A
licenseB
qualityD
maintenanceMCP server for MoltAwards that enables AI agents to search, filter, and engage with federal and state government contract opportunities, including teaming and commenting.
35
MIT
OpenGOS
by ANAMIZED
The OpenGrants OS server provides tools for discovering, evaluating, and drafting proposals for grants and public-goods funding, with a focus on open-source AI projects.
Search federal grants: Search live U.S. federal grant opportunities on Grants.gov by keyword, with full provenance metadata.
Get grant details: Retrieve detailed information for a specific grant opportunity by its ID.
Discover open-source relevant grants: Find grants particularly relevant to open-source AI and public goods, with a built-in open-source bias in ranking.
List public-goods funding sources: Browse donation, sponsorship, quadratic funding, and open-source fund opportunities from platforms like GitHub Sponsors, Open Collective, Gitcoin, OpenSSF, NumFOCUS, PSF, and more.
Search NSF awards: Query the NSF Awards public API for historical and active awards by keyword.
Refresh grant corpus: Trigger a continuous-ingestion refresh of the local grant corpus using configurable keywords.
Run evaluation harness: Execute the built-in evaluation harness to assess discovery quality and open-source relevance.
Manage profiles: Create or update project or researcher profiles, including focus areas and GitHub URLs, to power personalized grant matching and drafting.
Draft proposal outlines: Generate grounded proposal outlines and short pitches tailored to a specific profile and funding opportunity — works for both traditional grants and public-goods/sponsorship vehicles.
Enables discovery and application for GitHub Sponsors as a public-goods and donation funding source for open-source AI and public-goods projects.
Enables discovery and application for Open Collective funding, treating it as a first-class public-goods and donation funding opportunity.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@OpenGOS Find grants for my open-source AI project and draft a pitch"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
OpenGOS
Autonomous agentic MCP server for grants discovery, ranking, drafting, and public-goods funding.
Support the work
OpenGOS is funded by donations and sponsorships only. There is no Pro seat, consulting hour, or pay-per-use search/draft SKU.
Demo: Interactive shell
Non-custodial USDC (preferred for agents / x402)
Network | Address |
Base / Ethereum |
|
Solana |
|
Related: RUI · LRSI · Server-OS · OpenMesha · YodMCP · desk
FOUNDRY mapping
FOUNDRY separates untrusted proposal generation from host-owned verification and an established-facts registry. OpenGOS is the grants surface of that split:
FOUNDRY role | OpenGOS surface |
Agents propose | discoverer → ranker → drafter ( |
Host verifies | human / kernel review before a proposal is sent |
Established facts | ranked grant matches + draft artifacts, not self-attested win reports |
Durable memory for those facts lives in YodMCP. Promotion through kernels is fail-closed (LRSI, Server-OS, RUI). Host owns the evaluator; agents propose.
One-page note: docs/FOUNDRY.md.
Related MCP server: Grants.gov MCP Server
Surfaces
Surface | Entry |
MCP Server |
|
CLI |
|
SDK |
|
REST API |
|
Multi-agent | discoverer → ranker → drafter + |
Hero demo | |
CI |
|
Quick Start
pip install -e ".[dev,api]"
opengos # MCP
opengos-cli status
opengos-api # REST :8080License
Apache-2.0
Available Tools
9 toolsdraft_proposal_outlineA
Generate a grounded proposal outline + short pitch for a profile + opportunity (works for grants and donation/public-goods vehicles).
Inputs: profile_id (required), opportunity_title (required), opportunity_type, opportunity_description. Returns: result
get_grant_detailsA
Retrieve details for a specific grant opportunity by ID.
Inputs: opportunity_id (required). Returns: result
list_open_source_relevant_grantsC
Discover grants particularly relevant to open-source AI and public goods.
Inputs: focus, max_results. Returns: result
list_public_goods_fundingB
List donation, sponsorship, quadratic funding, and open-source public-goods funding opportunities (GitHub Sponsors, Open Collective, Gitcoin, Sentient, OpenSSF, NumFOCUS, PSF, etc.).
Inputs: focus, type_filter. Returns: result
refresh_corpusC
Trigger continuous-ingestion style refresh of the local grant corpus.
Inputs: keywords. Returns: result
run_evaluationC
Run the basic OpenGrants evaluation harness.
Inputs: no named parameters. Returns: result
search_grantsC
Search open U.S. federal grant opportunities (Grants.gov) by keyword with provenance.
Inputs: keyword (required), status, max_results. Returns: result
search_nsf_awardsC
Search NSF Awards (public API) for historical and active awards.
Inputs: keyword (required), max_results. Returns: result
upsert_profileB
Create or update a project/researcher profile for matching and drafting. focus_areas = comma-separated.
Inputs: name (required), profile_id (required), description (required), github_url, +1 more. Returns: result
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
B3.4/5.0
Scored across 9 tools
Disambiguation5/5
Each tool has a distinct purpose: general federal grant search, detailed grant retrieval, open-source-specific grants, public-goods funding, NSF awards, corpus maintenance, evaluation, profile management, and proposal drafting. No two tools overlap significantly.
Naming Consistency5/5
All tool names follow a consistent verb_noun pattern with lowercase underscores (search_grants, get_grant_details, list_public_goods_funding, etc.). Verbs like search, get, list, and refresh clearly indicate the action, and the pattern is uniform across the set.
Tool Count5/5
Nine tools is well within the ideal range for a funding-discovery and proposal-drafting server. Each tool addresses a distinct part of the workflow without redundancy or bloat.
Completeness4/5
The tool set covers core workflows: discovering grants and non-grant funding, retrieving details, creating/updating profiles, drafting proposals, and maintaining/evaluating the corpus. Minor gaps exist, such as no delete profile or no dedicated detail fetch for public-goods opportunities, but these are not likely to cause agent failures.
Maintenance
ActivityStale
ResponsivenessOutdated data
Related MCP Connectors
MCP server for AI agents to discover campaigns by humans and donate USDC directly on Base.
Search verified-open US grants (federal, state, foundation). Read-only MCP for AI agents.
Grants.gov MCP — open federal grant opportunities (free, no auth)
Grants.gov search and USAspending grant data. 4 MCP tools for grant discovery.
Related MCP Servers
- FlicenseNot gradedqualityDmaintenanceModel Context Protocol (MCP) server that provides access to the Grants.gov API for searching and retrieving federal grant opportunities.-
- AlicenseAqualityBmaintenanceAn MCP server that searches grant opportunities across multiple CommonGrants-compliant APIs from a single set of tools.33MIT
- FlicenseNot gradedqualityFmaintenanceA paid MCP server that gives AI agents instant, structured access to every open US federal grant and contract opportunity.-