Digital Humani for AI agents

Digital Humani is a reforestation API that lets businesses browse tree-planting projects, submit planting requests, and track trees planted, used by brands running sustainability and loyalty programs. 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.

Connect Digital Humani See the 7 actions ↓

Developer toolsAPI keyMCP + RESTdigitalhumani.com

AUDIT LOG · DIGITAL HUMANIPOLICY: acme-support

09:41:07 · claude · u_8f2read

digital_humani.list_projects

List Reforestation Projects✓ allowed · 212ms

09:41:08 · claude · u_8f2read

digital_humani.get_project

Get Reforestation Project✓ allowed · 164ms

09:41:09 · claude · u_8f2write

digital_humani.plant_trees

Plant Trees✓ approved · approved by user

EVERY DIGITAL HUMANI CALL, ON THE RECORD

01 · USE CASES

What agents do in Digital Humani.

Browse planting projects

List available reforestation projects so a team can pick one for a customer reward program.

Submit a tree-planting request

Plant trees against an enterprise account after a customer hits a purchase milestone.

Check tree count before reporting

Read the enterprise's total tree count to include in a sustainability update, without changing anything.

02 · ACTIONS

7 Digital Humani actions, graded by risk.

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

read

Look things up. Allowed by default.

digital_humani.get_project
Get Reforestation Project
digital_humani.list_projects
List Reforestation Projects
digital_humani.get_tree_request
Get Tree Request
digital_humani.get_user_tree_count
Get User Tree Count
digital_humani.get_enterprise_tree_count
Get Enterprise Tree Count
digital_humani.get_current_user_and_enterprise
Get Current User and Enterprise

write

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

digital_humani.plant_trees
Plant Trees

destructive

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

No destructive actions.

03 · HOW IT WORKS

Digital Humani in three steps.

01Your users connect Digital HumaniThey add their Digital Humani api key on Arc0 Connect, under your brand. It goes straight into the vault.
02You set the rulesReads run, and writes like “plant Trees” can wait for the user to approve.
03Any agent can actYour agent calls Digital Humani 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('digital_humani', {
  read: 'allow',
  write: 'ask',        // plant_trees
  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 Digital Humani connects.

Users add their Digital Humani api key on Arc0 Connect. It is encrypted in the vault, never shown to the model, and each user can rotate or revoke it at any time.

The same Digital Humani 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: API key
CREDENTIALS: Per-tenant encrypted vault
MODEL SEES: Results only, never credentials
AUDIT LOG: Every call, on every plan

05 · WORKS WITH

Use Digital Humani from any agent.

Claude

ChatGPT

Cursor

Codex

VS Code

OpenAI Agents SDK

Claude Agent SDK

Vercel AI SDK

Mastra

LangGraph

06 · RELATED

More developer tools apps.

Addressfinder17 actions

Addresszen2 actions

Alchemy36 actions

ALL DEVELOPER TOOLS APPS →

07 · FAQ

Digital Humani and Arc0, answered.

Q01

Can I use Digital Humani with Claude, ChatGPT or Cursor?

Yes. Connect Digital Humani 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 Digital Humani actions you allow.

Q02

How do users connect Digital Humani?

Users add their Digital Humani api key on Arc0 Connect. It is encrypted in the vault, never shown to the model, and each user can rotate or revoke it at any time.

Q03

Which Digital Humani actions can my agent take?

7 in total: 6 read, 1 write and 0 destructive, such as “plant Trees”. Your policies decide which of them each agent may call.

Q04

Can I make my agent read-only in Digital Humani?

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

Q05

Can my own backend call Digital Humani too?

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

Get started

Plug Digital Humani into your agent.

Your users connect Digital Humani once, under your brand. Your agent gets 7 actions behind your policies, with every call on the record.

Connect Digital Humani Browse all apps →

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