grantconnect-au
Enables searching and analyzing Australian Commonwealth grant opportunities and awarded grants from grants.gov.au, including recipient lookups and coverage checks.
README
@pipeworx/grantconnect-au
GrantConnect (Australia) MCP — Commonwealth grant opportunities and grants awarded, from grants.gov.au. Keyless (Pipeworx-hosted).
Tools
au_grants_search(query, agency, category, recipient_state, selection_process, min_value, max_value, awarded_from, awarded_to, sort, order, limit, offset)— awarded grants. Free text is a case-insensitive substring acrossrecipient_name,purpose,grant_program,grant_activity; multiple words are AND-ed. Newest first by default,sort: "value"ranks by AUD.au_grant_award(ga_id)— one award in full, with the linked grant opportunity inlined when the award records ago_id. GrantConnect publishes awards and opportunities as separate reports; this is the join.au_grants_by_recipient(recipient_name | abn, awarded_from, awarded_to, limit, offset)— every award to one organisation plus the funding total: total AUD, award count, first/last award date, per-agency breakdown. ABN is accepted spaced (48 008 389 151) or unspaced.au_grant_opportunities_open(query, agency, category, closing_within_days, limit, offset)— opportunities whoseclose_dateis still in the future, soonest first, withdays_until_closecomputed at request time.au_grants_top_recipients(agency, category, recipient_state, awarded_from, awarded_to, limit, scan_limit)— recipients ranked by total AUD. Reportsrows_scanned,total_matching_awardsandranking_covers_all_matching_awards.grantconnect_coverage()— which reports/date windows are actually loaded, row counts, min/max dates, and any ingest windows inerror.
Auth
None. Pipeworx hosts the data; the gateway injects _supabaseUrl / _supabaseKey.
Data sources
- GrantConnect — https://www.grants.gov.au (Commonwealth Grants Rules and Guidelines reporting: grant opportunities + grants awarded)
- Mirrored into Pipeworx Postgres by
workers/grantconnect-ingest; queried here through PostgREST (au_grant_awards,au_grant_opportunities,grantconnect_ingest_state)
Gotchas
GrantConnect has no JSON API — it publishes dated report downloads only, which is why this pack reads a Pipeworx mirror rather than the site, and why grantconnect_coverage matters: while the ingest backfills, a year you ask about may simply not be loaded yet, and every tool returns { found: false, reason, hint } rather than an empty-looking answer. Recipient identity is messy at source: names are the legal entity as the recipient typed it (so one organisation appears under several spellings), and recipient_abn is published spaced and is blank on some rows — au_grants_by_recipient normalises the ABN and reports matched_recipient_names so you can see what was actually aggregated. is_aggregate rows bundle many small grants into one record (aggregate_number says how many), so award counts are not payment counts. Because PostgREST aggregate functions are disabled on this project, au_grants_top_recipients ranks from a bounded scan taken largest-award-first and states rows_scanned versus total_matching_awards — treat a ranking with ranking_covers_all_matching_awards: false as a ranking of the big-ticket end, not the whole table. Finally, close_date on opportunities carries a real time of day and addenda can move it: addenda_count > 0 means the notice was amended after publication.
Quick Start
Add to your MCP client (Claude Desktop, Cursor, Windsurf, etc.):
{
"mcpServers": {
"grantconnect-au": {
"url": "https://gateway.pipeworx.io/grantconnect-au/mcp"
}
}
}
Or connect to the full Pipeworx gateway for access to all 1394+ data sources:
{
"mcpServers": {
"pipeworx": {
"url": "https://gateway.pipeworx.io/mcp"
}
}
}
Using with ask_pipeworx
Instead of calling tools directly, you can ask questions in plain English:
ask_pipeworx({ question: "your question about GrantConnect (Australia) data" })
The gateway picks the right tool and fills the arguments automatically.
More
License
MIT
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。