LicenseGround
REMOTE · LICENSEGROUND.COM · 2 COMPONENTS · SCANNED OCT 6
Deterministic trade contractor license verification & compliance gating for autonomous AI agents.
Available components
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. How we score → Why this is hard to score →
Endpoint Security63
- The endpoint's TLS certificate is valid, in date, and uses a strong key. View diagnostics → Pass
- Authorisation not fully verified: no authorisation is required to call this server, and 6 tool(s) never declared a destructiveHint. The MCP spec treats an absent hint as destructive by default, so we cannot call this surface safe. See how to fix → View diagnostics → Unverified
- HTTPS is enforced; there's no plaintext access path. View diagnostics → Pass
- The HSTS (Strict-Transport-Security) header is present. View diagnostics → Pass
- DNSSEC check failed: this domain isn't protected by DNSSEC. See how to fix → View diagnostics → Fail
Transport & Reachability100
- Verified streamable-http transport via a live MCP handshake. View diagnostics → Pass
Schema Quality & AI Usability60
- AI-judged instruction clarity (good).Pass
- Context-footprint check failed: tool/resource definitions use about 1014 tokens (~169/item across 6 items; 6 tools + 0 resources), over budget; trim descriptions and params. See how to fix → Fail
- Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management10
- Stability observed for 3 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage71
- 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
- 0% of tool parameters carry a description.Fail
- Structured output schemas are declared (100% of tools); any adoption earns full credit.Pass
Tool Safety100
- No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
- We read all 6 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
- An AI judge read all 7 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
- Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass
How do I install the LicenseGround MCP server?
LicenseGround is a hosted endpoint at https://licenseground.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.
remote · licenseground.com
claude mcp add --transport http com-licenseground-licenseground 'https://licenseground.com/mcp'
{
"mcpServers": {
"com-licenseground-licenseground": {
"url": "https://licenseground.com/mcp"
}
}
} {
"servers": {
"com-licenseground-licenseground": {
"type": "http",
"url": "https://licenseground.com/mcp"
}
}
} [mcp_servers.com-licenseground-licenseground] url = "https://licenseground.com/mcp"
{
"$schema": "https://opencode.ai/config.json",
"mcp": {
"com-licenseground-licenseground": {
"type": "remote",
"url": "https://licenseground.com/mcp",
"enabled": true
}
}
} openclaw mcp add com-licenseground-licenseground --url 'https://licenseground.com/mcp' --transport streamable-http
mcp_servers:
com-licenseground-licenseground:
url: "https://licenseground.com/mcp" {
"McpServers": {
"com-licenseground-licenseground": {
"Transport": "http",
"Url": "https://licenseground.com/mcp"
}
}
} assistant mcp add com-licenseground-licenseground -t streamable-http -u 'https://licenseground.com/mcp'
{
"mcpServers": {
"com-licenseground-licenseground": {
"type": "http",
"url": "https://licenseground.com/mcp"
}
}
} The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.
Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.
- 3 Oct 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 3 to 7. That category is still filling its 30-day observation window: 1 days of observed history at the previous scan, 2 at this one. The score rises as the window fills, whether or not the server changes.
- 2 Oct 26 0
- Stability: unverified → 0.03 ▲ functional
- 1 Oct 26 +27
- Injection markers: unverified → pass ▲ security
- First check of Judged manipulation: pass security
- Authorization: Authorisation not fully verified: no authorisation is required to call this server, and 6 tool(s) never declared a destructiveHint. The MCP spec treats an absent hint as destructive by default, so we cannot call this surface safe. security
- Tool coverage: unverified → 100 ▲ functional
- MCP protocol: unverified → pass ▲ functional
- First check of Tool coverage: 0 functional
- First check of Schema quality: fail functional
- First check of Destructive annotations: pass functional
- First check of Schema quality: fail functional
- First check of Schema quality: good functional
- First check of Tool coverage: 100 functional
- 30 Sept 26 35
First indexed and scored.
Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.
Captured 5 Oct 2026 · Probed https://licenseground.com/mcp/ · Declared URL https://licenseground.com/mcp
TLS valid
Negotiated TLS 1.3 with TLS_AES_128_GCM_SHA256 .
| Subject | Issuer | Valid from | Valid until | Key | Signature | Serial |
|---|---|---|---|---|---|---|
| CN=licenseground.com | CN=YE1,O=Let's Encrypt,C=US | 29 Sept 2026 | 28 Dec 2026 | ECDSA 256 | ECDSA-SHA384 | 505d239789ec59164f600ccb4c5ab4a4575 |
| SANs: *.licenseground.com, licenseground.com | ||||||
| CN=YE1,O=Let's Encrypt,C=US (CA) | CN=Root YE,O=ISRG,C=US | 3 Sept 2025 | 2 Sept 2028 | ECDSA 384 | ECDSA-SHA384 | 5ddd70dd31f801c85c186a7a04b80afe |
| CN=Root YE,O=ISRG,C=US (CA) | CN=ISRG Root X2,O=Internet Security Research Group,C=US | 13 May 2026 | 2 Sept 2032 | ECDSA 384 | ECDSA-SHA384 | 872165fc34b6e5fba8add5b3705fb53a |
| CN=ISRG Root X2,O=Internet Security Research Group,C=US (CA) | CN=ISRG Root X1,O=Internet Security Research Group,C=US | 13 May 2026 | 2 Sept 2032 | ECDSA 384 | SHA256-RSA | 6c8f1dc727c7117f7baf853ac980f9cd |
Background: What to check on a remote MCP endpoint →
DNSSEC insecure
Validation of licenseground.com. — Not signed
| Zone | DS | Keys | Algorithms | Outcome |
|---|---|---|---|---|
| . | trust_anchor | 20326, 38696 | 8, 8 | Verified |
| com. | present | 19718 | 13 | Verified |
| licenseground.com. | absent | Unsigned (proven) parent-signed NSEC/NSEC3 proves an unsigned delegation |
Authentication No authorisation required
The endpoint answered without asking for a token. Anyone who knows the URL can reach it.
| Result | No authorisation required |
|---|---|
| HTTP status | 200 |
| Header | Value |
|---|---|
| strict-transport-security | max-age=31536000; includeSubDomains; preload |
| x-content-type-options | nosniff |
| x-frame-options | SAMEORIGIN |
| referrer-policy | strict-origin-when-cross-origin |
| permissions-policy | camera=(), microphone=(), geolocation=() |
Background: How OAuth 2.1 works in the 2026 MCP spec →
Transports 3 probes
| Transport | URL | Outcome | Status | Location |
|---|---|---|---|---|
| streamable-http | https://licenseground.com/mcp | Redirected | 307 | https://licenseground.com/mcp/ |
| streamable-http · followed | https://licenseground.com/mcp/ | Verified | 200 | |
| http (plaintext) | http://licenseground.com/mcp | HTTPS enforced | 301 | https://licenseground.com/mcp |
The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →
audit_osha_safety ~68
Audit contractor worksite safety history against the OSHA inspection and enforcement database. Evaluates willful safety violations, repeat fall protection citations, and cumulative penalties. Args: entity_name: Official business or entity name to evaluate.
| Name | Type | Req | Description |
|---|---|---|---|
| entity_name | string | yes | – |
| Name | Type | Req | Description |
|---|---|---|---|
| result | object | yes | – |
No examples provided.
check_compliance_risk ~319
Perform an automated compliance and liability risk assessment for autonomous onboarding, hiring, or payments. Args: state: Two-letter US state code ('CA', 'FL', or 'TX'). Required. entity_name: Company name or DBA to assess. license_number: State license number to assess. trade: Trade category: 'roofing', 'hvac', 'electrical', 'plumbing', 'general_contractor', or 'any'. require_workers_comp: If true, fails compliance if no verified workers' comp policy is active on file. require_surety_bond: If true, fails compliance if contractor bond is inactive or missing. max_disciplinary_actions: Maximum allowed board citations or disciplinary orders (default 0). min_confidence_score: Minimum entity name match confidence threshold (0.0 to 1.0, default 0.85). Returns: JSON with 'can_hire' boolean, 'risk_level' ('LOW', 'MEDIUM', 'HIGH', 'CRITICAL'), 'risk_score' (0.0 to 100.0), specific 'flags', and the full underlying verification result.
| Name | Type | Req | Description |
|---|---|---|---|
| entity_name | – | – | – |
| license_number | – | – | – |
| max_disciplinary_actions | integer | – | – |
| min_confidence_score | number | – | – |
| require_surety_bond | boolean | – | – |
| require_workers_comp | boolean | – | – |
| state | string | yes | – |
| trade | string | – | – |
| Name | Type | Req | Description |
|---|---|---|---|
| result | object | yes | – |
No examples provided.
check_federal_debarment ~83
Check if a contractor is actively debarred or suspended on the federal SAM.gov Excluded Parties List System (EPLS). Crucial for public contracts, infrastructure, and enterprise B2B compliance. Args: entity_name: Official business or entity name to evaluate against federal sanctions.
| Name | Type | Req | Description |
|---|---|---|---|
| entity_name | string | yes | – |
| Name | Type | Req | Description |
|---|---|---|---|
| result | object | yes | – |
No examples provided.
get_registry_status ~62
Check the system health, cache performance statistics, and multi-state registry connectivity. Returns: JSON object with cache hit/miss counts, total records cached, and connector status for CA, FL, TX, NY, MA, IL, AZ.
Input schema present but exposes no named parameters.
| Name | Type | Req | Description |
|---|---|---|---|
| result | object | yes | – |
No examples provided.
search_contractors ~157
Discover active, verified trade contractors in California, Florida, or Texas by trade classification and location. Args: state: Two-letter US state code ('CA', 'FL', or 'TX'). Required. trade: Trade category ('roofing', 'hvac', 'electrical', 'plumbing', 'general_contractor'). Required. city: Optional city to filter contractors by location. limit: Maximum number of contractors to return (1 to 50, default 10). Returns: JSON list of verified contractors with active licenses, phone numbers, and addresses.
| Name | Type | Req | Description |
|---|---|---|---|
| city | – | – | – |
| limit | integer | – | – |
| state | string | yes | – |
| trade | string | yes | – |
| Name | Type | Req | Description |
|---|---|---|---|
| result | object | yes | – |
No examples provided.
verify_license ~236
Verify an entity's trade contractor license against the official state licensing board (CSLB, DBPR, or TDLR). Args: state: Two-letter US state code ('CA', 'FL', or 'TX'). Required. entity_name: The company name, DBA, or contractor name to verify (e.g. 'Apex Roofing LLC'). license_number: The official state license or certificate ID (e.g. '1058291', 'CCC1330999', 'TACLA29188C'). trade: Trade category: 'roofing', 'hvac', 'electrical', 'plumbing', 'general_contractor', or 'any'. Default is 'any'. city: Optional city to filter geographic disambiguation. Returns: Deterministic, machine-actionable JSON containing verification status, canonical name, active standing, disciplinary action count, workers' compensation status, bond status, and confidence score.
| Name | Type | Req | Description |
|---|---|---|---|
| city | – | – | – |
| entity_name | – | – | – |
| license_number | – | – | – |
| state | string | yes | – |
| trade | string | – | – |
| Name | Type | Req | Description |
|---|---|---|---|
| result | object | yes | – |
No examples provided.
What is the LicenseGround MCP server?
LicenseGround is an MCP server listed in the public MCP registry as com.licenseground/licenseground. Deterministic trade contractor license verification & compliance gating for autonomous AI agents. This page covers its hosted endpoint (https://licenseground.com/mcp).
Is the LicenseGround MCP server safe to use?
LicenseGround scores 63 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.
What tools does the LicenseGround MCP server expose?
LicenseGround exposes 6 tools: verify_license, check_compliance_risk, search_contractors, check_federal_debarment, audit_osha_safety, get_registry_status. Their descriptions and schemas cost roughly 925 tokens of context every time the server is loaded.
Does the LicenseGround MCP server require authentication?
No. We connected to LicenseGround without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.
Is the LicenseGround MCP server still maintained?
LicenseGround is still listed as active in the MCP registry. We last reached this channel on 4 October 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.