Security & Testing

apir.ai

Verifies AI agent credentials and human mandates using cryptographically signed grants and Ed25519 public keys.

1 endpoint3 known toolsFirst detected October 13, 2026Last detected October 13, 2026

ENDPOINT 1

https://apir.ai/api/mcp

No auth detected

MCP server metadata

Name: apir-verify
Version: 1.0.0

Capabilities

tools

Server instructions

APIR answers three questions about an AI agent you did not build: is it who it claims to be, is it acting inside a human mandate, and what is its record. Call verify_agent when an unfamiliar agent contacts you or your user. Call check_authority before letting one transact, spend or commit on anyone's behalf. Never read VERIFIED as "safe": it confirms the credential is genuine and unaltered, not that the agent behaves well. Never read NO_RECORD as suspicious: it means nothing is on file.

Known tools 3

verify_agent

Check whether an AI agent carries a real, cryptographically signed credential.

Inferred read-only

check_authority

Resolve the human mandate behind an AI agent: which actions a named person actually permitted, any value cap, the expiry, and whether the grant itself is signed.

Inferred read-only

get_verification_keys

Return the Ed25519 public keys APIR publishes, so a signature can be recomputed offline without trusting any APIR response, including this one.

Inferred read-only

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.apir-verify]
url = "https://apir.ai/api/mcp"
enabled = true

Claude Code

.mcp.json

{
  "mcpServers": {
    "apir-verify": {
      "type": "http",
      "url": "https://apir.ai/api/mcp"
    }
  }
}

Claude Desktop

Settings → Connectors → Add custom connector

Name: apir-verify
Remote MCP URL: https://apir.ai/api/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": {
    "apir-verify": {
      "url": "https://apir.ai/api/mcp"
    }
  }
}

Visual Studio Code

.vscode/mcp.json

Add to Visual Studio Code

{
  "servers": {
    "apir-verify": {
      "type": "http",
      "url": "https://apir.ai/api/mcp"
    }
  }
}

Generic MCP

Client-specific MCP configuration

{
  "name": "apir-verify",
  "transport": "streamable-http",
  "url": "https://apir.ai/api/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 apir.ai was fetched 2026-10-14T05:00:17.456Z.

Trust status Neutral

apir.ai 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.