usaspending-mcp
About
mcp server to interact with usaspending.gov api
Details
- Author
- flothjl
- Downloads
- 364
- Categories
- Other
Jump to
- Provides four tools to query USAspending.gov data
- GetSpendingAwardsByAgencyId searches awards by agency and year
- GetAwardInfoByAwardId retrieves details for a specific award
- SearchByKeywords performs broad keyword searches for a year
- GetAgencies lists all agencies and their IDs for other calls
- Runs as a stdio MCP server via uvx
Configure usaspending-mcp as a stdio extension in Goose using the provided YAML block, specifying the command uvx with --from git+https://github.com/flothjl/usaspending-mcp@main usaspending-mcp and setting the model to gpt-4o-mini with OpenAI as the provider.
usaspending-mcp
usaspending-mcp is an MCP (Modular Computing Platform) server designed
to facilitate AI agents in accessing and interacting with the
USAspending.gov API. This project provides tools,
endpoints, and data processing utilities to streamline the retrieval
and analysis of U.S. government spending data.
Tools
- GetSpendingAwardsByAgencyId
- Search for awards for a given agency id for a given year
- GetAwardInfoByAwardId
- Get information about a given award. Requires the generated unique award ID.
- SearchByKeywords
- Broad search for given keywords for a given year.
- GetAgencies
- Get a list of all agencies and associated data needed for other calls (i.e. agency id)
Configuration
Goose
extensions:
usaspending-mcp:
args:
- --from
- git+https://github.com/flothjl/usaspending-mcp@main
- usaspending-mcp
cmd: uvx
enabled: true
envs: {}
name: usaspending
type: stdio
GOOSE_MODEL: gpt-4o-mini
GOOSE_PROVIDER: openai
Sign in to leave a review
Use Google, GitHub, or an email account so ratings stay tied to real people.
No reviews posted yet.
