What can you do with this server?

The Vexi MCP Server connects AI agents to structured business data via the Vexi API, enabling discovery, retrieval, and crawling of business information in a clean, typed format. * search_businesses: Find businesses using free-text queries (name, keyword, etc.), filtered by location, business type/category, and minimum data completeness score — returns structured Agent Business Objects (ABOs). * get_business: Retrieve a complete ABO for a specific business by its unique slug, including identity, offerings, location, contact info, trust signals, operations, and quality metadata. * crawl_business: Submit a website URL to queue a new business for crawling, with an option to wait for the crawl to complete before returning results. * list_categories: Retrieve all available business categories to assist with filtering and discovery.

How do I use Vexi MCP Server?

1. Click on "Install Server". 2. Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state. 3. In the chat, type @ followed by the MCP server name and your instructions, e.g., "@Vexi MCP Server find top CRM platforms in the US" 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.

Vexi MCP Server

Official

by getvexi

Overview Schema Related Servers Score Discussions

JavaScript

Remote

@getvexi/mcp

npm version License: MIT Website

Structured business data for AI agents - connect Claude, Cursor, and any MCP-compatible client to the Vexi API in 30 seconds.

What is Vexi?

Vexi is a structured business data API designed for AI agents. Instead of scraping and parsing raw HTML, your agent gets a clean, typed Agent Business Object (ABO) - a JSON document with identity, offerings, contact channels, trust signals, and quality metadata.

With one call, agents can discover businesses, fetch full records, and request fresh crawls when data is missing or stale.

Related MCP server: AI List My Business

Prerequisites

Node.js 18+
A Vexi API key - get one free at https://getvexi.dev/signup

Installation

Claude Desktop

Open your Claude Desktop MCP configuration file:

macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
Windows: %APPDATA%\Claude\claude_desktop_config.json

Add or merge the vexi server entry under mcpServers.
Paste the following configuration (replace the API key with yours):

{
  "mcpServers": {
    "vexi": {
      "command": "npx",
      "args": ["-y", "@getvexi/mcp"],
      "env": {
        "VEXI_API_KEY": "vxi_live_..."
      }
    }
  }
}

Windows users: If npx doesn't work, use the cmd wrapper instead:

{
  "mcpServers": {
    "vexi": {
      "command": "cmd",
      "args": ["/C", "npx", "-y", "@getvexi/mcp"],
      "env": {
        "VEXI_API_KEY": "vxi_live_..."
      }
    }
  }
}

Save the file and fully quit Claude Desktop.
Relaunch Claude Desktop - the vexi tools should appear in your MCP tools list.

Cursor

Open Cursor.
Go to Settings > MCP.
Add a new server:

Command: npx
Args: -y, @getvexi/mcp
Env: VEXI_API_KEY=vxi_live_...

Save and restart Cursor.

Other MCP clients

Run the server via stdio:

npx -y @getvexi/mcp

Set VEXI_API_KEY in the process environment before starting the client.

Available Tools

Tool	Description
`search_businesses`	Search for businesses by query and location
`get_business`	Get a full ABO for a specific business by slug
`crawl_business`	Queue a new business for crawling
`list_categories`	List all available business categories

Example Usage

User: Find the top 3 CRM platforms in the US.

Claude calls search_businesses:

{
  "query": "CRM platform",
  "location": "US",
  "limit": "3"
}

Claude: Here are three CRM platforms in the US:

Business	Completeness
HubSpot	0.94
Salesforce	0.97
Pipedrive	0.89

User: Give me full details on HubSpot.

Claude calls get_business:

{
  "slug": "hubspot"
}

Claude: Returns the full ABO for HubSpot - identity, offerings, contact channels, trust signals, operations, agent interface hints, and quality metadata in one structured document.

ABO Schema

Every business is returned as an Agent Business Object with eight top-level sections:

{
  "identity": {
    "id": "biz_hubspot",
    "name": "HubSpot",
    "slug": "hubspot"
  },
  "offerings": {
    "products": ["CRM", "Marketing Hub", "Sales Hub"],
    "price_range": "$$"
  },
  "location": {
    "headquarters": "Cambridge, MA",
    "country": "US"
  },
  "contact": {
    "website": "https://hubspot.com",
    "email": "support@hubspot.com"
  },
  "trust": {
    "rating": 4.5,
    "review_count": 12000
  },
  "operations": {
    "founded_year": 2006,
    "employee_range": "5000+"
  },
  "agent_interface": {
    "summary": "Inbound marketing and CRM platform for SMBs and enterprises",
    "suggested_queries": ["Compare pricing tiers", "List integrations"]
  },
  "quality": {
    "completeness_score": 0.94,
    "last_updated": "2026-05-28T12:00:00Z"
  }
}

Get your API Key

Start free with 500 credits - no credit card required.

License

MIT

Available Tools

4 tools

crawl_businessC

Queue a new business for crawling from a URL.

ParametersJSON Schema

Name	Required	Description	Default
`url`	Yes	Website URL to crawl
`wait`	No	Wait for crawl to complete before returning (optional)

TDQS

C2.9/5.0

Behavior2/5

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

No annotations are provided, so the description must disclose behavioral traits. It says 'queue,' suggesting asynchronous operation, but does not explain how to check completion, handle errors, or that crawling may take time. No mention of side effects or rate limits.

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?

The description is a single, clear sentence with no redundant words. It is front-loaded with the key action and resource, though it may be overly brief given the tool's complexity.

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

Completeness2/5

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

No output schema exists, but the description does not hint at return values or behavior (e.g., returns a crawl_id). Given the tool has a non-trivial action (queuing and waiting), the description is incomplete for an AI agent to know how to interpret results.

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

Parameters3/5

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

Schema coverage is 100%, so the schema already describes both parameters. The description adds no additional nuance beyond 'queue a new business,' which reiterates the tool's purpose. Baseline of 3 is appropriate.

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

Purpose4/5

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

The description clearly states the action ('queue') and resource ('business for crawling from a URL'). It distinguishes from siblings like get_business (retrieve cached) and search_businesses (search), but does not explicitly contrast them.

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

Usage Guidelines2/5

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

No explicit guidance on when to use this tool versus alternatives, such as get_business for cached data. The description implies it is for starting a crawl, but omits prerequisites or context like needing authentication or URL validity.

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

get_businessC

Get a full ABO for a specific business by slug.

ParametersJSON Schema

Name	Required	Description	Default
`slug`	Yes	Business slug identifier

TDQS

C2.9/5.0

Behavior2/5

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

No annotations provided, so description must convey behavioral traits. It only states 'Get', implying a read operation, but does not disclose any side effects, authentication needs, or data scope. The term 'full ABO' is vague about what exactly is returned.

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

Conciseness5/5

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

Single sentence with no wasted words. It is front-loaded and efficient.

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

Completeness2/5

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

No output schema and no description of return value. Low complexity with one parameter, but the description fails to clarify what 'full ABO' entails, leaving the agent uninformed about the response structure.

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

Parameters3/5

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

Only one parameter 'slug' with schema description 'Business slug identifier'. Schema coverage is 100%, so description adds no extra meaning beyond the schema. Baseline 3 is appropriate.

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

Purpose4/5

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

The description uses 'Get' as a verb and specifies the resource as 'full ABO' with the method 'by slug'. However, the term 'ABO' is unexplained acronym, causing ambiguity. It distinguishes from siblings like 'search_businesses' by implying a single-object retrieval.

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

Usage Guidelines2/5

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

No guidance on when to use this tool versus alternatives like 'crawl_business' or 'search_businesses'. The description lacks context on prerequisites or scenarios for usage.

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

list_categoriesA

List all available business categories.

ParametersJSON Schema

Name	Required	Description	Default
No parameters

TDQS

A3.9/5.0

Behavior3/5

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

With no annotations, the description carries full burden. It only says 'List', implying a read operation, but does not disclose pagination, caching, or other behavioral traits. For a zero-parameter list, this is adequate minimal disclosure.

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

Conciseness5/5

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

The description is a single, concise sentence with no unnecessary words. Every part is relevant.

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

Completeness3/5

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

The tool has no output schema and no parameters. The description is minimal but sufficiently explains the tool's core function. However, it could mention the return format or potential empty results for completeness.

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?

There are no parameters, and schema coverage is 100% (empty). The description does not need to add parameter details. Baseline for zero parameters is 4.

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?

The description 'List all available business categories' clearly states the verb (List) and resource (business categories), and it distinguishes the tool from siblings like crawl_business, get_business, and search_businesses.

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

Usage Guidelines3/5

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

The description implies that the tool is used to retrieve all categories, but it does not explicitly state when to use it versus alternatives or provide any exclusions or context-specific guidance.

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

search_businessesC

Search for businesses by query and location. Returns Agent Business Objects (ABOs).

ParametersJSON Schema

Name	Required	Description
`q`	No	Search query (business name, keyword, or free-text)
`location`	No	City, state, country, or geo hint (optional)
`business_type`	No	Business type or category filter (optional)
`limit`	No	Max number of results to return (optional)
`min_completeness`	No	Minimum ABO completeness score 0-1 (optional)

TDQS

C2.9/5.0

Behavior2/5

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

With no annotations, the description must disclose behavioral traits but only states that it searches and returns ABOs. It omits details like pagination, ordering, rate limits, or error handling, which are critical for AI agents.

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

Conciseness5/5

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

The description is extremely concise with two sentences, no redundant information, and the purpose is front-loaded. Every word earns its place.

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

Completeness2/5

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

Given the tool has 5 optional parameters and no output schema, the description is insufficient. It does not explain what an ABO is, how results are sorted, or how to use optional parameters effectively.

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

Parameters3/5

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

Schema coverage is 100%, so the baseline is 3. The description adds no new meaning beyond the schema; it merely restates the presence of query and location parameters.

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

Purpose4/5

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

The description clearly states the tool searches for businesses by query and location, and mentions the output type (ABOs). It is distinguishable from sibling tools like 'crawl_business' or 'get_business' which focus on specific businesses.

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

Usage Guidelines2/5

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

No guidance is provided on when to use this tool versus alternatives. There are no exclusions or when-not scenarios mentioned. The purpose is implied but not explicitly contextualized.

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

Install Server

RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

TDQS

A3.7/5.0

Disambiguation5/5

Each tool serves a distinct purpose: crawl queues a business, get retrieves by slug, lists categories, and searches by query/location. No overlap.

Naming Consistency5/5

All tool names follow a consistent verb_noun pattern in snake_case (crawl_business, get_business, list_categories, search_businesses).

Tool Count5/5

Four tools are appropriate for a business data server, covering core operations without being too many or too few.

Completeness5/5

The tool set covers creation via crawling, retrieval, search, and category listing. Missing update/delete are likely intentional for a crawling-focused server, so no gaps.

Maintenance

ActivityInactive

ResponsivenessSyncing

Resources

Need Help?

Related Servers

Unclaimed servers have limited discoverability.

Looking for Admin?

If you are the server author, to access and configure the admin panel.

Related MCP Connectors

Google Maps Scraper
com.gmapsextractor
Live Google Maps business search, review, and photo data for AI agents over MCP.
Web Scraping Location Services
21
Nordax AI Entity Network A
ai.nordax
Search and verify 360K+ business entities with trust scores and W3C credentials.
Search Security
132
visibilityai
io.github.thinksuitesolution-coder
Verified Indian business data and AI-visibility reports for MCP-compatible AI agents.
Search Open Data Marketing
1
CoreLoop Business Network A
so.coreloop
Search real businesses, then read profiles, services and hours or contact them, in one endpoint.
Search Location Services
71

Related MCP Servers

Sylex Search
Search RAG Systems Agent Orchestration
MastadoonPrime
A
license
A
quality
F
maintenance
Universal search engine for AI agents. Discover products, services, and businesses across every category. 10 MCP tools, zero LLM calls, millisecond responses.
Updated 4 months ago (2026-04-24 21:29 UTC)
11
4
AGPL 3.0
AI List My Business
Location Services Real Estate Search
mutamiri-sudo
A
license
A
quality
B
maintenance
Country-agnostic MCP-callable directory for AI agents to find local SMBs — realtors, insurance agents, medical practitioners — by category, location, or natural-language query. Returns business catalog data and UTM-tagged booking URLs (zero PII).
Updated 3 months ago (2026-06-12 02:55 UTC)
5
MIT
agentweb-mcp
Search Open Data Location Services
zerabic
A
license
A
quality
D
maintenance
Enables agents to search, retrieve, and contribute business data from a directory of 11M+ businesses across 195 countries, returning markdown prose by default.
Updated 5 months ago (2026-04-11 09:05 UTC)
22
115
3
MIT
AgentRank MCP
Search Open Data
saviodamato
A
license
A
quality
C
maintenance
Provides AI agents with access to real, verifiable businesses with provenance and source URLs, enabling natural-language business search and profile retrieval.
Updated 2 months ago (2026-07-10 04:46 UTC)
2
MIT

Latest Blog Posts

Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)
By Om-Shree-0709 on July 25, 2026.
mcp
Agent Identity
OAuth 2.1
Your AI Chatbot Just Exposed Your CEO's Salary to an Intern
By Om-Shree-0709 on July 2, 2026.
Agent Identity
MCP Security
OAuth Delegation
Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)
By Om-Shree-0709 on June 30, 2026.
Agentic Ai
Prompt Injection
WebAssembly

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/getvexi/mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server

@getvexi/mcp

What is Vexi?

Prerequisites

Installation

Claude Desktop

Cursor

Other MCP clients

Available Tools

Example Usage

ABO Schema

Get your API Key

Links

License

Available Tools

Maintenance

Resources

Looking for Admin?

Related MCP Connectors

Related MCP Servers

Latest Blog Posts

MCP directory API