This server analyzes company domains to determine how far they've actually gone with AI, returning a maturity tier and supporting evidence.
Detect an ai_maturity tier for a domain: none, declared, deployed, or commercialized
Analyze a single domain or batch multiple domains in one call
Get detected AI vendors and categories, validated llms.txt status, and robots.txt AI-crawler policy
Read quotable evidence strings behind each verdict
Optionally restrict reporting to specific AI vendors
Toggle pricing-page analysis (check_pricing) for faster results, capped at deployed when disabled
Force a fresh analysis with skipCache, bypassing the 7-day cache
Distinguish bot-challenged domains with blocked: true instead of false negatives
Return flat, Clay-ready JSON; read-only and idempotent, requiring only an Apify token
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@AI Tooling Detector MCP Server Does intercom.com charge for AI or just talk about it?"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
An MCP server that exposes the Mamba Labs AI Tooling Detector as a single tool. Install one package and give your MCP client a way to ask, for any company domain, whether that company only talks about AI, actually runs AI tooling on its site, or charges money for AI. It wraps the Mamba Labs actor on Apify and returns Clay-ready flat JSON.
Related MCP server: enrich-company-mcp
This server gives an AI client one tool:
detect_ai_tooling: return an ai_maturity tier for a company domain, plus the evidence behind it.
The tier has four levels and each one needs its own class of evidence:
Tier | What it means | What proves it |
| The company charges for AI | AI credits, a token allowance, an AI add-on, an AI-named plan, or a per-outcome AI price on the pricing page |
| AI tooling is running on the site | An AI-native vendor, a direct inference endpoint, or an AI-capable platform backed by AI copy |
| The company says AI, nothing observable | A validated llms.txt, AI crawler rules in robots.txt, or weighted marketing copy |
| No signal fired | Nothing |
A domain sitting behind a bot challenge comes back with blocked: true at low confidence rather than as a confident no, so a challenged site is never mistaken for a company with no AI.
All of the work runs on Apify. This package is a thin client that routes the tool call to the actor and hands back the result.
You need Node.js 18 or newer and an Apify account with an API token.
Add this to your Claude Desktop config:
{
"mcpServers": {
"mamba-ai-tooling-detector": {
"command": "npx",
"args": ["-y", "@mambalabsdev/mcp-ai-tooling-detector"],
"env": { "APIFY_TOKEN": "your-apify-token" }
}
}
}Restart the client and the detect_ai_tooling tool appears.
Node.js 18 or newer
An Apify API token from https://console.apify.com/account/integrations
Calls consume Apify credits, billed per domain analyzed. Free Apify plans get 15 results per calendar month.
"Does intercom.com actually charge for AI, or do they just market it?"
"Check notion.so, figma.com and berkshirehathaway.com for AI adoption and tell me which ones already pay for AI."
"Which AI vendors are running on zendesk.com?"
"Does cursor.com publish an llms.txt, and does their robots.txt block GPTBot?"
detect_ai_tooling
Input | Type | Required | Description |
| string | one of these | A single company domain, e.g. |
| string[] | one of these | Batch mode. Takes precedence over |
| array | no | Report only these AI vendors, one or more of the 52 fingerprinted tools ( |
| boolean | no | Fetch and score the pricing page. Default true. Setting it false is faster but caps the result at |
| boolean | no | Force a fresh analysis and ignore the 7 day result cache. |
The tool is read-only and idempotent. It never writes anything.
Input reference, the complete output field list, pricing tiers, error handling, and the measured limitations are on the actor's Apify Store page:
https://apify.com/mambalabs/ai-tooling-detector
Immutable actor ID: EwkHhmqiuJgRoVEbE
This server is part of the Mamba Labs GTM Suite, a fleet of specialized MCP servers for go-to-market signal intelligence, each backed by a dedicated Apify actor. The @mambalabsdev/mcp-gtm-suite umbrella server exposes all of them, including this one, through a single install.
Actor | Immutable Actor ID |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
|
Built by Mamba Labs | npm | Apify Store
MIT
Built by Mamba Labs. https://apify.com/mambalabs
Given a company domain, determine how far that company has actually gone with AI. Returns an ai_maturity tier of none, declared (says AI but nothing observable is running), deployed (AI tooling is live on the site), or commercialized (the pricing page charges for AI via credits, tokens, an add-on, an AI-named plan, or a per-outcome price). Also returns the detected AI vendors and categories, validated llms.txt status, robots.txt AI-crawler policy, and the quotable evidence strings behind the verdict. A domain behind a bot challenge comes back with blocked=true at low confidence rather than as a false negative. Public data only, no login. Returns flat Clay-ready JSON. Read-only; requires an APIFY_TOKEN and consumes Apify credits per domain analyzed.
| Name | Required | Description | Default |
|---|---|---|---|
| domain | No | A single company domain, e.g. intercom.com. Provide either domain or domains. | |
| domains | No | Batch mode: several company domains analyzed in one call. Takes precedence over domain. | |
| skipCache | No | Force a fresh analysis and ignore the 7 day result cache. | |
| check_pricing | No | Fetch and score the pricing page. Default true. Setting this false is faster but caps the result at 'deployed', because 'commercialized' can only be proven on a pricing page. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Beyond the annotations (readOnlyHint, idempotentHint), the description discloses many behavioral traits: returns specific fields (ai_maturity, vendors, categories, llms.txt status, robots.txt policy, evidence strings), how bot challenges are handled (blocked=true at low confidence), and that public data requires no login but costs credits. This is rich, useful context that annotations alone do not provide.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a well-organized paragraph that front-loads the core purpose, then details return values, an edge case, and operational constraints. Each sentence adds distinct value, and the length is appropriate for the tool's complexity.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
With no output schema, the description must explain return values and does so thoroughly: it lists the ai_maturity tiers, detected vendors/categories, llms.txt status, robots.txt policy, evidence strings, and the blocked field. It also covers the 'flat Clay-ready JSON' format, making the tool's behavior fully understandable without an output schema.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The schema description coverage is 100%, so all parameter semantics are already documented. The tool description adds no new parameter-specific details beyond what the schema already states, though it does reinforce the overall domain-targeting concept. Baseline 3 is appropriate because the schema does the heavy lifting.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool's function: 'Given a company domain, determine how far that company has actually gone with AI' and defines the exact output tiers (none, declared, deployed, commercialized). This makes the purpose specific and unambiguous, even without siblings to distinguish from.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides clear usage context: it takes a domain or domains, supports batch mode, and explains the effect of check_pricing (capping at 'deployed'). It also mentions operational prerequisites (APIFY_TOKEN, Apify credits) and the bot-challenge edge case. No explicit exclusions or alternatives are given, but with no sibling tools this is not a gap.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections. Dates show when Glama detected each change.
v1.0.0detect_ai_toolingWith only one tool, there is no possibility of confusing it with others. The tool's purpose is clearly defined and unique within the server.
The single tool name follows a clear verb_noun pattern ('detect_ai_tooling'), which is consistent and descriptive. With one tool, naming consistency is trivially maintained.
The server has only one tool, which feels thin for a comprehensive tool server but is appropriate for a narrowly focused utility. The count is on the low end of reasonable.
The tool covers the entire domain of AI tooling detection for a given domain, including maturity tiering, vendor detection, llms.txt validation, robots.txt policy, and evidence. No obvious gaps exist for the stated single-purpose scope.
Unclaimed servers have limited discoverability.
If you are the server author, to access and configure the admin panel.
Scan any website for AI readiness — 100-point score across 6 AEO categories in seconds.
Scan any website's AI readiness: AI search visibility and AI agent usability. Free, no auth.
Turn a company domain into a structured B2B sales brief from their public website.
Extract structured pricing tiers and addons from any SaaS pricing page URL. Built for AI agents.
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/mambalabsdev/mcp-ai-tooling-detector'
If you have feedback or need assistance with the MCP directory API, please join our Discord server
