MoSPI for AI agents

MoSPI provides India's official government statistics from the Ministry of Statistics and Programme Implementation, queryable through natural language instead of raw data files. 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.

AnalyticsNo authMCP + RESTmospi.gov.in
AUDIT LOG · MOSPIPOLICY: acme-support
09:41:07 · claude · u_8f2read
mospi.list_datasets
List datasets✓ allowed · 212ms
09:41:08 · claude · u_8f2read
mospi.get_data
Get data✓ allowed · 164ms
EVERY MOSPI CALL, ON THE RECORD
01 · USE CASES

What agents do in MoSPI.

01

Look up an economic indicator

Pull a specific national statistic, such as inflation or employment, for a research question.

02

List available datasets

List the datasets published by the ministry to find the right source for a report, read-only.

03

Check a dataset's metadata

Read a dataset's published metadata to understand its methodology before citing it in a report.

02 · ACTIONS

4 MoSPI actions, graded by risk.

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

read

4

Look things up. Allowed by default.

  • mospi.get_data
    Get data
  • mospi.get_metadata
    Get metadata
  • mospi.list_datasets
    List datasets
  • mospi.get_indicators
    Get indicators

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

MoSPI in three steps.

  1. 01Your users connect MoSPIThey add their MoSPI 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 MoSPI 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('mospi', {
  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 MoSPI connects.

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

The same MoSPI 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 MoSPI from any agent.

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

MoSPI and Arc0, answered.

Q01

Can I use MoSPI with Claude, ChatGPT or Cursor?

Yes. Connect MoSPI 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 MoSPI actions you allow.

Q02

How do users connect MoSPI?

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

Q03

Which MoSPI actions can my agent take?

4 in total: 4 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 MoSPI?

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

Q05

Can my own backend call MoSPI too?

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

Get started

Plug MoSPI into your agent.

Your users connect MoSPI once, under your brand. Your agent gets 4 actions behind your policies, with every call on the record.

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