AI & Machine Learning

agnt.id

An MCP server for resolving, checking, and searching .agnt agent names to retrieve owner, wallet, endpoint, and identity metadata.

x402 supported1 endpoint9 known toolsFirst detected May 29, 2026Last detected October 6, 2026

ENDPOINT 1

https://www.agnt.id/.well-known/mcp

No auth detected

MCP server metadata

Name: agnt
Version: 0.2.1

Capabilities

tools.listChangedresources.listChangedprompts.listChanged

Server instructions

Resolve and inspect .agnt agent identities (agnt.id). Use resolve_agnt / resolve_wallet to turn a name into an address, reverse_agnt to name an address, search_agnt to discover agents, and trust_score / domain_verifications to vet one before delegating. All tools are read-only.

Known tools 9

resolve_agnt

Resolve a .agnt name to its owner, wallets, agent endpoints (A2A/MCP), identity records, and metadata.

Inferred read-only

reverse_agnt

Find the primary .agnt name for an EVM address.

Inferred read-only

resolve_wallet

Resolve a .agnt name to the single EVM wallet address to transact with on a given chain — the fast path before sending funds or an on-chain call.

Inferred read-only

check_availability

Check whether a .agnt name can be registered.

Inferred read-only

search_agnt

Search and discover .agnt agents by keyword, skill, or domain.

Inferred read-only

owner_names

List every .agnt name owned by an EVM address (its on-chain inventory).

Inferred read-only

trust_score

Get the trust score, badge, and reputation signals for a .agnt name — use before delegating work or funds to an agent you don't already trust.

Inferred read-only

domain_verifications

List the DNS/web domains a .agnt name has verifiably linked (proof of who operates the agent).

Inferred read-only

x402_config

Read the x402 pay-per-call configuration for a .agnt agent (payment address, price per call, chain).

Potential side effects

CONNECT WITH APPROVAL

Client installation

Review this server and its permissions before adding it. Secret placeholders must be set locally.

Codex

~/.codex/config.toml

[mcp_servers.agnt]
url = "https://www.agnt.id/.well-known/mcp"
enabled = true

Claude Code

.mcp.json

{
  "mcpServers": {
    "agnt": {
      "type": "http",
      "url": "https://www.agnt.id/.well-known/mcp"
    }
  }
}

Claude Desktop

Settings → Connectors → Add custom connector

Name: agnt
Remote MCP URL: https://www.agnt.id/.well-known/mcp

Add this remote URL as a custom connector in Claude Desktop. Availability depends on the user plan and workspace policy.

Cursor

.cursor/mcp.json

{
  "mcpServers": {
    "agnt": {
      "url": "https://www.agnt.id/.well-known/mcp"
    }
  }
}

Visual Studio Code

.vscode/mcp.json

Add to Visual Studio Code

{
  "servers": {
    "agnt": {
      "type": "http",
      "url": "https://www.agnt.id/.well-known/mcp"
    }
  }
}

Generic MCP

Client-specific MCP configuration

{
  "name": "agnt",
  "transport": "streamable-http",
  "url": "https://www.agnt.id/.well-known/mcp"
}

MCP Inspector

Run the official MCP Inspector locally and enter the indexed Streamable HTTP endpoint.

TRUST AND VERIFICATION EVIDENCE

Trust Data Available

BuiltWith Trust API v2 evidence for agnt.id was fetched 2026-10-13T11:38:46.644Z.

Trust status Neutral

agnt.id is assessed as Neutral: No suspicious signals found, but no strong positive signal either

Indexed

Evidence is source-attributed and does not guarantee that a third-party server is safe. Risk labels are conservative metadata heuristics.