Holston AI MCP server
com.holstonai/holston-aiholstonai.comstreamable-httpv1.5.0Scanned
AI visibility audits, llms.txt and schema generators, instant quotes, missed-call and ROI tools.
12 tools: 1 do something that can't be undone, 9 change things and 2 only read.
- Reads private data · 0
- Reads text others write · 4
- Can send data out · 4
- 4 findings
Tools listed without sign-in. Remote posture
With Anlyon
1 tool here does something that can't be undone. Govern it.
- Anlyon lists the tools and adopts none.
- Each tool you adopt gets approvals and receipts.
- Your agent never holds the key.
A tool your agent calls directly is not routed through Anlyon and is not governed by it. Anlyon Radar only lists and labels, and these labels are the same either way.
What the Holston AI MCP server can do
The Holston AI MCP server is published by holstonai.com, a domain the MCP Registry verified. It has 12 tools. It can do things that cannot be undone, such as sending, paying or publishing (request_consultation) and create or change data (9 tools: generate_boilerplate_schema, audit_ai_visibility, build_quote, build_systems_map and 5 more), but cannot delete data. 2 tools only read.
4 tools bring in text other people can write (audit_ai_visibility, generate_llms_txt, generate_business_schema and 1 more); 4 tools can send data out of your system (audit_ai_visibility, generate_llms_txt, generate_business_schema and 1 more).
The fixed checks matched 4 findings (annotation-conflict). Each one comes with the text it matched.
Its remote endpoint lists its tools without sign-in.
Last scanned Nov 13, 2026, version 1.5.0.
Tools
Grouped by what each tool does, most consequential first. Open one for its reasons and full description; descriptions are the publisher's own words.
12 tools
Can't be undone 1Claude Code: ask
request_consultationSends the user's contact details and project summary to Holston AI so the team can follow up.Reads text others writeCan send data outNo findings
Why it is in this group
- The name "request_consultation" says "request": a word for a change.
- The description's first verb is "send": a word for sending, and what is sent cannot be taken back.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
- outboundThe input takes a destination (input.phone): what the tool writes goes there.
Description, as the server wrote it Sends the user's contact details and project summary to Holston AI so the team can follow up. Before calling: collect name, email or phone, and a summary of what they need (include any quote or report links from this conversation), show the user exactly what will be sent, and get their explicit agreement. Never call it without that agreement or with made-up details.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: false
- openWorldHint: true
Changes things 9Claude Code: ask
audit_ai_visibilityAudits 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.Reads text others writeCan send data outNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
- outboundThe input takes a URL (input.url): a request to a URL can carry data to whoever runs it.
Description, as the server wrote it 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.
Annotations the server declares
- readOnlyHint: true
- idempotentHint: true
- openWorldHint: true
build_quoteBuilds 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, a…No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Description, as the server wrote it 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.
Annotations the server declares
- readOnlyHint: true
- idempotentHint: true
- openWorldHint: false
build_systems_mapDraws 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.No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Description, as the server wrote it 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.
Annotations the server declares
- readOnlyHint: true
- idempotentHint: true
- openWorldHint: false
calculate_manual_work_costCalculates 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 fr…No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Description, as the server wrote it 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.
Annotations the server declares
- readOnlyHint: true
- idempotentHint: true
- openWorldHint: false
calculate_missed_call_costEstimates 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 …1 finding
Why it is in this group
- The name "calculate_missed_call_cost" says "call": a word for a change.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Findings
- Warn
The server marks "calculate_missed_call_cost" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"idempotentHint":true,"openWorldHint":false}; The name "calculate_missed_call_cost" says "call": a word for a change.
Description, as the server wrote it 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.
Annotations the server declares
- readOnlyHint: true
- idempotentHint: true
- openWorldHint: false
design_ai_agentDesigns 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…No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Description, as the server wrote it 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.
Annotations the server declares
- readOnlyHint: true
- idempotentHint: true
- openWorldHint: false
generate_boilerplate_schemaGenerates a production-ready Next.js App Router repository layout, Prisma schema, and PostgreSQL DDL for a business domain (b2b_saas, marketplace, healthcare_admin, logistics, rest…1 finding
Why it is in this group
- The name "generate_boilerplate_schema" says "generate": a word for a change.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Findings
- Warn
The server marks "generate_boilerplate_schema" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"idempotentHint":true,"openWorldHint":false}; The name "generate_boilerplate_schema" says "generate": a word for a change.
Description, as the server wrote it 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.
Annotations the server declares
- readOnlyHint: true
- idempotentHint: true
- openWorldHint: false
generate_business_schemaBuilds ready-to-paste Organization or LocalBusiness structured data (JSON-LD) with address, phone, hours, service area, services, social profiles and optional FAQs.Reads text others writeCan send data out1 finding
Why it is in this group
- The name "generate_business_schema" says "generate": a word for a change.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
- outboundThe input takes a destination (input.phone): what the tool writes goes there.
- outboundThe input takes a URL (input.url): a request to a URL can carry data to whoever runs it.
Findings
- Warn
The server marks "generate_business_schema" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"idempotentHint":true,"openWorldHint":true}; The name "generate_business_schema" says "generate": a word for a change.
Description, as the server wrote it 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 <script> tag plus checks to fix before publishing. Use it when an audit shows missing business schema.
Annotations the server declares
- readOnlyHint: true
- idempotentHint: true
- openWorldHint: true
generate_llms_txtReads 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 an…Reads text others writeCan send data out1 finding
Why it is in this group
- The name "generate_llms_txt" says "generate": a word for a change.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
- outboundThe input takes a destination (input.phone): what the tool writes goes there.
- outboundThe input takes a URL (input.url): a request to a URL can carry data to whoever runs it.
Findings
- Warn
The server marks "generate_llms_txt" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"idempotentHint":true,"openWorldHint":true}; The name "generate_llms_txt" says "generate": a word for a change.
Description, as the server wrote it 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.
Annotations the server declares
- readOnlyHint: true
- idempotentHint: true
- openWorldHint: true
Only reads 2Show 2 read-only tools
calculate_mvp_timeline_roiCompares a Holston AI fixed-price 2–4 week build against a traditional ~6-month build.No findings
Why it is in this group
- The description's first verb is "compare": a word for reading.
Description, as the server wrote it 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.
Annotations the server declares
- readOnlyHint: true
- idempotentHint: true
- openWorldHint: false
get_agent_templatesLists 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 f…No findings
Why it is in this group
- The name "get_agent_templates" says "get": a word for reading.
Description, as the server wrote it 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.
Annotations the server declares
- readOnlyHint: true
- idempotentHint: true
- openWorldHint: false
This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.
Exfil surface
Which tools read private data, which read text someone else can write, and which can send data out. One of each is a path a prompt injection can use.
No private-data, untrusted-input, outbound path in this server alone: no tool is tagged private-data.
- Reads private data0
- Reads files, mail, messages, databases, secrets, calendars or repositories.
- Reads text others write4
- Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
- Can send data out4
- Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.
Other servers in the same agent add their own tools to these paths. Audit your whole setup to see them together.
Remote posture
What anyone on the internet sees at the remote endpoint: an anonymous initialize and tools/list, and the public OAuth metadata.
Looked at Nov 20, 2026, 18:40 UTC, unchanged since Oct 29, 2026. No credentials were sent and no tool was called. What is looked at.
- Reachable
- yes
- HTTP status of an anonymous initialize
- 200
- tools/list served without credentials
- yes
- Tools that change things, listed without credentials
- 10
- Protocol version
- 2025-06-18
- WWW-Authenticate on 401
- not observed
- resource_metadata in WWW-Authenticate
- not observed
- RFC 9728 protected resource metadata
- not observed
- Authorization servers
- not observed
- Legacy HTTP+SSE transport
- no
- Dynamic client registration
- not observed
- Client ID metadata documents
- not observed
- HighThe whole server
The endpoint served tools/list without credentials, and the list has 10 tools that change things (1 irreversible, 9 write). Whether a call also works without credentials was not tested: tools are never called.
What this check looks forMatched text
https://holstonai.com/mcp: tools/list returned 12 tools to an anonymous client, including request_consultation (irreversible), generate_boilerplate_schema (write), audit_ai_visibility (write), build_quote (write), build_systems_map (write) and 5 more
Posture changes
- Oct 29, 2026
- Reachable: no to yes
- HTTP status of an anonymous initialize: none to 200
- tools/list served without credentials: no to yes
- Tools that change things, listed without credentials: 0 to 10
- Protocol version: none to 2025-06-18
Findings
Matches of fixed checks, with the text they matched.
The server marks "generate_boilerplate_schema" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"idempotentHint":true,"openWorldHint":false}; The name "generate_boilerplate_schema" says "generate": a word for a change.
The server marks "calculate_missed_call_cost" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"idempotentHint":true,"openWorldHint":false}; The name "calculate_missed_call_cost" says "call": a word for a change.
The server marks "generate_llms_txt" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"idempotentHint":true,"openWorldHint":true}; The name "generate_llms_txt" says "generate": a word for a change.
The server marks "generate_business_schema" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"idempotentHint":true,"openWorldHint":true}; The name "generate_business_schema" says "generate": a word for a change.
History
Changes to its tool definitions and to its remote endpoint, newest first.
PostureRemote posture changed. Reachable: no -> yes; HTTP status of an anonymous initialize: none -> 200; tools/list served without credentials: no -> yes (and 2 more).View diff
- Reachable: no to yes
- HTTP status of an anonymous initialize: none to 200
- tools/list served without credentials: no to yes
- Tools that change things, listed without credentials: 0 to 10
- Protocol version: none to 2025-06-18
Install
Pinned to version 1.5.0. Values in angle brackets are yours to fill in.
claude mcp add --transport http holston-ai https://holstonai.com/mcpclaude mcp add --transport http holston-ai https://holstonai.com/mcpRun in a terminal.
Claude Code permissions
Allow the reads, ask before a change or a way out, deny the deletes. Paste into .claude/settings.json.
{
"permissions": {
"allow": [
"mcp__holston-ai__calculate_mvp_timeline_roi",
"mcp__holston-ai__get_agent_templates"
],
"ask": [
"mcp__holston-ai__generate_boilerplate_schema",
"mcp__holston-ai__audit_ai_visibility",
"mcp__holston-ai__build_quote",
"mcp__holston-ai__build_systems_map",
"mcp__holston-ai__calculate_manual_work_cost",
"mcp__holston-ai__calculate_missed_call_cost",
"mcp__holston-ai__design_ai_agent",
"mcp__holston-ai__generate_llms_txt",
"mcp__holston-ai__generate_business_schema",
"mcp__holston-ai__request_consultation"
],
"deny": []
}
}Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. A read that can send data out (it takes a URL, say) asks first too. It assumes the server is installed as holston-ai. Review it before you use it.
Capability tags behind 4 rules
- mcp__holston-ai__audit_ai_visibility untrusted-input, outbound
- mcp__holston-ai__generate_llms_txt untrusted-input, outbound
- mcp__holston-ai__generate_business_schema untrusted-input, outbound
- mcp__holston-ai__request_consultation untrusted-input, outbound
Pin
Keep the decision: fail CI when the tools change, follow every change, or show a badge.
Pin in CI
Fail a build when the tools you reviewed are not the tools the server serves today.
curl -s "https://radar.anlyon.com/api/v1/servers/com.holstonai/holston-ai/verify?hash=f44e5dfcd648713999a1cef69438a4e49d6a0fddf229c920b83780dcad482b34" | jq -e '.changed == false'Pinned hash f44e5dfcd648, from Nov 13, 2026, 11:17 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/com.holstonai/holston-ai/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/com.holstonai/holston-ai)Source: MCP Registry. Synced Oct 21, 2026, 17:56 UTC.
Holston AI MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the Holston AI MCP server safe?
- No scan can promise that. What its definitions show: 12 tools, 10 of which can change, send or delete something, and 4 findings from fixed checks. Allow the reads, ask before each change, and deny the deletes; the permissions block on this page does that.
Can the Holston AI MCP server delete data?
- No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.
Can the Holston AI MCP server do things that cannot be undone?
- Yes. 1 tool can send, pay, publish or merge: request_consultation.
What tools does the Holston AI MCP server have?
- 12 tools: 1 irreversible, 9 write, 2 read. request_consultation, generate_boilerplate_schema, audit_ai_visibility, build_quote, build_systems_map, calculate_manual_work_cost, calculate_missed_call_cost, design_ai_agent and 4 more.
Does the Holston AI MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the Holston AI MCP server send data to outside services?
- 4 tools can carry data out (it sends, posts or publishes, or takes a recipient, channel or URL): audit_ai_visibility, generate_llms_txt, generate_business_schema and request_consultation.
Has the Holston AI MCP server changed its tools?
- Not since Anlyon Radar started tracking it. Last scanned Nov 13, 2026.