covalt-gateway
MCP serverAI & modelsTrusted execution infrastructure for AI agents. Proposal-only protocol with human consent.
Use covalt-gateway in Claude, ChatGPT or Ahel Desktop
Free. Sign in, add covalt-gateway and connect your AI. About a minute.
Also: Claude Code · Cursor · Codex
Then ask your AI: use covalt-gateway
Needs your own covalt-gateway account. You sign in to it and approve access when you connect.
Details
Available today. Use it from your connected AI after setup.
Add Ahel to your AI once: Claude, ChatGPT, Cursor, Claude Code or Codex. Then ask it to use this.
Install covalt-gateway
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 covalt-gateway 'https://kcafcrbeaudhibyytziw.supabase.co/functions/v1/mcp'Run it once in your project, then open /mcp to approve any sign-in the server asks for.
Claude Desktop
https://kcafcrbeaudhibyytziw.supabase.co/functions/v1/mcpAdd a custom connector in Settings, paste this address, and approve the sign-in.
Cursor
cursor://anysphere.cursor-deeplink/mcp/install?name=covalt-gateway&config=eyJ1cmwiOiJodHRwczovL2tjYWZjcmJlYXVkaGlieXl0eml3LnN1cGFiYXNlLmNvL2Z1bmN0aW9ucy92MS9tY3AifQ==Open the link and Cursor adds the server at that address.
ChatGPT
https://kcafcrbeaudhibyytziw.supabase.co/functions/v1/mcpIn Settings, enable Developer mode, create an MCP app, and paste this address. Your plan and workspace must allow custom apps.
Codex
codex mcp add covalt-gateway --url 'https://kcafcrbeaudhibyytziw.supabase.co/functions/v1/mcp'Run it once, then sign in with codex mcp login covalt-gateway if the server asks for an account.
From the project's README
As published by covaltpay/covaltpay in README.md.
# CovaltPay
CovaltPay
CovaltPay is a trust-first payment orchestration platform for coordinated payments between multiple parties.
It enables rule-based, milestone-driven payment flows where trust is enforced by structure — not relationships.
---
Status
CovaltPay is under active development.
Core payment orchestration concepts are live. Internal intelligence agents (Sonar and Guard Dog) are operational and available independently.
Early access, demos, or agent licensing: → https://covaltpay.gumroad.com/l/kpvcd
Why CovaltPay exists
Most group payments assume trust. CovaltPay is designed for scenarios where:
- Parties may not know each other
- Funds are material
- Failure or non-delivery is costly
- Accountability matters
Instead of “send and hope”, CovaltPay introduces enforceable rules.
Core concepts
- Pacts – structured agreements defining roles, rules, and conditions
- Milestones – objective checkpoints that gate payment release
- Escrow logic – funds are controlled by rules, not individuals
- Verification layers – human, automated, or agent-assisted
Intelligence & risk layer
CovaltPay is supported by internal intelligence agents:
- Sonar – detects emerging risk, regulation, and opportunity signals
- Guard Dog – flags fraud patterns, delivery risk, and rule breaches
These agents operate independently and can be deployed without CovaltPay.
Status
This repository documents architecture, concepts, and integration patterns. Core components are under active development.
For early access, demos, or agent licensing: → https://covaltpay.gumroad.com/l/kpvcd
Signals
- Last commit
- Feb 2026
Advanced
- Delivery
- covalt-gateway MCP server → your Ahel connector (mcp.ahel.ai) → your AI.
- Item type
- mcp-server
- Key
io-github-covaltpay-covalt-gateway- Source
- github.com/covaltpay/covaltpay
- Hosted endpoint
https://kcafcrbeaudhibyytziw.supabase.co/functions/v1/mcp
github.com/covaltpay/covaltpay
More in AI & models
MCP server · upstash
More in AI & modelsAdButler
MCP server · adbutler
More in AI & modelsatom-mcp-server
MCP server · a7om-ai
More in AI & modelsottasia
MCP server · aiweather-anurag
More in AI & modelsunphurl
MCP server · 123ergo
More in AI & modelsmicrosoft-learn-mcp
MCP server · microsoftdocs
More in AI & models