General Tools
grantgraph.org
Provides general-purpose tools through the Model Context Protocol.
ENDPOINT 1
https://mcp.grantgraph.org/mcp
MCP server metadata
- Name
- grantgraph
- Version
- 0.1.0
Grant funding data from public records: IRS 990 filings and grants.gov. Call list_causes first if unsure which cause names are covered.
Known tools 4
find_fundersFind the private foundations that have actually funded a cause, from their own IRS 990 filings.
Inferred read-onlyopen_federal_opportunitiesOpen federal funding opportunities that are eligible for nonprofit applicants, matched against full synopsis text.
Inferred read-onlyfunding_gapFor each cause: how many open, nonprofit-eligible FEDERAL opportunities exist right now versus how much PRIVATE foundation money demonstrably flowed to it.
Inferred read-onlyCONNECT WITH APPROVAL
Client installation
Review this server and its permissions before adding it. Secret placeholders must be set locally.
Codex
~/.codex/config.toml
[mcp_servers.grantgraph]
url = "https://mcp.grantgraph.org/mcp"
enabled = true
Claude Code
.mcp.json
{
"mcpServers": {
"grantgraph": {
"type": "http",
"url": "https://mcp.grantgraph.org/mcp"
}
}
}
Claude Desktop
Settings → Connectors → Add custom connector
Name: grantgraph
Remote MCP URL: https://mcp.grantgraph.org/mcp
Add this remote URL as a custom connector in Claude Desktop. Availability depends on the user plan and workspace policy.
Cursor
.cursor/mcp.json
{
"mcpServers": {
"grantgraph": {
"url": "https://mcp.grantgraph.org/mcp"
}
}
}
Visual Studio Code
.vscode/mcp.json
Add to Visual Studio Code{
"servers": {
"grantgraph": {
"type": "http",
"url": "https://mcp.grantgraph.org/mcp"
}
}
}
Generic MCP
Client-specific MCP configuration
{
"name": "grantgraph",
"transport": "streamable-http",
"url": "https://mcp.grantgraph.org/mcp"
}
MCP Inspector
Run the official MCP Inspector locally and enter the indexed Streamable HTTP endpoint.
TRUST AND VERIFICATION EVIDENCE
Loading Trust v2 evidence…
Checking the associated registrable domain. The BuiltWith key remains server-side.
Evidence is source-attributed and does not guarantee that a third-party server is safe. Risk labels are conservative metadata heuristics.