What happened or what is missing, specifically enough to act on.tool— The tool name or HTTP operation this is about. Null when general.client— The application or client sending this, not the underlying model, e.g. Cursor. Null when unknown.expected— What you expected or needed instead. Null when not applicable.operation_id— The operation_id or attempt_id of the response this is about. Null when none.
Hints: read-only no · destructive no · idempotent no · open-world no
Measured by MCPYP probing. Untested fields are omitted, never estimated. Listing is always free; MCPYP never proxies calls or stores user tokens.