mcp-agentcore

MCP serverDev tools

Give your AI the ability to work with geospatial data. Once added, it can pull satellite imagery, use geospatial embeddings, and check weather information, with GNS governance applied to how it operates.

Use mcp-agentcore in Claude, ChatGPT or Ahel Desktop

Free. Sign in, add mcp-agentcore and connect your AI. About a minute.

Also: Claude Code · Cursor · Codex

Then ask your AI: use mcp-agentcore to verify jurisdiction

Details

Available today. Use it from your connected AI after setup.

After adding it, visit github.com/gns-foundation/geiant for setup details. Then ask your AI to pull imagery or check weather for a location.

mcp-agentcoreStart free

What your AI can do with it

  • Pull satellite imagery for locations you care about
  • Use geospatial embeddings in your AI's work
  • Check weather information
  • Operate under GNS governance rules

Install mcp-agentcore

The server’s own address, for the clients that take one directly. Or connect Ahel once and every client you use reads it from one address, with the account kept on Ahel rather than in each client’s config.

  • Claude Code

    claude mcp add --transport http --scope user mcp-agentcore 'https://geiant-agentcore-production.up.railway.app/mcp'

    Run it once in your project, then open /mcp to approve any sign-in the server asks for.

  • Claude Desktop

    https://geiant-agentcore-production.up.railway.app/mcp

    Add a custom connector in Settings, paste this address, and approve the sign-in.

  • Cursor

    cursor://anysphere.cursor-deeplink/mcp/install?name=mcp-agentcore&config=eyJ1cmwiOiJodHRwczovL2dlaWFudC1hZ2VudGNvcmUtcHJvZHVjdGlvbi51cC5yYWlsd2F5LmFwcC9tY3AifQ==

    Open the link and Cursor adds the server at that address.

  • ChatGPT

    https://geiant-agentcore-production.up.railway.app/mcp

    In Settings, enable Developer mode, create an MCP app, and paste this address. Your plan and workspace must allow custom apps.

  • Codex

    codex mcp add mcp-agentcore --url 'https://geiant-agentcore-production.up.railway.app/mcp'

    Run it once, then sign in with codex mcp login mcp-agentcore if the server asks for an account.

From the project's README

As published by gns-foundation/geiant in README.md. This repository publishes several servers, so only the opening is shown here.

Geo-Identity Agent Navigation & Tasking

The first AI orchestrator that knows where it is.


What is GEIANT?

GEIANT is a geospatial AI agent orchestration runtime built on the GNS Protocol. It is a direct competitor to LangChain, CrewAI, and AutoGen — with one structural difference: every agent has a cryptographic identity bound to an H3 territory, and every task is routed through a compliance enforcement layer before dispatch.

LangChain doesn't know where it is. GEIANT does.


The Ant Metaphor

In GEIANT, agents are ants. Ants are the canonical model of emergent collective intelligence from simple agents following spatial rules. Ant Colony Optimization (ACO) is a real algorithm used in routing and pathfinding. The colony is the orchestrated workflow. The territory is the H3 grid.

  • An ant (AntIdentity) is an agent with a GNS Ed25519 keypair + H3 territory + facet scope + trust tier
  • The colony is a multi-agent workflow where ants delegate and collaborate
  • The nest is the Agent Registry — the directory of available ants
  • The trail is the Virtual Breadcrumb chain — the Proof-of-Jurisdiction audit log

Shortened here. Read the whole README on GitHub.

Tools it offers (3)

What this server listed when Ahel dialed its public endpoint in Oct 2026, with no key and no account of yours. The names are the server’s own.

  • verify_jurisdiction
  • generate_audit_proof
  • check_delegation_chain

Signals

Last commit
Sep 2026
Advanced
Delivery
mcp-agentcore MCP server → your Ahel connector (mcp.ahel.ai) → your AI.
Item type
mcp-server
Key
com-geiant-mcp-agentcore
Source
github.com/gns-foundation/geiant
Hosted endpoint
https://geiant-agentcore-production.up.railway.app/mcp