Sourcelane

USAspending Federal Contracts & Grants Scraper

Finance & Company Data

Operated by Sourcelane✓ verified

A scraper for USAspending.gov that extracts federal contract and grant awards by recipient, awarding agency, or NAICS industry code; it returns award identifiers and links, recipient names and locations, award amounts, awarding agency and sub-agency, award start/end dates, short award descriptions, NAICS codes and descriptions, and other award metadata. The connector supports searching across contracts, grants, or both, filtering by recipient/agency/industry and by date range (historical coverage back to 2007-10-01), and it paginates to retrieve large result sets.

Verified Sep 28, 12:10 AM

$0.01

per result

Up to 100 per call. Only pay for results returned; failed calls are refunded.

What people use it for

Trust & reliability

7d uptime trend
WindowUptimeSuccess ratep50p95Calls
24h————0
7d————0
30d————0

Calling contract

Call it through Sourcelane's gateway or MCP server. We run the connector, apply your agent's spend guardrails, and bill only the results returned.

Call it via Sourcelane

curl -X POST https://cool-puffin-608.convex.site/v1/call \
  -H "Authorization: Bearer sl_live_your_agent_key" \
  -H "Content-Type: application/json" \
  -d '{"listing":"usaspending-federal-contracts-scraper","params":{"recipientName":"Boeing","maxItems":5},"maxResults":10}'

Request params

FieldTypeRequiredDescription
recipientNamestringoptionalCompany or organization name to search for (partial match), e.g. 'Boeing'. Leave blank to browse all recipients matching the other filters.
naicsCodestringoptionalOptional. Filter to a specific 6-digit NAICS industry code, e.g. '336411' for Aircraft Manufacturing.
agencyNamestringoptionalOptional. Filter to a top-tier federal agency by exact name, e.g. 'Department of Defense'.
awardTypestringoptionalSearch federal contracts, grants, or both. Contracts and grants use different USAspending record types, so 'Both' runs two passes.
startDatestringoptionalEarliest award start date to include, in YYYY-MM-DD format. USAspending's search API only covers data back to 2007-10-01; earlier dates are clamped to that floor. Leave blank for the earliest available date.
endDatestringoptionalLatest award start date to include, in YYYY-MM-DD format. Defaults to today.
maxItemsintegeroptionalMaximum number of award records to push. Set 0 for unlimited (the run paginates until every match is fetched or the run times out). Capped at 100 per call.
pageIdstringoptionalOptional. Paste NEXT_PAGE_ID from the previous run's Key-value store to continue where that run stopped.

Each result contains

FieldTypeDescription
awardTypestringAward Type
awardIdstringAward Id
recipientNamestringRecipient Name
awardAmountnumberAward Amount
awardingAgencystringAwarding Agency
awardingSubAgencystringAwarding Sub Agency
startDatestringStart Date
endDatestringEnd Date
descriptionstringDescription
naicsCodestringNaics Code
naicsDescriptionstringNaics Description
recipientStatestringRecipient State
recipientCitystring—
recipientAddressstring—
recipientZipstring—
usaspendingUrlstring—

Use USAspending Federal Contracts & Grants Scraper from Claude, ChatGPT or Cursor

Pick your tool and connect in under a minute. Then just ask — for example: “Which AI companies filed a Form D in the last two weeks, and how much did they raise?”

Connect Claude

Web, desktop and mobile. Paste one URL.

  1. 1Copy your personal connector URL
  2. 2In Claude open Settings → Connectors → Add custom connector
  3. 3Paste the URL and click Add — done
Manual setup (config files, REST, Python) +

Claude Code

Adds the Sourcelane MCP server with your key as a header.

terminal
claude mcp add --transport http sourcelane https://cool-puffin-608.convex.site/mcp \
  --header "Authorization: Bearer sl_live_your_agent_key"

Claude Desktop (config file)

Alternative to the connector URL: add to claude_desktop_config.json, then restart Claude.

claude_desktop_config.json
{
  "mcpServers": {
    "sourcelane": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-remote",
        "https://cool-puffin-608.convex.site/mcp",
        "--header",
        "Authorization:${AUTH_HEADER}"
      ],
      "env": {
        "AUTH_HEADER": "Bearer sl_live_your_agent_key"
      }
    }
  }
}

Cursor & Windsurf

Add to ~/.cursor/mcp.json (or Windsurf's mcp_config.json).

mcp.json
{
  "mcpServers": {
    "sourcelane": {
      "url": "https://cool-puffin-608.convex.site/mcp",
      "headers": {
        "Authorization": "Bearer sl_live_your_agent_key"
      }
    }
  }
}

VS Code

Save as .vscode/mcp.json. VS Code prompts for your key once.

.vscode/mcp.json
{
  "servers": {
    "sourcelane": {
      "type": "http",
      "url": "https://cool-puffin-608.convex.site/mcp",
      "headers": {
        "Authorization": "Bearer ${input:sourcelane-key}"
      }
    }
  },
  "inputs": [
    {
      "type": "promptString",
      "id": "sourcelane-key",
      "description": "Sourcelane agent key",
      "password": true
    }
  ]
}

ChatGPT Custom GPT (Actions)

Create a GPT → Actions → Import from URL, then Authentication: API Key, Bearer.

OpenAPI schema URL
https://sourcelane-amber.vercel.app/openapi.json

REST

One POST. Pass maxResults to cap cost.

curl
curl -X POST https://cool-puffin-608.convex.site/v1/call \
  -H "Authorization: Bearer sl_live_your_agent_key" \
  -H "Content-Type: application/json" \
  -d '{"listing":"usaspending-federal-contracts-scraper","params":{"recipientName":"Boeing","maxItems":5},"maxResults":10}'

Python, LangChain, CrewAI, OpenAI Agents SDK…

Wrap the REST call as a tool, or point an MCP client at the endpoint.

python
import requests

res = requests.post(
    "https://cool-puffin-608.convex.site/v1/call",
    headers={"Authorization": "Bearer sl_live_your_agent_key"},
    json={
        "listing": "usaspending-federal-contracts-scraper",
        "params": {"recipientName":"Boeing","maxItems":5},
        "maxResults": 10,
    },
    timeout=300,
)
body = res.json()
print(body["receipt"]["chargedMicros"], "micro-USD for", body["receipt"]["results"], "results")
print(body["data"])

Reviews

—

0 reviews

5
0
4
0
3
0
2
0
1
0

Leave a review

Loading reviews…