Get started

Pointagram for AI agents

Pointagram is a gamification tool that runs competitions and scoring to increase team motivation and celebrate achievements. Sales and operations teams use it to keep goals visible and fun. 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 PointagramSee the 8 actions ↓
ProductivityAPI keyMCP + RESTpointagram.com
AUDIT LOG · POINTAGRAMPOLICY: acme-support
09:41:07 · claude · u_8f2read
pointagram.list_teams
List Teams✓ allowed · 212ms
09:41:08 · claude · u_8f2read
pointagram.list_players
List Players✓ allowed · 164ms
09:41:09 · claude · u_8f2write
pointagram.add_score
Add Score✓ approved · approved by user
EVERY POINTAGRAM CALL, ON THE RECORD
01 · USE CASES

What agents do in Pointagram.

01

Add a score for a player

Record a new score entry for a team member after they hit a milestone.

02

Check competition standings read-only

List competition players and their rankings before announcing a leaderboard update.

03

Check score history read-only

Pull a score series' history to verify point totals before awarding a prize.

02 · ACTIONS

8 Pointagram actions, graded by risk.

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

read

7

Look things up. Allowed by default.

  • pointagram.list_teams
    List Teams
  • pointagram.list_players
    List Players
  • pointagram.list_competitions
    List Competitions
  • pointagram.list_score_series
    List Score Series
  • pointagram.list_competition_players
    List Competition Players
  • pointagram.list_score_series_history
    List Score Series History
  • pointagram.list_score_series_point_types
    List Score Series Point Types

write

1

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

  • pointagram.add_score
    Add Score

destructive

0

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

  • No destructive actions.
03 · HOW IT WORKS

Pointagram in three steps.

  1. 01Your users connect PointagramThey add their Pointagram api key on Arc0 Connect, under your brand. It goes straight into the vault.
  2. 02You set the rulesReads run, and writes like “add Score” can wait for the user to approve.
  3. 03Any agent can actYour agent calls Pointagram 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('pointagram', {
  read: 'allow',
  write: 'ask',        // add_score
  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 Pointagram connects.

Users add their Pointagram 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 Pointagram 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 Pointagram from any agent.

Claude
ChatGPT
Cursor
Codex
VS Code
OpenAI Agents SDK
Claude Agent SDK
Vercel AI SDK
Mastra
LangGraph
06 · RELATED

More productivity apps.

Notion57 actionsAirtable27 actionsConfluence70 actionsClickUp164 actionsAmazing Marvin10 actionsRentman130 actionsHub Planner122 actionsCoda110 actions
ALL PRODUCTIVITY APPS →
07 · FAQ

Pointagram and Arc0, answered.

Q01

Can I use Pointagram with Claude, ChatGPT or Cursor?

Yes. Connect Pointagram 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 Pointagram actions you allow.

Q02

How do users connect Pointagram?

Users add their Pointagram 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 Pointagram actions can my agent take?

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

Q04

Can I make my agent read-only in Pointagram?

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

Q05

Can my own backend call Pointagram too?

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

Get started

Plug Pointagram into your agent.

Your users connect Pointagram once, under your brand. Your agent gets 8 actions behind your policies, with every call on the record.

Connect PointagramBrowse all apps →

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