Datasource wholesale background check API docs. Sandbox tools: sandbox.datasourcecorp.app/mcp
Maintain this server? Claim it
Call this server's tools from your browser. Nothing to install.
Requests go through mcptry because browsers can't call most MCP servers directly. Header values are sent to the server for that request only and are never stored or logged.
Tool list from our last check. Connect live to refresh it.
One error code from the error catalog: its HTTP status, what it means, what to do, and whether a retry is safe. Pass the `code` from a problem details body (e.g. client_not_found).
The error `code`, e.g. client_not_found.
Pick your client. Values in capitals, like YOUR_TOKEN, are yours to fill in.
Run in a terminal
claude mcp add --transport http wholesale https://api.datasourcecorp.app/mcp
One error code from the error catalog: its HTTP status, what it means, what to do, and whether a retry is safe. Pass the `code` from a problem details body (e.g. client_not_found).
| Argument | Type | Description |
|---|---|---|
| code* | string | The error `code`, e.g. client_not_found. |
{
"type": "object",
"required": [
"code"
],
"properties": {
"code": {
"type": "string",
"maxLength": 200,
"description": "The error `code`, e.g. client_not_found."
}
},
"additionalProperties": false
}One section of the integration guide, by heading or number (e.g. 'Webhooks', '9', 'Testing in the sandbox'). Without a match, lists the sections.
| Argument | Type | Description |
|---|---|---|
| heading* | string | The section's heading or number, e.g. 'Webhooks' or '9'. |
{
"type": "object",
"required": [
"heading"
],
"properties": {
"heading": {
"type": "string",
"maxLength": 200,
"description": "The section's heading or number, e.g. 'Webhooks' or '9'."
}
},
"additionalProperties": false
}Full details of one API operation: description, parameters, request body fields, every response and JSON examples (the same text as its section of /llms-full.txt). Pass its operationId from list_operations (e.g. GetCheck), or 'METHOD /path'.
| Argument | Type | Description |
|---|---|---|
| operationId* | string | The operationId (from list_operations), or 'METHOD /path'. |
{
"type": "object",
"required": [
"operationId"
],
"properties": {
"operationId": {
"type": "string",
"maxLength": 200,
"description": "The operationId (from list_operations), or 'METHOD /path'."
}
},
"additionalProperties": false
}One webhook event: when it is sent, its payload fields and an example (e.g. check.updated). Signature, retry and ordering rules are in the guide's webhooks section.
| Argument | Type | Description |
|---|---|---|
| event* | string | The event name, e.g. check.updated. |
{
"type": "object",
"required": [
"event"
],
"properties": {
"event": {
"type": "string",
"maxLength": 200,
"description": "The event name, e.g. check.updated."
}
},
"additionalProperties": false
}Lists every operation of the API (operationId, HTTP method, path, summary), grouped by tag. Then call get_operation for one operation's full details.
No arguments.
{
"type": "object",
"properties": {},
"additionalProperties": false
}Lists every webhook event we send (event name and summary). Then call get_webhook for its fields and an example payload.
No arguments.
{
"type": "object",
"properties": {},
"additionalProperties": false
}Searches the integration guide, error catalog, changelog, operations and webhooks. Returns the best-matching sections with a snippet and a link; read one in full with get_guide_section, get_error, get_operation or get_webhook.
| Argument | Type | Description |
|---|---|---|
| limit | integer | Most sections to return (default 8). |
| query* | string | Words to look for, e.g. 'webhook signature' or 'duplicate check'. |
{
"type": "object",
"required": [
"query"
],
"properties": {
"limit": {
"type": "integer",
"maximum": 20,
"minimum": 1,
"description": "Most sections to return (default 8)."
},
"query": {
"type": "string",
"maxLength": 200,
"description": "Words to look for, e.g. 'webhook signature' or 'duplicate check'."
}
},
"additionalProperties": false
}We read every tool's name, description and inputs the way the model will, looking for instructions hidden from you. A clean result means no warning signs, not a guarantee. Scanned Nov 14, 2026.