Liquid Agent

Local business leads with checked emails (paid, $0.03 a lead)

leads_search

Read-only

PAID over x402 inside this tool call (USDC on Base or Arc, $0.03 per lead returned, flat, with or without an email; default 3 leads = $0.09; set sample=true for 3 free leads first; the PaymentRequired quotes the exact total; no leads, no charge): local businesses by category and place with a graded email (A/B/C), a contact name when the email shows one, phone, website, socials and buying signals (no website, booking tool, payment system, hiring). Call once without payment to get the x402 PaymentRequired, then call again with the signed payment in _meta["x402/payment"].

Input Schema

TableJSON Schema

Name	Required	Description
`zip`	No	5-digit ZIP (a prefix works).
`city`	No	City, e.g. Atlanta, Savannah, Macon. Give city, county, zip or near.
`near`	No	lat,lng to search around.
`email`	No	required (default), any, or none (phone-only businesses).
`limit`	No	How many leads, 1-1,000 (default 3 = $0.09); $0.03 per lead.
`county`	No	County, e.g. Gwinnett, Chatham.
`hiring`	No	Only businesses whose site says they are hiring.
`offset`	No	Skip this many, for the next page.
`sample`	No	true = 3 free leads to judge quality (3 a day), no payment.
`booking`	No	Online booking tool: yes, none, vagaro, square_appointments, calendly, booksy, mindbody, acuity, opentable, housecall_pro, jobber, servicetitan, zocdoc.
`website`	No	needs = no working website (a sales signal).
`category`	Yes	Business type in plain words: dentist, plumber, hvac, roofing, hair salon, law firm, med spa, restaurant.
`minGrade`	No	Email grade floor (A best). Default C.
`payments`	No	Payment system on their site: yes, none, square, toast, clover, stripe, paypal.
`radiusKm`	No	Radius for near, default 5.

Output Schema

TableJSON Schema

Name	Required	Description
`next`	No	URL of the next page
`count`	No	Leads returned
`leads`	No	Each lead: name, category, address, phone, website, websiteProof, email with grade, contact, socials, signals, listing
`query`	No	The search as understood
`checks`	No	How leads are checked
`grades`	No	What each email grade means
`sample`	No	true when this was the free sample
`source`	No	Data sources
`priceUsd`	No	Price of this call in USD

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedOct 12, 2026

changedOutput schema / (root)

Previous value: -nullNew value: +{
+  "$schema": "http://json-schema.org/draft-07/schema#",
+  "additionalProperties": {},
+  "properties": {
+    "checks": {
+      "description": "How leads are checked",
+      "type": "string"
+    },
+    "count": {
+      "description": "Leads returned",
+      "type": "number"
+    },
+    "grades": {
+      "additionalProperties": {},
+      "description": "What each email grade means",
+      "properties": {},
+      "type": "object"
+    },
+    "leads": {
+      "description": "Each lead: name, category, address, phone, website, websiteProof, email with grade, contact, socials, signals, listing",
+      "items": {},
+      "type": "array"
+    },
+    "next": {
+      "description": "URL of the next page",
+      "type": "string"
+    },
+    "priceUsd": {
+      "description": "Price of this call in USD",
+      "type": "number"
+    },
+    "query": {
+      "additionalProperties": {},
+      "description": "The search as understood",
+      "properties": {},
+      "type": "object"
+    },
+    "sample": {
+      "description": "true when this was the free sample",
+      "type": "boolean"
+    },
+    "source": {
+      "description": "Data sources",
+      "type": "string"
+    }
+  },
+  "type": "object"
+}

Changed2 schema fields changedOct 12, 2026

changedInput schema / properties / limit / description

Previous value: -"How many leads, 1-1,000 (default 10 = $0.30); $0.03 per lead."New value: +"How many leads, 1-1,000 (default 3 = $0.09); $0.03 per lead."

addedInput schema / properties / sample

Added value: +{
+  "description": "true = 3 free leads to judge quality (3 a day), no payment.",
+  "type": "boolean"
+}

Changed1 schema field changedOct 12, 2026

changedInput schema / properties / limit / description

Previous value: -"How many leads, 1-1,000 (default 10 = $0.10); 100+ and 500+ per call cost less per lead."New value: +"How many leads, 1-1,000 (default 10 = $0.30); $0.03 per lead."

Changed3 schema fields changedOct 11, 2026

removedInput schema / properties / key

Removed value: -{
-  "description": "Your Liquid Leads plan key: plan leads are free, past the quota the overage pays per lead.",
-  "pattern": "^ll_[A-Za-z0-9]{32}$",
-  "type": "string"
-}

changedInput schema / properties / limit / description

Previous value: -"How many leads, 1-100 (default 25)."New value: +"How many leads, 1-1,000 (default 10 = $0.10); 100+ and 500+ per call cost less per lead."

changedInput schema / properties / limit / maximum
```
Previous value: -100New value: +1000
```

AddedOct 10, 2026

TDQS

A4.5/5.0

Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Extensive disclosure beyond the annotations: flat $0.03 per lead regardless of email presence, default 3 leads = $0.09, sample limited to 3 free leads per day, 'no leads, no charge', and the two-call x402 handshake. readOnlyHint=true remains consistent since no data is mutated.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loads the cost model in capitals so the agent sees 'PAID' immediately, then packs the payment flow and payload description into two dense sentences. The parenthetical is long but every clause carries pricing or workflow information rather than filler.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a 15-parameter, paid, open-world tool with an output schema, the description covers the payment lifecycle and the shape of returned leads, which is what an agent needs before calling. It leaves unspecified the relative scope versus the other leads_* siblings, a minor gap.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is already 100%, so the baseline is 3, but the description adds meaning the schema lacks: the pricing consequence of limit ('default 3 = $0.09; $0.03 per lead'), the purpose of sample, and the semantics of minGrade and buying-signal filters framed as sales signals rather than raw fields.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource – returning local businesses by category and place with graded emails (A/B/C), contact name, phone, website, socials and buying signals. It is distinguishable from sibling leads tools (leads_lookup, leads_count, leads_tech) by its explicit email-grade and signal payload.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives concrete invocation guidance: set sample=true for 3 free leads first, then call once without payment to receive the x402 PaymentRequired and call again with the signed payment in _meta["x402/payment"]. It does not, however, say when to prefer this over sibling leads_lookup or leads_tech.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All Liquid Agent tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Local business leads with checked emails (paid, $0.03 a lead)

Input Schema

Output Schema

Schema Changelog

TDQS

Glama MCP Gateway

Resources