This server enables real-time contractor license verification across 45 US states by querying official state licensing board portals.
Verify a single license (clv_verify_license): Check a contractor's license validity, holder name, status, expiration date, and disciplinary history by providing a state code, license number, and optional trade type. Supports cache bypass for fresh data.
Batch verify up to 25 licenses (clv_batch_verify): Submit multiple license verification requests in one call, run in parallel, with partial failure handling so individual errors don't block the rest.
List supported states (clv_list_supported_states): Retrieve all supported US states along with their portal URLs, health status, and available trades (general, electrical, plumbing, HVAC, mechanical, residential, home inspection).
Search contractors by name (clv_search_by_name): Look up contractors by business or individual name within a state's licensing database, returning matching results with license numbers, status, and confidence scores (up to 50 results).
All tools are read-only and idempotent. Data is fetched live from official state portals and cached for 24 hours, with results available in either markdown or json format.
Real-time contractor license verification across all 50 US states + DC, plus 8 major-city contractor licensing portals (Chicago, NYC, Philadelphia, Detroit, Atlanta, Dallas, Las Vegas, Nashville). An MCP server that lets Claude Desktop, Claude Code, Cursor, Windsurf, and any MCP-compatible AI agent verify a contractor's license, status, expiration, and disciplinary history directly against licensing board portals.
Send {state, license_number, trade} — get back validity, licensee name, expiration date, status, and any disciplinary actions on file. Results are fetched live from official state portals (no stale nightly exports) and cached for 24 hours when active.
All 50 US states + DC + 8 major cities covered via official licensing board portals, not third-party data aggregators
Live lookups — each verification hits the authoritative portal, so expirations and disciplinary actions are as fresh as the board's own data
Batch verification — up to 25 licenses per call, run in parallel
Disciplinary history — returned when the portal exposes it
Backed by TradesAPI, a hosted HTTP API you can also hit directly
Related MCP server: LocalPro MCP Server
No install required. Add this to your Claude Desktop config:
macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
Windows: %APPDATA%\Claude\claude_desktop_config.json
{
"mcpServers": {
"tradesapi": {
"type": "streamable-http",
"url": "https://www.tradesapi.com/mcp",
"headers": {
"Authorization": "Bearer YOUR_API_KEY"
}
}
}
}Replace YOUR_API_KEY with the key from your dashboard and restart Claude Desktop.
If you prefer to run the MCP server locally via stdio:
{
"mcpServers": {
"tradesapi": {
"command": "npx",
"args": ["-y", "contractor-license-mcp-server"],
"env": {
"CLV_API_URL": "https://www.tradesapi.com",
"CLV_API_KEY": "your-api-key-here"
}
}
}
}Restart Claude Desktop after saving.
Go to www.tradesapi.com and click Sign up free
Enter your email — you'll get a magic link
Click the link and land on your dashboard, where your API key is waiting
New accounts start with 50 free verification credits, no credit card required. You can purchase additional credit packs from the dashboard when you need more.
npm install -g contractor-license-mcp-serververify_licenseVerify a single contractor license against the official state (or city) licensing portal.
Parameter | Required | Description |
| yes | Two-letter state code ( |
| no | Optional city slug to target a municipal portal: |
| yes | The license number to verify |
| no |
|
| no | Bypass the 24h cache and re-fetch from the portal |
| no |
|
Example result:
## License Verification: VALID
| Field | Value |
|------------|--------------------------|
| Name | ANDERSON, ORIN RAE |
| License # | TACLA00000103C |
| State | TX |
| Trade | hvac |
| Status | Active |
| Expiration | 05/12/2026 |batch_verifyVerify up to 25 licenses in a single call. Each verification runs independently — partial failures do not block the batch. Per-item city is supported.
Parameter | Required | Description |
| yes | Array of |
| no |
|
search_by_nameFuzzy-match contractors by business or individual name within a single state (or city) database. Costs 2 credits per call.
Parameter | Required | Description |
| yes | Two-letter state code |
| no | Optional city slug for municipal databases |
| yes | Business or individual name (case-insensitive, partial-match tolerant) |
| no | Trade filter |
| no | Max results (1–50, default 20) |
| no |
|
Not every state portal supports name search — call list_supported_states and check supports_name_search per jurisdiction first.
list_supported_statesList every supported jurisdiction with portal URLs, current health, available trades, and registered municipal scrapers nested under each state. Use this to discover what's reachable before constructing other tool calls.
Parameter | Required | Description |
| no |
|
All 50 US states + DC at the state level, plus 8 major-city contractor licensing portals (Chicago, NYC, Philadelphia, Detroit, Atlanta, Dallas, Las Vegas, Nashville).
Run list_supported_states from your agent for the live, fetched-fresh-each-call list of supported jurisdictions, available trades per jurisdiction, current portal health, and which states support name search. The MCP package no longer bundles a static state table — what comes back from list_supported_states is always current with prod.
You can also see the live state grid at www.tradesapi.com.
Variable | Required | Description |
| yes | API backend URL (use |
| yes | Your API key from the dashboard |
Each license verification consumes 1 credit, whether the result is fresh or cached. New accounts receive 50 free credits. Additional credit packs can be purchased from the dashboard at www.tradesapi.com.
git clone https://github.com/jackunderwood/Contractor-License-Verification.git
cd Contractor-License-Verification/mcp-server
npm install
npm run build
npm testMIT
Verify multiple contractor licenses in a single request (max 25). Returns results for each license, with partial failure handling — individual failures don't block others.
| Name | Required | Description | Default |
|---|---|---|---|
| licenses | Yes | Array of licenses to verify (1-25 items). | |
| response_format | No | Response format. | markdown |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true, destructiveHint=false, and idempotentHint=true, covering safety and idempotency. The description adds valuable behavioral context beyond annotations: the 25-item maximum limit and partial failure handling where individual failures don't block others. This provides important operational details not captured in annotations.
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 perfectly concise and front-loaded: two sentences that efficiently convey the core functionality (batch verification with limit) and key behavioral trait (partial failure handling). Every word earns its place with zero waste.
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?
Given the tool's moderate complexity (batch operation with partial failures), rich annotations (read-only, non-destructive, idempotent), and 100% schema coverage, the description is mostly complete. The main gap is lack of output schema, so the description doesn't explain return values or format details, but it does mention response format as a parameter.
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?
Schema description coverage is 100%, so parameters are fully documented in the schema. The description doesn't add any parameter-specific semantics beyond what's in the schema (e.g., it doesn't explain license number formats or trade types). Baseline 3 is appropriate when 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 purpose: 'Verify multiple contractor licenses in a single request' with a specific maximum (25). It distinguishes from sibling tools by emphasizing batch verification versus single verification (clv_verify_license) or search by name (clv_search_by_name).
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 context for when to use this tool (batch verification of up to 25 licenses) and mentions partial failure handling, which is useful guidance. However, it doesn't explicitly state when NOT to use it or directly compare it to alternatives like clv_verify_license for single licenses.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
List all US states currently supported for contractor license verification, including portal URLs, health status, and available trades.
| Name | Required | Description | Default |
|---|---|---|---|
| response_format | No | Response format. | markdown |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true, destructiveHint=false, and idempotentHint=true, covering safety and idempotency. The description adds valuable context about what data is returned (portal URLs, health status, trades) and the scope ('currently supported'), which helps the agent understand the tool's behavior beyond basic annotations.
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 single, efficient sentence that front-loads the core purpose and includes all necessary details without redundancy. Every word earns its place, making it appropriately sized for this simple tool.
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?
Given the tool's low complexity (1 optional parameter, no output schema), rich annotations (readOnly, non-destructive, idempotent), and clear purpose, the description is nearly complete. It could slightly improve by mentioning the default response format or when to choose markdown vs. json, but it adequately covers the tool's function and scope.
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?
Schema description coverage is 100%, with the single parameter 'response_format' fully documented in the schema (enum: markdown/json, default: markdown). The description doesn't add any parameter-specific information beyond what the schema provides, so the baseline score of 3 is appropriate.
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 specific action ('List all US states'), resource ('supported for contractor license verification'), and scope ('including portal URLs, health status, and available trades'). It distinguishes itself from sibling tools like clv_batch_verify, clv_search_by_name, and clv_verify_license by focusing on metadata listing rather than verification operations.
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 implies usage context by specifying what information is returned (portal URLs, health status, trades), suggesting it's for discovering available verification options. However, it doesn't explicitly state when to use this tool versus alternatives or mention any prerequisites or exclusions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Search for contractors by business or individual name in a state licensing database. Returns matching contractors with license numbers, status, and confidence scores.
| Name | Required | Description | Default |
|---|---|---|---|
| state | Yes | Two-letter US state code (e.g. 'CA', 'TX'). Use clv_list_supported_states to see available states. | |
| name | Yes | Business or individual name to search for in the state licensing database. | |
| trade | No | The trade/contractor type to filter by (e.g. 'General Contractor', 'Electrical'). Use clv_list_supported_states to see valid values per state. | general |
| limit | No | Maximum number of results to return. | |
| response_format | No | Response format. | markdown |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true, destructiveHint=false, and idempotentHint=true, indicating a safe, non-mutating, repeatable operation. The description adds valuable context beyond this by specifying the database source ('state licensing database') and detailing the return content ('matching contractors with license numbers, status, and confidence scores'), which helps the agent understand the tool's behavior and output format.
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 single, well-structured sentence that front-loads the core purpose and efficiently lists the return values. There is no wasted verbiage, and every part of the sentence contributes essential information, making it highly concise and clear.
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?
Given the tool's complexity (a search operation with 5 parameters), rich annotations (covering safety and idempotency), and 100% schema coverage, the description is largely complete. It specifies the database source and return content, though without an output schema, it could benefit from more detail on result structure (e.g., pagination or error handling). However, it provides sufficient context for effective use.
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?
Schema description coverage is 100%, so the schema fully documents all parameters. The description mentions 'business or individual name' and 'state licensing database', which aligns with the schema but doesn't add significant semantic detail beyond it. The baseline score of 3 is appropriate as the schema handles parameter documentation effectively.
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 specific action ('Search for contractors'), the resource ('in a state licensing database'), and the scope ('by business or individual name'). It distinguishes from siblings like clv_verify_license (which verifies specific licenses) and clv_list_supported_states (which lists states), making the purpose unambiguous and well-differentiated.
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 implies usage context by specifying 'in a state licensing database' and listing what it returns, but it doesn't explicitly state when to use this tool versus alternatives like clv_batch_verify or clv_verify_license. The input schema references clv_list_supported_states for valid values, providing some guidance, but the description itself lacks explicit when/when-not instructions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Verify a contractor's license by checking the state licensing board portal. Returns license validity, holder name, status, expiration, and any disciplinary actions.
| Name | Required | Description | Default |
|---|---|---|---|
| state | Yes | Two-letter US state code (e.g. 'CA', 'TX'). Use clv_list_supported_states to see available states. | |
| license_number | Yes | The contractor's license number as shown on their license card. Format varies by state. | |
| trade | No | The trade/contractor type (e.g. 'General Contractor', 'Electrical'). Use clv_list_supported_states to see valid values per state. | general |
| force_refresh | No | Bypass cache and fetch fresh data from the state portal. | |
| response_format | No | Response format. | markdown |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true, destructiveHint=false, and idempotentHint=true, indicating a safe, non-mutating, repeatable operation. The description adds valuable context beyond annotations: it specifies the data source ('state licensing board portal'), mentions caching behavior ('bypass cache' via force_refresh parameter), and lists the specific return fields (e.g., disciplinary actions), enhancing transparency about behavior and output without contradicting annotations.
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 single, dense sentence that front-loads the core action and resource, followed by a concise list of return values. Every word earns its place, with no redundancy or fluff, making it highly efficient and well-structured for quick comprehension by an AI agent.
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?
Given the tool's moderate complexity (5 parameters, no output schema) and rich annotations (read-only, non-destructive, idempotent), the description is largely complete: it covers purpose, data source, return fields, and caching behavior. However, it lacks details on error handling (e.g., invalid license numbers), rate limits, or authentication requirements, which could be useful for an agent despite the safe annotations. The absence of an output schema means the description must fully explain returns, which it does adequately but not exhaustively.
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?
Schema description coverage is 100%, with each parameter well-documented in the input schema (e.g., state codes, license number format, trade defaults, force_refresh purpose, response_format options). The description does not add significant semantic details beyond the schema, such as explaining parameter interactions or trade-specific nuances. With high schema coverage, the baseline score of 3 is appropriate, as the description relies on the schema for parameter semantics.
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 specific action ('verify a contractor's license'), resource ('contractor's license'), and scope ('by checking the state licensing board portal'), distinguishing it from sibling tools like clv_batch_verify (batch operations) and clv_search_by_name (search by name). It explicitly mentions the return data (validity, holder name, status, expiration, disciplinary actions), making the purpose highly specific and differentiated.
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 implies usage context (verifying individual licenses via state portals) and references sibling tools (clv_list_supported_states for valid inputs), providing clear guidance on prerequisites. However, it does not explicitly state when to use this tool versus alternatives like clv_batch_verify (e.g., for single vs. multiple licenses) or clv_search_by_name (e.g., when license number is unknown), missing explicit exclusions or comparisons.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Each tool has a clearly distinct purpose: batch verification, listing supported states, searching by name, and single license verification. There is no overlap in functionality, and an agent can easily differentiate between them based on their specific operations.
All tool names follow a consistent 'clv_' prefix and snake_case pattern (e.g., clv_batch_verify, clv_list_supported_states). This uniformity makes the tools predictable and easy to identify within the server's domain.
With 4 tools, the server is well-scoped for contractor license verification, covering key operations like verification, batch processing, state listing, and name searching. Each tool serves a necessary function without redundancy or bloat.
The tool set provides strong coverage for core verification workflows, including single and batch checks, state support info, and name searches. A minor gap might be the lack of tools for updating or managing license data, but for a verification-focused server, the surface is largely complete.
Unclaimed servers have limited discoverability.
If you are the server author, to access and configure the admin panel.
Real-time U.S. medical license verification across all 50 states + DC.
Free contractor-license checks from official state records; a no-match never proves unlicensed.
Search licensed US contractors by trade or location, fetch profiles and reviews, and submit leads.
Confirm a US business is real and find who controls it. 32.6M official registry records.
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/Noquarter6/contractor-license-mcp-server'
If you have feedback or need assistance with the MCP directory API, please join our Discord server
