US Employment Grounding Data
The tool
Ground enterprise agents in verifiable BLS employment figures — unemployment, payrolls and sector data since 1948 — so economic answers cite official statistics.
Once your client is connected to the VerveContext MCP server, this appears in its tool list as USEmploymentGroundingData. It is read-only and open-world: it fetches, it never mutates anything on your side, so most clients will call it without asking you to confirm.
{
"name": "USEmploymentGroundingData",
"arguments": {}
}Connecting
One server URL covers every source in the catalog, including this one. Authorization is OAuth — the client opens a browser once and there is no key to paste into a config file.
{
"mcpServers": {
"vervecontext": {
"url": "https://api.vervecontext.com/v1/mcp"
}
}
}https://api.vervecontext.com/v1/mcpPer-client setup — Claude Desktop, Cursor, VS Code, ChatGPT — is on the MCP setup page.
Arguments
These are the properties on the tool's inputSchema, so a well-behaved client validates them before the call is made.
| Argument | Type | Example | Description |
|---|---|---|---|
datePremium | string | 2023-06 | Optional date in YYYY-MM format for historical lookup. Omit for current data. |
What the model gets back
The result carries a structuredContent object matching the tool's declared outputSchema, so a client can read fields without parsing prose. status is "ok" on success and error is null; a null field means the value wasn't available for that input, not that the call failed.
{
"status": "ok",
"error": null,
"data": {
"yearMonth": "2024-01",
"year": 2024,
"month": 1,
"jobsChangeDirection": "growth",
"summary": {
"unemploymentRate": 3.7,
"laborForceParticipation": 62.5,
"totalEmployed": 161152000,
"totalUnemployed": 6124000,
"laborForce": 167276000,
"jobsChange": 353000
},
"nonfarmPayrolls": {
"total": 157245000,
"private": 133567000
},
"bySector": {
"mining": 645000,
"construction": 8123000,
"manufacturing": 12987000,
"tradeTransportUtilities": 29456000,
"information": 2987000,
"financialActivities": 9234000,
"professionalBusiness": 22876000,
"educationHealth": 25678000,
"leisureHospitality": 16789000,
"otherServices": 5892000,
"government": 23678000
},
"topSector": "Trade, Transport & Utilities",
"formatted": {
"totalEmployed": "161.15M",
"totalUnemployed": "6.12M",
"laborForce": "167.28M",
"jobsChange": "+353.0K",
"nonfarmPayrolls": "157.25M"
}
}
}Fields
| Field | Type | Example | Description |
|---|---|---|---|
yearMonth | string | Report date in YYYY-MM format (e.g. 2024-01) | |
year | number | Year of the employment report | |
month | number | Month of the employment report (1-12) | |
jobsChangeDirection | string | Direction of job change: 'growth', 'decline', or 'unchanged' | |
summary | object | ||
└ summary.unemploymentRate | number | National unemployment rate as percentage | |
└ summary.laborForceParticipation | number | Labor force participation rate as percentage | |
└ summary.totalEmployedPremium | number | Total number of employed persons in millions | |
└ summary.totalUnemployedPremium | number | Total number of unemployed persons in millions | |
└ summary.laborForcePremium | number | Total labor force size in millions | |
└ summary.jobsChange | number | Change in jobs for the month in thousands | |
nonfarmPayrolls | object | ||
└ nonfarmPayrolls.totalPremium | number | Total nonfarm payroll employment in millions | |
└ nonfarmPayrolls.privatePremium | number | Private nonfarm payroll employment in millions | |
bySector | object | ||
└ bySector.miningPremium | number | Mining sector employment in thousands | |
└ bySector.constructionPremium | number | Construction sector employment in thousands | |
└ bySector.manufacturingPremium | number | Manufacturing sector employment in thousands | |
└ bySector.tradeTransportUtilitiesPremium | number | Trade, Transport & Utilities sector employment | |
└ bySector.informationPremium | number | Information sector employment in thousands | |
└ bySector.financialActivitiesPremium | number | Financial Activities sector employment in thousands | |
└ bySector.professionalBusinessPremium | number | Professional & Business Services sector employment | |
└ bySector.educationHealthPremium | number | Education & Health Services sector employment | |
└ bySector.leisureHospitalityPremium | number | Leisure & Hospitality sector employment in thousands | |
└ bySector.otherServicesPremium | number | Other Services sector employment in thousands | |
└ bySector.governmentPremium | number | Government sector employment in thousands | |
topSectorPremium | string | Sector with highest employment count | |
formatted | object | ||
└ formatted.totalEmployedPremium | string | Human-readable format of total employed (e.g 161.15M) | |
└ formatted.totalUnemployedPremium | string | Human-readable format of total unemployed (e.g 6.12M) | |
└ formatted.laborForcePremium | string | Human-readable format of labor force size | |
└ formatted.jobsChangePremium | string | Human-readable format of jobs change (e.g +353.0K) | |
└ formatted.nonfarmPayrollsPremium | string | Human-readable format of nonfarm payrolls |
Why ground on it
A model can produce something that looks like this answer from its training data, and be confidently out of date or simply wrong. This source returns the current value with a shape you can check, which is the difference between an answer you can cite and one you have to hedge.
Point an evaluation at yearMonth: it is the field most worth pinning a claim to, and it is either present and current or absent — never plausibly invented.
Failure modes
Errors come back as tool errors with a sentence the model can act on, not a bare status code.
| Status | What it means |
|---|---|
400 / 422 | The arguments didn't validate. The message names the offending one. |
401 | The OAuth session is invalid or expired — reconnect the server. |
403 | Out of credits. Not a bad key — the month's allowance is spent. |
404 | This source isn't part of VerveContext. Check the catalog. |
429 | Brief rate limit. Retrying after a moment succeeds. |
Other ways to use US Employment Grounding Data
Set up US Employment Grounding Data on VerveContext, or reach the same source a different way. Your VerveContext account and credits work on all of them — one key, one balance.
Frequently asked questions
Do I have to tell the agent to use USEmploymentGroundingData?
No. The tool's name and description are in the model's context once the server is connected, so it selects the tool when the question calls for it. Naming it explicitly works too and is useful when you want to force the call.
Does connecting the server expose every tool at once?
Yes — one connection lists the whole VerveContext catalog. Clients with a tool budget can usually filter the list; the credit cost is per call, so an unused tool costs nothing.
What does a call cost?
1 credit each time the tool actually runs. A model that reasons about the tool without calling it costs nothing.
Is there a REST version of this?
Yes — the same source is available as a plain HTTPS endpoint on APIVerve, linked above. Same data, same credits, same account.