Jid: the trust API for AI agents
com.jidv1.2.0Updated Oct 5, 2026
Verify a business before an agent pays, signs or buys: registry-cited decision and signed receipt.
Overview
AI-generated overview
Lets an assistant verify a business before it pays, signs, or buys, returning a registry-cited decision and a signed receipt.
- What it does
- This remote MCP server exposes a trust-check capability for AI agents: given a business, it returns a decision backed by registry citations plus a signed receipt. It is intended to be called at the moment an agent is about to pay, sign, or buy, so the decision can be recorded. The manifest does not list individual tool names, so the exact call surface is not documented here.
- When to use it
- Worth adding when an assistant takes or prepares commercial actions — payments, contract signing, purchases — and you want a verifiable, citable check on the counterparty first. Less useful for agents that never transact with third-party businesses.
- Requirements
- A remote streamable HTTP endpoint at jid.com; no local runtime or package install. An Authorization header is optional: without it, calls are rate-limited per IP. A free key (1,000 checks a month, no card) is available from the provider's pricing page.
Before you install
The Authorization header carries a bearer credential; treat it as a secret and do not expose it. The check itself is a read-style lookup, but it is designed to gate real payments, signatures, and purchases, so a wrong or stale decision can have financial consequences. Business identifiers you submit are sent to the provider's remote service.
Installation
In SourceWeft
- Open Jid: the trust API for AI agents in the dashboard and add it to a workspace.
- Enable the server for the chats that should use its tools.
Web executable via Streamable HTTP. Remote servers run from the web runtime once configured in a workspace.
Other MCP clients
Add this to your client's mcpServers config.
{
"mcpServers": {
"jid": {
"type": "http",
"url": "https://jid.com/mcp"
}
}
}Tools
0Tool metadata has not been indexed yet.
Version history
1- v1.2.0LatestOct 5, 2026


