Granted for AI agents

Granted is a search tool for finding grant opportunities across funders, with eligibility rules and deadlines. Finance teams use it to track this without reconciling numbers by hand at month end. Connect it once through Arc0, and your agent, or Claude, ChatGPT and Cursor, can use it through one MCP endpoint, limited to what each user approved.

Finance and accountingNo authMCP + RESTgranted.com
AUDIT LOG · GRANTEDPOLICY: acme-support
09:41:07 · claude · u_8f2read
granted.search_grants
Search grants✓ allowed · 212ms
09:41:08 · claude · u_8f2read
granted.get_grant
Get grant✓ allowed · 164ms
EVERY GRANTED CALL, ON THE RECORD
01 · USE CASES

What agents do in Granted.

01

Search for matching grants

Search open grants by keyword and eligibility to find opportunities that fit a nonprofit's mission.

02

Check a grant's deadline

Look up a specific grant's application deadline and requirements before a team applies.

03

Review past winners

Pull past winners of a grant program to gauge how competitive an application needs to be.

02 · ACTIONS

5 Granted actions, graded by risk.

Every Granted action is tagged read, write or destructive, so one policy covers the whole app and new actions inherit the right default.

read

5

Look things up. Allowed by default.

  • granted.get_grant
    Get grant
  • granted.get_funder
    Get funder
  • granted.search_grants
    Search grants
  • granted.search_funders
    Search funders
  • granted.get_past_winners
    Get past winners

write

0

Create and change things. Allow, or ask the user first.

  • No write actions.

destructive

0

Delete, cancel or archive. Ask first, or deny outright.

  • No destructive actions.
03 · HOW IT WORKS

Granted in three steps.

  1. 01Your users connect GrantedThey add their Granted no auth on Arc0 Connect, under your brand. It goes straight into the vault.
  2. 02You set the rulesReads run, and writes like “updates” can wait for the user to approve.
  3. 03Any agent can actYour agent calls Granted through the Arc0 SDK or MCP, and so can Claude, ChatGPT and Cursor. Every call lands on the audit log.
POLICY.TS
await arc0.policies.set('granted', {
  read: 'allow',
  write: 'ask',        
  destructive: 'deny',  
})

# Claude Code: the same connection, one URL
$ claude mcp add --transport http arc0 \
    https://mcp.arc0.ai/u/u_8f2
04 · AUTH AND DATA

How Granted connects.

Granted needs no credentials. Arc0 still applies your policies and records every call, so public tools get the same controls as private ones.

The same Granted connection serves your agent over MCP and your own backend over REST and the proxy, so a user connects once. How Arc0 handles credentials →

AUTH
No auth
CREDENTIALS
Per-tenant encrypted vault
MODEL SEES
Results only, never credentials
AUDIT LOG
Every call, on every plan
05 · WORKS WITH

Use Granted from any agent.

Claude
ChatGPT
Cursor
Codex
VS Code
OpenAI Agents SDK
Claude Agent SDK
Vercel AI SDK
Mastra
LangGraph
07 · FAQ

Granted and Arc0, answered.

Q01

Can I use Granted with Claude, ChatGPT or Cursor?

Yes. Connect Granted to Arc0 once, then add your Arc0 MCP URL to Claude, ChatGPT, Cursor, Claude Code or any other remote-MCP client. Each assistant only gets the Granted actions you allow.

Q02

How do users connect Granted?

Granted needs no credentials. Arc0 still applies your policies and records every call, so public tools get the same controls as private ones.

Q03

Which Granted actions can my agent take?

5 in total: 5 read, 0 write and 0 destructive. Your policies decide which of them each agent may call.

Q04

Can I make my agent read-only in Granted?

Yes. Allow read actions and deny writes in the Granted policy. Your agent can still look things up, and any write it attempts is blocked and logged.

Q05

Can my own backend call Granted too?

Yes. The same Granted connection is available over REST and through the Arc0 proxy, so your product and your agent share one connection per user.

Get started

Plug Granted into your agent.

Your users connect Granted once, under your brand. Your agent gets 5 actions behind your policies, with every call on the record.

Free to build · MCP + REST · Audit log on every plan