Mapflow.ai for AI agents
Mapflow.ai analyzes satellite and aerial imagery with AI, running geospatial processing jobs for mapping and land-use projects across large areas. 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.
What agents do in Mapflow.ai.
Check a processing job's status
Look up whether a submitted imagery processing job has completed before pulling its results, a read-only status check.
Search the imagery catalog
Search available satellite imagery to find coverage for an area of interest.
Estimate a job's cost before running
Estimate the credit cost of a processing job before submitting it, since it consumes account credits.
10 Mapflow.ai actions, graded by risk.
Every Mapflow.ai action is tagged read, write or destructive, so one policy covers the whole app and new actions inherit the right default.
read
8Look things up. Allowed by default.
- mapflow_ai.list_projectsList Projects
- mapflow_ai.get_processingGet Processing
- mapflow_ai.list_processingsList Processings
- mapflow_ai.get_storage_overviewGet Storage Overview
- mapflow_ai.search_imagery_catalogSearch Imagery Catalog
- mapflow_ai.get_account_capabilitiesGet Account Capabilities
- mapflow_ai.estimate_processing_costEstimate Processing Cost
- mapflow_ai.download_processing_resultDownload Processing Result
write
2Create and change things. Allow, or ask the user first.
- mapflow_ai.create_projectCreate Project
- mapflow_ai.create_processingCreate Processing (Consumes Credits)
destructive
0Delete, cancel or archive. Ask first, or deny outright.
- No destructive actions.
Mapflow.ai in three steps.
- 01Your users connect Mapflow.aiThey add their Mapflow.ai api key on Arc0 Connect, under your brand. It goes straight into the vault.
- 02You set the rulesReads run, and writes like “create Project” can wait for the user to approve.
- 03Any agent can actYour agent calls Mapflow.ai through the Arc0 SDK or MCP, and so can Claude, ChatGPT and Cursor. Every call lands on the audit log.
await arc0.policies.set('mapflow_ai', { read: 'allow', write: 'ask', // create_project destructive: 'deny', }) # Claude Code: the same connection, one URL $ claude mcp add --transport http arc0 \ https://mcp.arc0.ai/u/u_8f2
How Mapflow.ai connects.
Users add their Mapflow.ai 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 Mapflow.ai 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
Use Mapflow.ai from any agent.
Mapflow.ai and Arc0, answered.
Can I use Mapflow.ai with Claude, ChatGPT or Cursor?
Yes. Connect Mapflow.ai 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 Mapflow.ai actions you allow.
How do users connect Mapflow.ai?
Users add their Mapflow.ai 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.
Which Mapflow.ai actions can my agent take?
10 in total: 8 read, 2 write and 0 destructive, such as “create Project”. Your policies decide which of them each agent may call.
Can I make my agent read-only in Mapflow.ai?
Yes. Allow read actions and deny writes in the Mapflow.ai policy. Your agent can still look things up, and any write it attempts is blocked and logged.
Can my own backend call Mapflow.ai too?
Yes. The same Mapflow.ai connection is available over REST and through the Arc0 proxy, so your product and your agent share one connection per user.
Plug Mapflow.ai into your agent.
Your users connect Mapflow.ai once, under your brand. Your agent gets 10 actions behind your policies, with every call on the record.
Free to build · MCP + REST · Audit log on every plan