# Holston AI (remote · holstonai.com) AI visibility audits, llms.txt and schema generators, instant quotes, missed-call and ROI tools. - Trust score: 72/100 (medium) - Registry status: active - Liveness: live - Owner verified: no - Last scored: 2026-10-23 ## Components - remote · `holstonai.com`: 72/100 (this document), [markdown](https://verifymcp.io/servers/com-holstonai-holston-ai/holstonai.md), [page](https://verifymcp.io/servers/com-holstonai-holston-ai/holstonai) ## Channel facts - Endpoint: `https://holstonai.com/mcp` - Transports: `streamable-http` - Auth: `none` - Version: `1.5.0` ## Trust breakdown 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. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog) Scored 2026-10-23. - **Endpoint Security**: 74/100 - The endpoint's TLS certificate is valid, in date, and uses a strong key. - No authorisation is required to call this server. Every tool declares its destructiveHint and none is destructive, so open access doesn't expose one. - HTTPS is enforced; there's no plaintext access path. - HSTS check failed: the Strict-Transport-Security header is absent. - DNSSEC check failed: this domain isn't protected by DNSSEC. - **Transport & Reachability**: 100/100 - Verified streamable-http transport via a live MCP handshake. - **Schema Quality & AI Usability**: 74/100 - 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name). - AI-judged instruction clarity (good). - Context-footprint check failed: tool/resource definitions use about 3291 tokens (~274/item across 12 items; 12 tools + 0 resources), over budget; trim descriptions and params. - Usage-examples check failed: none of the tools include examples. - **Stability & Change Management**: 13/100 - Stability observed for 4 of 30 days with no destabilising changes; credit accrues until the full window elapses. - **Tool Coverage**: 95/100 - 100% of tools have a non-trivial description (not blank, and not just the tool's name). - 85% of tool parameters carry a description. - **Tool Safety**: 100/100 - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured. - All 1 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation. - An AI judge read all 13 captured unit(s) of tool text and found none that tries to manipulate the model reading it. - **Capabilities**: 100/100 - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28. ## Install ### How do I install the Holston AI MCP server? Holston AI is a hosted endpoint at https://holstonai.com/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. ### Claude ```bash claude mcp add --transport http com-holstonai-holston-ai 'https://holstonai.com/mcp' ``` ### Cursor ```json { "mcpServers": { "com-holstonai-holston-ai": { "url": "https://holstonai.com/mcp" } } } ``` ### VS Code ```json { "servers": { "com-holstonai-holston-ai": { "type": "http", "url": "https://holstonai.com/mcp" } } } ``` ### Codex ```toml [mcp_servers.com-holstonai-holston-ai] url = "https://holstonai.com/mcp" ``` ### opencode ```json { "$schema": "https://opencode.ai/config.json", "mcp": { "com-holstonai-holston-ai": { "type": "remote", "url": "https://holstonai.com/mcp", "enabled": true } } } ``` ### OpenClaw ```bash openclaw mcp add com-holstonai-holston-ai --url 'https://holstonai.com/mcp' --transport streamable-http ``` ### Hermes ```yaml mcp_servers: com-holstonai-holston-ai: url: "https://holstonai.com/mcp" ``` ### Netclaw ```json { "McpServers": { "com-holstonai-holston-ai": { "Transport": "http", "Url": "https://holstonai.com/mcp" } } } ``` ### Vellum ```bash assistant mcp add com-holstonai-holston-ai -t streamable-http -u 'https://holstonai.com/mcp' ``` ### Other ```json { "mcpServers": { "com-holstonai-holston-ai": { "type": "http", "url": "https://holstonai.com/mcp" } } } ``` The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs. ## Changelog Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims. ### 2026-10-21 (score 72, +1) - [security] The server rewrote its instructions, which are the text every model session reads - [functional regression] Schema quality: 2915 → 3291 - [functional] Server version: 1.5.0 → 1.6.0 - [functional] New tool “design_ai_agent” - [functional] New tool “get_agent_templates” ### 2026-10-20 (score 71, +1) - [security] The server rewrote its instructions, which are the text every model session reads - [functional regression] Schema quality: 2553 → 2915 - [functional improvement] Stability: unverified → 0.03 - [functional] Server version: 1.4.0 → 1.5.0 - [functional] New tool “calculate_missed_call_cost” ### 2026-10-19 (score 70) First indexed and scored. ## MCP tools (12) ### `calculate_mvp_timeline_roi` (~451 tokens) MVP Timeline ROI Calculator Compares a Holston AI fixed-price 2–4 week build against a traditional ~6-month build. Returns build costs, labor savings captured, cost of delay, developer-weeks freed, payback week, and a month-by-month cumulative net position over the analysis window. Input parameters: - `analysis_horizon_months` (integer): Length of the comparison window in months (default 6). - `automation_rate` (number): Fraction of the manual hours eliminated once the software is live, 0–1 (default 0.7). - `dev_annual_cost_usd` (number): Fully loaded annual cost per in-house developer (default $150,000). - `dev_headcount` (integer, required): Number of in-house developers who would be assigned to a traditional build. - `holston_fixed_price_usd` (number): A specific fixed-price quote from Holston AI. If omitted, the scope's standard starting price is used. - `holston_internal_involvement` (number): Share of the in-house dev team's time needed during a Holston build, 0–1 (default 0.1). - `manual_hourly_cost_usd` (number): Fully loaded hourly cost of the staff doing the manual work (default $45). - `manual_process_hours_per_week` (number, required): Hours per week your team currently spends on the manual process the software will replace. - `project_scope` (string, required): Target project scope. Websites: website_launch (up to 5 pages, 5 days) | website_growth (up to 10 pages, 10 days) | website_commerce (online store, 15–20 days). Small app: small_app (2 wks). Apps & A… - `traditional_timeline_weeks` (integer): Delivery timeline of the traditional path in weeks (default: 6–12 for websites, 26 ≈ 6 months for apps/agents). - `traditional_vendor_cost_usd` (number): External agency/vendor spend on the traditional path, on top of in-house dev time (default 0). ### `generate_boilerplate_schema` (~168 tokens) Boilerplate Schema Generator Generates a production-ready Next.js App Router repository layout, Prisma schema, and PostgreSQL DDL for a business domain (b2b_saas, marketplace, healthcare_admin, logistics, restaurant_retail, professional_services, manufacturing). Multi-tenant by default with org membership and audit logging; optional agent-run tables. Input parameters: - `domain` (string, required): Business domain: b2b_saas | marketplace | healthcare_admin | logistics | restaurant_retail | professional_services | manufacturing. - `include_ai_agents` (boolean): Add AgentRun/ToolCall tables plus agent runtime and MCP directories (default true). - `output` (string): What to generate: repo_layout | prisma | sql | all (default all). - `project_name` (string): Repository / package name (kebab-case). ### `audit_ai_visibility` (~142 tokens) AI Visibility Audit Audits a live public website and scores (0–100, grade A–F) how well AI assistants (ChatGPT, Claude, Perplexity) and search engines can find, read and cite it. Checks robots.txt rules for AI and search crawlers, server-rendered text, business and FAQ structured data, Open Graph, llms.txt, sitemap, HTTPS, mobile viewport and response time. Returns each check with a plain-English fix, the top 3 fixes, and a shareable report link. Takes up to ~20 seconds. Input parameters: - `url` (string, required): Website to audit, e.g. example.com or https://www.example.com/ ### `build_quote` (~343 tokens) Instant Quote Builds an itemized Holston AI quote from fixed prices: one-time builds, monthly plans, first-year total (monthly plans have a 12-month minimum), timeline, terms, fitting add-ons, and a shareable link to the quote on holstonai.com. Ask what the customer needs first; do not add plans they did not ask for. Input parameters: - `assessment` (string): Systems & Data Health Check, a one-time fixed-price assessment by company size: assessment-small (up to 50 employees) | assessment-medium (51–200) | assessment-large (201–500). The fee is credited to… - `builds` (array): One-time builds. website-starter (one page, 3 days) | website-launch (up to 5 pages, 5 days) | website-growth (up to 10 pages, CMS, 10 days) | website-commerce (online store, 15–20 days) | small-app… - `business_name` (string): Customer or business name to show on the quote. - `care` (string): Monthly service contract: care-site (websites) | care-app (apps and agents). - `hosting` (string): Monthly hosting: hosting-site (websites) | hosting-app (apps and agents). - `seo_plan` (string): Monthly SEO + AEO plan: seo-essentials (local) | seo-growth (adds AI search / AEO) | seo-authority (adds links, PR, competitor tracking). ### `build_systems_map` (~129 tokens) Systems Map Draws a map of a company's software systems and how data moves between them (automatic, manual, export/import), as a Mermaid diagram with a shareable link. Flags manual handoffs, the same data kept in several unsynced systems, hub systems many processes depend on, and systems with no connections. Use after interviewing the user about their systems; nothing is stored. Input parameters: - `company` (string): Company name, shown on the map. - `flows` (array): How data moves between systems. - `systems` (array, required): Every software system, database or important spreadsheet the business uses. ### `calculate_manual_work_cost` (~164 tokens) Manual Work Cost Calculator Calculates what manual, repetitive work caused by disconnected systems costs per year: staff hours, full-time equivalents, labor and error costs, five-year cost, and the savings from automating it. Input a list of tasks with hours per week; hourly cost is optional. Input parameters: - `automation_rate` (number): Share of these hours that connecting the systems would remove, 0–1 (default 0.7). - `company` (string): Company name for the report. - `default_hourly_cost_usd` (number): Hourly cost used when a task has none (default $40). - `tasks` (array, required): Each manual or repetitive task caused by disconnected systems. - `working_weeks_per_year` (number): Working weeks per year (default 48). ### `calculate_missed_call_cost` (~325 tokens) Missed Call Cost Calculator Estimates the revenue a business loses each year to unanswered phone calls (missed calls, lost callers, lost customers, monthly and five-year loss) and how much an AI receptionist that answers every call could recover. Give calls per week (or missed calls per week) and the average job value; every other assumption has a sensible default. Input parameters: - `average_job_value_usd` (number, required): Average revenue from a new customer's first job or purchase. - `calls_per_week` (number): Inbound phone calls per week. - `close_rate` (number): Share of new callers who become customers when answered, 0–1 (default 0.4). - `company` (string): Company name for the report. - `customer_lifetime_value_usd` (number): Optional: total revenue from a typical customer over time. Used instead of the average job value. - `missed_per_week` (number): Missed calls per week, if known. Overrides calls_per_week × missed_rate. - `missed_rate` (number): Share of calls that go unanswered, 0–1 (default 0.25). - `new_caller_share` (number): Share of missed callers who are new potential customers, 0–1 (default 0.5). - `no_callback_rate` (number): Share of those new callers who call a competitor instead of calling back, 0–1 (default 0.6). - `recovery_rate` (number): Share of lost calls an AI receptionist would handle, 0–1 (default 0.9). ### `get_agent_templates` (~94 tokens) AI Agent Templates Lists Holston AI's ready-built AI receptionist templates by industry (HVAC, plumbing, roofing, dental, law and more): the services, the questions the agent asks, the default call flow, optional steps, and emergency handling. Give an industry id for one template, or omit it for the list. Use it before design_ai_agent. Input parameters: - `industry` (string): Industry id. Omit to list all industries. ### `design_ai_agent` (~242 tokens) AI Receptionist Designer Designs an AI receptionist for a business from Holston AI's templates: the step-by-step call flow, what it does at any point (pricing questions, emergencies, transfers), and a link to holstonai.com where the owner can edit it and talk to the agent out loud in their browser for free. Only the industry and business name are required. Holston AI builds the real version on the business's phone line at a fixed price confirmed after a short call. Input parameters: - `add_steps` (array): Optional step ids to switch on, e.g. photos, returning, message. - `business_name` (string, required): The business name the agent answers with. - `city` (string): Main service area, if it is one of these East Tennessee and Southwest Virginia cities. - `emergency_transfer` (boolean): Transfer emergencies to an on-call number (default true where emergencies apply). - `hours` (string): Business hours option. - `industry` (string, required): Industry id (see get_agent_templates). - `pricing` (string): How the agent answers pricing questions. - `services` (array): Service ids from the template. Defaults to the template's main services. ### `generate_llms_txt` (~269 tokens) llms.txt Generator Reads a public website (homepage, sitemap and main pages) and writes a ready-to-upload llms.txt file that tells AI assistants who the business is, what it offers, where it works and which pages matter. Optional details (services, service area, hours, key facts) make it stronger. Use it when an audit shows no llms.txt. Input parameters: - `address` (string): Street address, city, state and ZIP. - `business_name` (string): Override the business name found on the site. - `email` (string) - `hours` (string): Opening hours, e.g. 'Mon–Fri 8am–5pm, Sat 9am–1pm'. - `key_facts` (array): Short facts AI assistants should know: years in business, licenses, starting prices, guarantees, awards. - `phone` (string) - `service_area` (string): Where the business works, e.g. 'Kingsport, Johnson City and Bristol, TN'. - `services` (array): Main services or products, one per item. - `summary` (string): Two or three sentences: what the business does, for whom, and where. Overrides the site's description. - `url` (string, required): The business website, e.g. example.com ### `generate_business_schema` (~349 tokens) Business Schema Generator Builds ready-to-paste Organization or LocalBusiness structured data (JSON-LD) with address, phone, hours, service area, services, social profiles and optional FAQs. If a website is given, details are pre-filled from it. Returns the