# acquiresure > acquiresure is a people and company data API, a product of Keirolabs (keirolabs.cloud). Connect it to Claude, Codex or Cursor with one prompt and your agent can find work emails, verify them before outreach and identify the companies visiting your website. Also available as a no-code dashboard and a REST API. Pay only for results. acquiresure is a people and company data API, a product of Keirolabs (https://keirolabs.cloud). ## Product - Email validation: verdict (valid, risky, invalid), confidence, mail provider, catch-all detection. - Email finder: first name + last name + company domain → professional email. - IP to company: company domain, organization, location, network type for an IPv4/IPv6 address. - Batch email validation: up to 100 emails per batch, processed in the background. - Access: REST API (x-api-key header), MCP server (Streamable HTTP), and no-code dashboard tools. ## Pricing (credits per result; no result, no charge) - Find email (`POST /v1/email/find`): 1 credit, free when no email is found - Search leads (`POST /v1/leads/search`): 0.1 credit, free when no leads match; per lead listed; counting matches is free - Unlock lead email (`POST /v1/leads/reveal`): 1 credit, free when no email is found - People at a company (`POST /v1/company/people`): 0.1 credit, free when no one is found; per person, plus 1 per email found - Verify email (`POST /v1/email/validate`): 0.1 credit, free when the result is risky - Batch verify (`POST /v1/email/validate/batch`): 0.1 credit, free when risky or unprocessed (refunded); per unique email, up to 100 per batch - Person from email (`POST /v1/person/lookup`): 1 credit, free when no profile is found - Company tech stack (`POST /v1/company/tech`): 0.5 credit, free when nothing is detected - Company from IP (`POST /v1/ip/company`): 10 credits, free when no company is found - Access: open sign-up with email (not available in every region). Free trial: 10 credits, no card. Plans (monthly): Starter $25/mo for 2,000 credits a month, Growth $98/mo for 8,000 credits a month, Scale $365/mo for 50,000 credits a month. Yearly billing: 2 months free. Unused credits roll over while subscribed; volumes above the top plan are custom. - Sending: connect a Google Workspace inbox and your agent sends one-off emails or campaigns with up to 9 follow-ups (own copy, delay and local send time each) that stop on reply or bounce. Included in every paid plan, up to the plan's monthly email count (Starter 2,000, Growth 8,000, Scale 50,000, follow-ups included); the trial covers 20 emails. Outlook coming soon. - Rate limit: 120 requests per minute per account. ## MCP server - Works with: Claude Code, Codex, Cursor, Claude Desktop, VS Code, Windsurf, Gemini CLI. - Tools: validate_email, validate_emails_batch, get_batch_results, find_email, ip_to_company, search_leads, count_leads, reveal_emails, find_people_at_company, lookup_person, company_tech. - Install: tell your agent "Install the acquiresure MCP server by following https://api.acquiresure.cloud/mcpinstall.md. My API key is ." ## Blog Guides on finding work emails, verification, MCP servers and identifying website visitors, at https://acquiresure.cloud/blog: - [How to Find Anyone's Work Email (and Verify It Before You Send)](https://acquiresure.cloud/blog/find-work-emails) — The reliable ways to find a professional email address in 2026 — the name-plus-domain method, email finders, lead databases — and how to verify an email so your campaign never bounces. (September 18, 2026) - [How to Turn Your Website Visitors into Company Names](https://acquiresure.cloud/blog/website-visitors-to-companies) — Reverse IP lookup turns anonymous website traffic into company names — here's what an IP address can actually tell you, why B2B traffic is different, and how to build a visitor-based outreach workflow. (September 26, 2026) - [What Is an MCP Server? A Plain-English Guide](https://acquiresure.cloud/blog/what-is-an-mcp-server) — MCP (Model Context Protocol) is the open standard that lets AI agents like Claude, Cursor and Codex connect to real tools and data. Here's how MCP servers work, in plain English, and how sales teams use them. (September 22, 2026) ## Links - [Sign up](https://app.acquiresure.cloud/signup) - [Documentation](https://app.acquiresure.cloud/docs) - [MCP install guide](https://api.acquiresure.cloud/mcpinstall.md) - [Blog](https://acquiresure.cloud/blog) - [Help center](https://acquiresure.cloud/help): getting started, connecting Claude and ChatGPT, sending email, billing, troubleshooting - [Terms](https://app.acquiresure.cloud/terms) · [Privacy](https://app.acquiresure.cloud/privacy) ## FAQ ### What is acquiresure? acquiresure is a people and company data API for AI agents, a product of Keirolabs (keirolabs.cloud). Once connected, your agent (Claude, Codex, Cursor and others) can search for leads by title, skills, location and company, find their work emails, verify emails before outreach identify the companies behind your website visitors, and send the outreach from your own inbox with follow-ups that stop when someone replies. Your team can use the same tools in a dashboard, and developers can call a REST API. ### How do I sign up? Sign up with your email: no card, no password. You get a free trial to try it, once per person. acquiresure isn't available in every region yet. ### How do I connect acquiresure to Claude, ChatGPT, Codex or Cursor? In Claude or ChatGPT on the web, add a custom connector with the URL https://api.acquiresure.cloud/mcp, click Connect and approve on the acquiresure page: no API key needed (in ChatGPT, turn on Developer mode first). In Claude Code, Codex or Cursor, paste one prompt: "Install the acquiresure MCP server by following https://api.acquiresure.cloud/mcpinstall.md. My API key is ." The agent reads the install guide and adds the server to its own config. ### How much does it cost? One credit finds one work email. Searching leads costs 0.1 credits per lead, verifying an email 0.1 and identifying a company from an IP 10. Counting matching leads is free, and lookups with no result are never charged. New accounts start with 10 free credits, no card needed (one free trial per person). Plans are monthly: Starter is $25 for 2,000 credits, Growth $98 for 8,000 and Scale $365 for 50,000 ($0.0073 an email). Pay yearly and get 2 months free. Unused credits roll over while you stay subscribed, and you can cancel any time. Larger volumes get custom pricing. ### Can my agent send the emails too? Yes. Connect your Google Workspace inbox once, then ask your agent to email the leads it found. It drafts the emails and shows you, then sends them from your inbox, one at a time or as a campaign with up to 9 follow-ups. Each follow-up has its own copy, delay and send time, and stops as soon as someone replies or bounces. Sending respects working hours in the recipient's timezone and a daily cap for every inbox, and every email has one-click unsubscribe. Sending is included in every paid plan, up to the plan's monthly email count (2,000, 8,000 or 50,000 a month, follow-ups included); the free trial covers 20 emails. ### Which inboxes can I send from? Google Workspace inboxes today, connected with a Google app password that we check with Google and store encrypted. Outlook and Microsoft 365 are coming soon with Microsoft sign-in. Replies land in your inbox as usual; we read message headers to spot replies and bounces so follow-ups stop on their own. ### How accurate is email verification? Each check returns a verdict (valid, risky or invalid) with a confidence level, the mail provider, and whether the domain is a catch-all. Risky results, such as catch-all domains, are never charged. ### Can my agent build and clean a lead list? Yes. Give your agent names and company domains and it finds the work emails. Hand it a list and it verifies up to 100 emails per batch, dropping anything that would bounce. Risky and unprocessed emails are refunded. ### Can I verify a list of emails at once? Yes. The batch endpoint and the dashboard's list tool verify up to 100 emails per batch in the background. Duplicates are free, and risky or unprocessed emails are refunded when the batch finishes. ### Do you store the data I look up? No. Lookup inputs are sent to our data provider to perform the lookup and returned to you. We keep only request metadata (endpoint, time, status, latency, credits) for billing and your usage logs. Emails you send from a connected inbox are kept so you can see them, schedule follow-ups and track replies; you can delete them with your account at any time. ### What happens if you can't find an email? You're not charged. Lookups that return nothing, risky verifications and IPs with no company behind them never cost a credit. ### Can I cancel any time? Yes. Cancel from Billing in one click and your plan runs to the end of the period you paid for. Unused credits roll over every month while you're subscribed. ### Is it legal to email the people I find? B2B outreach to work emails is legal in most countries when it's relevant to the person's job and every email offers an easy way to opt out. Some countries, including parts of the EU, have stricter rules, so check the rules where your prospects are. Our terms don't allow spam. ### Is there a rate limit? Each account can make 120 API or MCP requests per minute. Contact us if you need more. --- # Blog articles (full text) # How to Find Anyone's Work Email (and Verify It Before You Send) Source: https://acquiresure.cloud/blog/find-work-emails Published: September 18, 2026 · Updated: September 27, 2026 Author: The acquiresure team Reading time: 6 minutes --- title: How to Find Anyone's Work Email (and Verify It Before You Send) description: The reliable ways to find a professional email address in 2026 — the name-plus-domain method, email finders, lead databases — and how to verify an email so your campaign never bounces. date: 2026-09-18 author: The acquiresure team updated: 2026-09-27 tags: Email finding, Verification, Guide tldr: Combine first name, last name and company domain, and let an email finder check the address against the company's mail server. | Pattern-guessing works sometimes, but every unverified guess risks a hard bounce that hurts your sender reputation. | Verify before sending — valid means send, risky (catch-all) means be careful, invalid means never send. | On acquiresure, a found email costs 1 credit (about $0.0125) and a verification 0.1; no result means no charge. --- The most reliable way to find someone's work email is to combine their first name, last name and company domain, then let an email finder check the address against the company's mail server before returning it. Guessing patterns works occasionally, but a verified finder is the only method that scales and doesn't poison your sender reputation with bounces. This guide walks through every method that still works in 2026, from free pattern-guessing to agent-driven lookup, and explains how to verify what you find before a single email goes out. ## What's the fastest way to find a work email address? Take the person's name and their company's domain, and run them through an email finder. A good finder tests candidate addresses against the company's mail servers and returns one it has confirmed is deliverable, so you start with an address that actually receives mail. With [acquiresure](https://acquiresure.cloud/), finding one work email costs 1 credit, and if no email exists you pay nothing — which is the honest way to price a lookup, because guessing is exactly what you're paying to avoid. ## Method 1: Guess the pattern and check it yourself Most companies use one of a handful of patterns for everyone: - `first@company.com` — very common in small companies and startups - `first.last@company.com` — the default at most mid-size companies - `f.last@company.com` or `firstinitiallast@company.com` — common in large, older organisations - `first_last@company.com` — frequent in engineering-heavy companies If you know one address at a company — say, the one on a press release or a job posting — you already know the pattern, and one guess for a new person is often right. The problem: you can't *know* an unverified guess is deliverable. Sending to a mailbox that doesn't exist produces a hard bounce, and every bounce damages your sender reputation. If you must guess, verify first (see below). ## Method 2: Use an email finder API An email finder does the guessing and the checking for you. You send a first name, last name and company domain; the service generates the likely candidates, checks them against the mail server, and returns the one that works — sometimes with the source that corroborates it. A REST call looks like this: ``` POST /v1/email/find { "firstName": "Maya", "lastName": "Chen", "domain": "brightpathfin.com" } ``` The response contains the email, a confidence score and how the address was found. If the finder can't produce a deliverable address, a good API returns nothing — and doesn't charge you for the miss. That's how acquiresure's [email finder](https://acquiresure.cloud/#tools) works: 1 credit per email found, free when nothing is found. ## Method 3: Start from the role, not the name Often you don't have a name — you have a target: "the Head of Sales at Series A fintechs in New York." Then the order of operations flips: 1. **Search a lead database by title, skills, location and company filters.** Counting the matches costs nothing on acquiresure; listing them costs 0.1 credits per lead. 2. **Pick the right person**, not just any person — the one whose job makes your email relevant. 3. **Reveal their email** from the profile (1 credit, charged only when an email is actually found). This is the workflow AI agents run best: you brief them on who you want to reach, and they search, filter and fetch verified emails in one pass. ## Why you must verify an email before sending Every hard bounce tells the receiving server you send to addresses you never checked. Accumulate enough of them and your messages start landing in spam — for everyone, not just the address that bounced. Verification is how you protect the reputation of the domain you send from. Mailbox providers are strict about this: Gmail's sender guidelines require bulk senders to authenticate with SPF, DKIM and DMARC and to keep their reported spam rate below 0.3%. A verification service connects to the recipient's mail server and performs a handshake: it asks whether the mailbox exists and accepts mail, without actually sending a message. In SMTP terms (RFC 5321) that's the `RCPT TO` step, where a `550` reply means the mailbox is unavailable. From that handshake (plus DNS checks on MX records and catch-all behaviour) you get a verdict: - **Valid** — the mailbox exists and accepts mail. Send with confidence. - **Risky** — the domain is a catch-all (it accepts everything, so existence can't be confirmed) or the server gave an ambiguous answer. Send carefully, or not at all. - **Invalid** — the mailbox doesn't exist. Never send. On acquiresure, verification costs 0.1 credits and risky results are never charged — you only pay for the answer you can act on. Batch verification handles up to 100 emails per run, and duplicates cost nothing. ## How to do all of this from your AI agent If Claude, Cursor, Codex or another MCP-speaking agent does your prospecting, you don't call the API — your agent does. Paste one prompt: > Install the acquiresure MCP server by following https://api.acquiresure.cloud/mcpinstall.md. My API key is . Then brief it like a teammate: "Find 20 heads of growth at Series A SaaS companies in New York and get me their verified work emails." The agent searches the lead database, reveals the emails, verifies each one and hands you a list that won't bounce. [Start with 10 free credits](https://api.acquiresure.cloud/signup) — no card needed. ## Frequently asked questions ### Is it legal to email someone's work address? B2B outreach to professional email addresses is legal in most countries when the message is relevant to the person's job and includes an easy way to opt out. Some regions, including parts of the EU, have stricter rules — check the rules where your prospects are, and don't spam. ### How accurate are email finders? A finder that verifies against the mail server before returning an address is materially more reliable than pattern-guessing, because it reports what the server said rather than what a pattern predicts. Look for a verdict and a confidence score with every result, and never trust a finder that claims 100% accuracy. ### What is a catch-all domain? A catch-all domain accepts mail for every address at the company, including ones that don't exist. That means a server handshake can't confirm an individual mailbox, so any address at a catch-all domain is inherently risky. acquiresure flags catch-alls in every verification and never charges for a risky result. ### Can I verify a whole list at once? Yes. Batch verification checks up to 100 emails per run in the background, deduplicates for free, and refunds risky and unprocessed emails. Give the list to your agent and ask it to "verify this CSV and drop anything that would bounce." ### How much does it cost to find and verify one email? Finding a work email costs 1 credit (about $0.0125 on the Starter plan at $25 for 2,000 credits); verifying it costs 0.1 credits. If no email is found or the verification comes back risky, you pay nothing. New accounts get [10 free credits](https://api.acquiresure.cloud/signup). ## Sources - [Google Workspace Admin Help: Email sender guidelines](https://support.google.com/a/answer/81126) - [IETF RFC 5321: Simple Mail Transfer Protocol](https://datatracker.ietf.org/doc/html/rfc5321) --- # How to Turn Your Website Visitors into Company Names Source: https://acquiresure.cloud/blog/website-visitors-to-companies Published: September 26, 2026 Author: The acquiresure team Reading time: 5 minutes --- title: How to Turn Your Website Visitors into Company Names description: Reverse IP lookup turns anonymous website traffic into company names — here's what an IP address can actually tell you, why B2B traffic is different, and how to build a visitor-based outreach workflow. date: 2026-09-26 author: The acquiresure team tags: IP intelligence, Outbound, Guide --- When someone visits your website, they don't leave a name — they leave an IP address. Reverse IP lookup (also called IP-to-company enrichment) resolves that address to the organisation behind it: the company name, its domain, its location and its network. For B2B sites, that conversion from anonymous hit to named account is the cheapest pipeline there is, because the visitors already raised their hands by showing up. Here's how the method works, what it can and can't tell you, and how to run the whole workflow — from raw log to verified email — with your AI agent. ## What can you actually learn from an IP address? An IPv4 or IPv6 address belongs to a network, and networks belong to organisations. A reverse lookup walks from the address to the network's registration and returns what's attached to it: - **The organisation name** — "Northwind Labs, Inc.", not just an ISP - **The company domain** — northwind.io, so you know where their email lives - **The location** — usually the registered office or network centre - **The network type** — whether it's a corporate/registered network or a consumer ISP The network type is the honest part of the answer. An address on a company's own network maps cleanly to that company. An address on a consumer ISP maps to a household, and household-level identification is neither possible nor appropriate — so a good lookup returns nothing rather than guessing. acquiresure's IP-to-company endpoint returns a company or a clean miss, and a miss costs you nothing. ## Why B2B traffic is different Consumer traffic mostly arrives over mobile networks and home broadband — thousands of people sharing address space, none of them individually identifiable. Business traffic is the opposite: offices sit on fixed, registered ranges owned by the employer. Someone browsing your pricing page from a corporate network is very plausibly there for work. That's why visitor identification is a B2B technique: - **Good matches:** visits from office networks, VPNs owned by companies, and business ISPs — you get a company name and domain. - **No matches (correctly):** mobile carriers, residential broadband, privacy-shared ranges. A tool that names a "company" for these is making it up. Your own analytics will tell you the split. If a meaningful slice of your traffic comes from corporate networks — and for most B2B products it's the majority of high-intent traffic — those visits are currently sitting in your logs as unexplored pipeline. ## The visitor-to-outreach workflow, step by step The full loop takes four steps, and an AI agent can run all of them: 1. **Collect the IPs.** Your web server already logs every visitor's address. Cloudflare, Vercel, nginx — wherever your access logs live, that's your source. Privacy rules matter here: don't hold on to raw visitor data longer than you need to enrich it. 2. **Resolve each IP to a company.** A batch of lookups turns addresses into company names and domains. On acquiresure this costs 10 credits per company found and nothing for addresses with no company behind them. 3. **Find the right person at each company.** Don't email `info@`. Decide who you'd want to talk to — the Head of Growth, the CTO, the founder — and search the people at each company for that role (0.1 credits per person found). 4. **Get a verified email and reach out.** Reveal the email (1 credit), verify it's deliverable (0.1 credits, risky results free), then send a personal note referencing what they looked at. "I saw someone from your team looking at our pricing page" is the warmest opener in outbound. ## Picking the person to email The company is the signal; the person is the work. Three heuristics that hold up: - **Small company?** Email the founder or CEO — they saw your site, or will want to know who did. - **Mid-size?** Email the person whose job matches the problem your product solves. The buyer, not the most senior name you can find. - **Enterprise?** Email the most senior person in the relevant team. A director of the right department beats a VP of the wrong one. This is where a lead database earns its keep: rather than guessing at org charts, you search the people at a specific company by title and seniority, and get the person whose job makes your email relevant — which is also the email that stays on the right side of the law in most countries. ## Running it from your agent You don't need to shuffle CSVs between four tools. Connect acquiresure to your agent with one prompt: > Install the acquiresure MCP server by following https://api.acquiresure.cloud/mcpinstall.md. My API key is . Then hand over the log: "Here are this week's visitor IPs. Find the companies, find the Head of Marketing at each, get their verified emails and draft a short intro to each." The agent resolves the IPs, searches each company, reveals and verifies emails, and comes back with a list — and a draft — while you were doing something else. [Start with 10 free credits](https://api.acquiresure.cloud/signup). ## Frequently asked questions ### Can you identify an individual person from an IP address? No, and any tool claiming to is overselling. Reverse IP lookup identifies the organisation that owns the network — the company, its domain and location. The individual person to email is a separate, deliberate step: searching the company for the right role. ### Is IP-to-company lookup legal? Resolving an IP to an organisation is generally treated like any other server-log analysis. What you do next is where care is needed: B2B outreach to work emails is legal in most countries when it's relevant to the recipient's job and easy to opt out of. Parts of the EU have stricter rules, so check where your prospects are before sending. ### Why does my traffic tool show fewer companies than visits? Because it's counting honestly. Consumer ISP and mobile visits resolve to nothing, repeat visits collapse to one company, and bots and monitors get filtered out. A smaller list of real companies beats a long list of guesses. ### How much does it cost to identify a website visitor's company? 10 credits per company identified on acquiresure (about $0.125 on the Starter plan), and addresses with no company behind them are free. From there, finding a person at the company costs 0.1 credits and a verified email 1 more. Lookups that return nothing are never charged. ### Do I need access logs to start? Yes — the method starts from IP addresses, which live in your web server's access logs or your analytics platform's raw export. If you use Cloudflare, Vercel or any mainstream host, you already have everything you need. --- # What Is an MCP Server? A Plain-English Guide Source: https://acquiresure.cloud/blog/what-is-an-mcp-server Published: September 22, 2026 Author: The acquiresure team Reading time: 5 minutes --- title: What Is an MCP Server? A Plain-English Guide description: MCP (Model Context Protocol) is the open standard that lets AI agents like Claude, Cursor and Codex connect to real tools and data. Here's how MCP servers work, in plain English, and how sales teams use them. date: 2026-09-22 author: The acquiresure team tags: MCP, AI agents, Explainer --- An MCP server is a small program that exposes a set of tools and data to an AI application over a standard protocol, so the AI can call those tools by itself. MCP stands for **Model Context Protocol** — an open standard, introduced by Anthropic in late 2024, that has since been adopted by Claude, Cursor, Codex, Windsurf and most other AI coding agents and assistants. Before MCP, every AI app needed a custom integration for every tool it wanted to use. After MCP, a tool needs one MCP server, and any MCP-speaking client can use it. That symmetry is the whole point. ## What "Model Context Protocol" actually means Break the name into its three words: - **Model** — an AI model: Claude, GPT, Gemini, or any other. - **Context** — the information and capabilities the model can reach beyond its training data: your CRM, a lead database, a web search API. - **Protocol** — an agreed message format, like HTTP for the web, that both sides speak. An MCP client lives inside the AI application. An MCP server lives wherever the tool's author runs it. The client asks the server "what can you do?", the server replies with a list of tools, and the model can then call any of them when a request calls for it — the same way it decides to run code or search the web. ## The problem MCP solves Without a protocol, connecting *M* AI applications to *N* tools means building *M × N* custom integrations. Every app has its own plugin format; every tool has to be wired up again for each app. MCP replaces that with one standard, so *M + N* implementations cover every combination. This is the same move the web made with HTTP and email made with SMTP: agree on the protocol once, and everything interconnects. For a sales or growth team, the practical consequence is bigger than it sounds: the tooling you buy once — a lead database, an email verifier — now works inside whichever agent each person on your team happens to use, today and next year. ## What an MCP server exposes An MCP server can offer three kinds of things. In practice, you'll mostly notice the first: 1. **Tools** — functions the model can call, with a name, a description and typed arguments. This is what makes an agent *act*: `find_email`, `search_leads`, `ip_to_company`. 2. **Resources** — data the model can read, like files or records, addressed like URLs. 3. **Prompts** — canned prompt templates the server offers to users of the client. Descriptions matter more than they look: the model reads them to decide when to call each tool. A good MCP server ships tools with descriptions precise enough that the model reaches for the right one without being told. ## What this looks like in practice acquiresure is a people-and-company data API — lead search, email finding and verification, company tech stacks, IP-to-company — that also ships as an MCP server. Its 11 tools include: - `search_leads` / `count_leads` — find people by title, skills, location and company filters - `find_email` / `reveal_emails` — get verified work emails - `validate_email` / `validate_emails_batch` — check deliverability before outreach - `company_tech`, `ip_to_company`, `lookup_person`, `find_people_at_company` A manual install in a client's config file looks like this: ```json { "mcpServers": { "acquiresure": { "url": "https://api.acquiresure.cloud/mcp?key=YOUR_KEY" } } } ``` Most agents today support remote MCP servers over HTTP, so there's usually nothing to install locally — the URL and your API key are the whole config. ## How to connect an MCP server to your agent The fastest path is to let the agent do it. Paste this one prompt into Claude, Cursor, Codex or any MCP-speaking agent: > Install the acquiresure MCP server by following https://api.acquiresure.cloud/mcpinstall.md. My API key is . The agent reads the install guide, writes its own config, reloads, and reports back that the tools are live. From then on you brief it in plain English — "find 50 heads of growth at Series A SaaS companies in New York and get their verified work emails" — and it calls the tools in sequence, verifies the emails and hands you a clean list. ## What MCP means if you're not a developer Three things change for a non-technical team: - **Your agent becomes the integration.** You don't build or configure anything per tool; you paste one prompt and the agent wires itself up. - **Tools become shareable across the team.** The same server works in Claude Code for one teammate and Cursor for another. acquiresure works across 17 agents, from Claude Code and Codex to Gemini CLI and Windsurf. - **The agent composes tools into workflows.** Search leads, reveal emails, verify them, check the company's tech stack — the model chains the calls itself, which is a different animal from clicking through a dashboard one lookup at a time. If your team sells to other businesses, that last point is the one to sit with: prospecting stops being a sequence of manual lookups and becomes a brief you hand to a teammate. ## Frequently asked questions ### Is MCP only for developers? No. MCP started in coding tools, and that's still where it's most visible, but it works in any AI client that speaks the protocol — including chat assistants like Claude on the web. If your agent can call tools, an MCP server can extend it, and installing one usually means pasting a single prompt. ### Does an MCP server run on my computer? Usually not. Modern agents support *remote* MCP servers, which run on the provider's infrastructure and are reached over HTTPS. Nothing is installed locally; your client just needs the server URL and an API key. ### Is MCP the same as a plugin? Plugins are specific to one application. An MCP server is written once against an open protocol and then works in every MCP-compatible client. acquiresure's server, for example, works in Claude Code, Codex, Cursor, Gemini CLI, Windsurf and more — from one URL. ### How much does it cost to use an MCP server? That depends on the tool behind it. acquiresure's MCP server is free to connect; you pay only for results — 1 credit per work email found, 0.1 to verify one, 10 to identify a company from an IP — and nothing when a lookup comes back empty. New accounts get [10 free credits](https://api.acquiresure.cloud/signup). ### Which agents support MCP? Most major ones: Claude Code, Claude Desktop, Codex, Cursor, Windsurf, Gemini CLI, VS Code (GitHub Copilot), Cline, OpenCode and more. acquiresure publishes [an install guide](https://api.acquiresure.cloud/mcpinstall.md) your agent can follow on its own.