Skip to content
verify mcp Beta VerifyMCP is currently in beta. If you notice any issues, get in touch and we’ll put it right.

Ankr Agent RPC

NPM · @W3TECH.IO/AGENT-RPC-MCP · 2 COMPONENTS

Read chain data on 200+ networks and Sui: transactions, logs, balances, objects, ABI-decoded.

– Trust /100
Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. How we score → Why this is hard to score →

No category breakdown is available for this channel yet.

Install

How do I install the Ankr Agent RPC MCP server?

Ankr Agent RPC runs locally as an npm package, launched with npx -y @w3tech.io/agent-rpc-mcp. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

npm · @w3tech.io/agent-rpc-mcp

# add to Claude Code
claude mcp add w3tech-agent-rpc-mcp -- npx -y @w3tech.io/agent-rpc-mcp
// .cursor/mcp.json
{
  "mcpServers": {
    "w3tech-agent-rpc-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "@w3tech.io/agent-rpc-mcp"
      ]
    }
  }
}
// .vscode/mcp.json
{
  "servers": {
    "w3tech-agent-rpc-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "@w3tech.io/agent-rpc-mcp"
      ]
    }
  }
}
# add to Codex CLI
codex mcp add w3tech-agent-rpc-mcp -- npx -y @w3tech.io/agent-rpc-mcp
// opencode.json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "w3tech-agent-rpc-mcp": {
      "type": "local",
      "command": [
        "npx",
        "-y",
        "@w3tech.io/agent-rpc-mcp"
      ],
      "enabled": true
    }
  }
}
# add to OpenClaw
openclaw mcp add w3tech-agent-rpc-mcp --command npx --arg -y --arg @w3tech.io/agent-rpc-mcp
# ~/.hermes/config.yaml
mcp_servers:
  w3tech-agent-rpc-mcp:
    command: "npx"
    args: ["-y", "@w3tech.io/agent-rpc-mcp"]
// ~/.netclaw/config/netclaw.json
{
  "McpServers": {
    "w3tech-agent-rpc-mcp": {
      "Transport": "stdio",
      "Command": "npx",
      "Arguments": [
        "-y",
        "@w3tech.io/agent-rpc-mcp"
      ]
    }
  }
}
# add to Vellum
assistant mcp add w3tech-agent-rpc-mcp -t stdio -c npx -a -y @w3tech.io/agent-rpc-mcp
// mcp.json
{
  "mcpServers": {
    "w3tech-agent-rpc-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "@w3tech.io/agent-rpc-mcp"
      ]
    }
  }
}
Changelog

Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.

We have not recorded any changes for this component yet

Diagnostics

Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.

Captured 9 Oct 2026 · Analysed npm/@w3tech.io/agent-rpc-mcp@0.2.4

Provenance No attestation

The registry publishes no build provenance for this version, so there is nothing to verify.

Result No attestation
Ecosystem npm

Background: How many MCP packages publish verified provenance →

Dependencies 173 packages
Packages resolved 173
Deprecated 1
Stale 55
Tree resolution Complete

Background: SBOMs and build attestations, explained →

MCP tools

The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →

Tools for package channels are captured by running the package in an isolated sandbox. This package has not been through a sandbox run yet.