OpenGrants OS
An MCP server for discovering, matching, drafting, and managing grants and public goods funding for open-source AI projects. It integrates Grants.gov, NSF Awards, GitHub Sponsors, Open Collective, Gitcoin, and other sources to provide grounded proposals and autonomous funding lifecycle management.
README
OpenGOS
Open-source Autonomous Agentic AI MCP Server for grants, public-goods funding, and open-source sustainability.
Eliminate the discovery tax. Treat traditional grants and donations / sponsorships / quadratic funding as equal first-class citizens so open-source projects can compete on a level playing field.
Try it now
Launch the interactive shell →
Discover · Constellation (3D knowledge graph) · Pipeline · Draft · Console · Profile — one HTML file. No install required.
Source: opengos.html
Catalog baseline: August 2026 (illustrative — always verify with the funder).
Why OpenGOS?
- A first-class MCP Server any agent (Claude, Cursor, custom agents) can call
- Discovery → ranking → drafting → evaluation with a declared open-source bias
- Public-goods funding (sponsors, collectives, quadratic) as first-class citizens
- Apache 2.0, self-hostable, provenance-first
Features (v0.3)
| Capability | Status |
|---|---|
| Live Grants.gov search | ✅ |
| NSF Awards search | ✅ |
| Public-goods / donation sources | ✅ |
| Profile Steward | ✅ |
| Grounded proposal drafting | ✅ |
| Continuous ingestion + evaluation harness | ✅ |
| Ranking with declared open-source bias | ✅ |
| Interactive shell + 3D Constellation | ✅ |
Quick Start (MCP Server)
git clone https://github.com/ANAMIZED/OpenGOS.git
cd OpenGOS
pip install -e .
opengos
MCP Client Config
{
"mcpServers": {
"opengos": {
"command": "opengos",
"args": []
}
}
}
Or via module:
{
"mcpServers": {
"opengos": {
"command": "python",
"args": ["-m", "opengrants"],
"cwd": "/absolute/path/to/OpenGOS"
}
}
}
MCP Tools
| Tool | Description |
|---|---|
search_grants |
Live Grants.gov keyword search with provenance |
get_grant_details |
Detail view for a specific opportunity |
list_open_source_relevant_grants |
Open-source biased discovery |
list_public_goods_funding |
Donations, sponsorships, quadratic & open-source funds |
search_nsf_awards |
NSF Awards public API |
refresh_corpus |
Continuous ingestion into local corpus |
run_evaluation |
Discovery + open-source relevance harness |
upsert_profile |
Create / update project profile |
draft_proposal_outline |
Grounded outline (grants and public-goods vehicles) |
Architecture
MCP Interface
↓
Discovery (Grants.gov · NSF · Public-Goods Catalog)
↓
Profile Steward → Ranking Agents → Drafting Agents
↓
Evaluation & Continuous Corpus
Support
- GitHub Sponsors
- Open Collective (update
.github/FUNDING.ymlwith your slug) - See
docs/DOGFOODING.md
Publishing
- PyPI:
opengos - MCP Registry:
io.github.ANAMIZED/opengos - Glama:
glama.json
License
Apache License 2.0 — see LICENSE.
https://github.com/ANAMIZED/OpenGOS
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
Neon Database
MCP server for interacting with Neon Management API and databases
E2B
Using MCP to run code via e2b.
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.