API & MCP

Grant data for AI agents and apps.

Semantic grant search over a corpus of 4,000+ open, rolling, and forecast opportunities, checked against the source — not an inflated catalog of duplicates and expired listings. A free Model Context Protocol (MCP) server for Claude, Cursor, and any MCP client.

Add to Claude or Cursor See pricing

Five lines, then your AI can find grants

Add the MCP server to your client config and restart. Your assistant can now search open, rolling, and forecast opportunities, pull full opportunity details, and check eligibility — in the flow of a normal conversation. The free tier needs no key.

Works with Claude Desktop, Cursor, and any MCP client
Streamable HTTP — no local install
Public search is read-only; paid-key tools write only to your organization

mcp.json

{
  "mcpServers": {
    "grantsonar": {
      "url": "https://grantsonar.com/api/mcp"
    }
  }
}

Higher limits? Add "headers": { "Authorization": "Bearer gsk_…" } with a key from Settings → API & MCP.

Add it to your client

The free tier needs no key. For higher limits, add an Authorization: Bearer header with a key from Settings → API & MCP.

Claude Code (CLI)

One command in your terminal

claude mcp add --transport http grantsonar https://grantsonar.com/api/mcp

Claude Desktop

Settings → Connectors → Add custom connector, then paste the URL

https://grantsonar.com/api/mcp

Cursor

~/.cursor/mcp.json

{
  "mcpServers": {
    "grantsonar": { "url": "https://grantsonar.com/api/mcp" }
  }
}

Windsurf

~/.codeium/windsurf/mcp_config.json

{
  "mcpServers": {
    "grantsonar": { "serverUrl": "https://grantsonar.com/api/mcp" }
  }
}

Codex CLI

~/.codex/config.toml

[mcp_servers.grantsonar]
url = "https://grantsonar.com/api/mcp"

The tools

Public tools your agent can call without a key. More of the graph is rolling out.

search_grantsLive

Semantic + keyword search over the catchable grant corpus from a plain-English description. Returns deadlines, award amounts, and a GrantSonar link.

get_grantLive

Full detail for one opportunity by id — synopsis, eligibility, deadlines, award floor/ceiling, application URL.

get_past_winnersSoon

Federal award history — who actually won, how much, and where. Competitive intelligence on every program.

match_grants_to_orgSoon

Score and rank opportunities against an organization profile (mission, focus, geography, eligibility). Our matching engine, not just keyword search — most grant APIs do not have this.

Why build on GrantSonar

Honest, source-checked data

We return 4,000+ open, rolling, and forecast opportunities, checked against the source — not an inflated catalog of duplicates and expired listings. A grant with no published deadline comes back with close_date null: that covers rolling programs and can include forecasts of competitions that have not opened yet.

Matching, not just searchSoon

Coming: match_grants_to_org will score opportunities against a real org profile, so your agent can hand over a mission and get ranked, eligible results — the thing keyword APIs can’t do.

Read-only search, scoped writes

The public search tools (search_grants, get_grant) are read-only. A paid key unlocks calls to the paid tools, which save or dismiss grants and write or draft application sections, only within your own organization.

Simple, metered pricing

Start free, no signup. Pay only when you scale — and the per-call rate drops as you grow.

Free

$0no signup

200 calls / day

For evaluation and AI-assistant use. Anti-abuse daily cap, shared fair-use.

Add to Claude

Hobby

$29/mo

10K calls / mo

$2.90 / 1K

Your own key and a monthly quota for side projects.

Start checkout

Best value

Developer

$99/mo

40K calls / mo

$2.48 / 1K

Production apps. 60% more volume than the next platform at a third less.

Start checkout

Growth

$339/mo

150K calls / mo

$2.26 / 1K

Scaled usage with the best per-call rate. Priority support.

Start checkout

Enterprise

Custom

Volume pricing

Custom volume and SLA by agreement.

The free tier is live now, no signup. Paid plans use hard monthly caps today; the $/1K figures are effective-rate comparisons, not metered overage charges. Every tier undercuts other grant APIs on price and volume, and runs far below opaque enterprise data vendors. Metered overages, if added, are a future option.

Developer FAQ

Do I need a GrantSonar account to use the MCP?

No. The free tier is unauthenticated — drop the endpoint into your MCP client and start searching. Create a free account and generate a key only when you want higher limits.

What is the data, exactly?

Federal, state, and foundation grant opportunities that are open, rolling, or forecast, checked against the source rather than padded with closed listings. A grant with no published deadline has close_date null: that covers rolling programs and can include forecasts that are not open yet, so confirm with the funder before applying.

How do rate limits work?

Free is a per-day cap for evaluation. Paid plans are monthly query quotas. Drafting is live on paid keys: each successful draft_application_section call counts as 25 calls against your monthly quota, and a failed draft counts as 1.

Can my agent write or change anything?

Not with the public tools: search_grants and get_grant are read-only. A paid key unlocks calls to the paid tools, which save or dismiss grants in your pipeline and write or AI-draft application sections, only within your own organization. Those tools are marked as writes so your MCP client can ask before running them, and section edits try to save the prior version to history first.

How does this compare to legacy nonprofit-data APIs?

Self-serve, transparent pricing, and a source-checked corpus of open, rolling, and forecast opportunities — at a fraction of the cost of opaque enterprise data vendors, and undercutting other grant APIs on both price and volume.

Point your agent at the source-checked grant corpus.

Free to start, no signup. Five lines of config and your assistant can find open, rolling, and forecast grant opportunities.

Get started