SDK runs on your own machine — the client starts it, so there is no endpoint to ping. 197 installs a week from npm. Last commit 26 Oct 2026.
TypeScript SDK for mutual ZKP authentication between humans and AI agents.
We read the source, 6 d ago · rules 995398eba69f
Found in continuous integration, deployment or infrastructure files, or in a neighbouring package of the same monorepo. None of this is installed when you add the server: it describes how the project is built and released. We list it because a leaked key in a build pipeline is still a real problem, but it is not something this server does on your machine.
result = subprocess.run(
const content = fs.readFileSync(path.join(receiptDir, latest), 'utf-8');
const child: ChildProcess = spawn(serverCmd, serverCmdArgs, {
export function checkRequestBinding(
pipeline.innerHTML = STEPS.map(s =>
…d00cf5f5b2fc97d9bbfdb7d025"}}});var j,I=co(()=>{j={tavily:{label:"Tavily POST /search 402 (observed 2026-09-29)",header:"eyJ4NDAyVmVyc2lvbiI6MiwiZXJyb3IiOiJQYXltZW50IGhlYWRlciBpcyByZXF1aXJlZCIsInJlc291cmNlIjp7InVybCI6Imh0dHBzOi8veDQwMi50YXZpbHkuY29tL3NlYXJjaCIsImRlc2NyaXB0aW9uIjo…
Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.
Today is the operative word: we check SDK every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.
This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.
claude mcp add sdk -- npx -y @bolyra/sdk
{
"mcpServers": {
"sdk": {
"command": "npx",
"args": [
"-y",
"@bolyra/sdk"
]
}
}
}
[mcp_servers.sdk]
command = "npx"
args = ["-y", "@bolyra/sdk"]
{
"mcpServers": {
"sdk": {
"command": "npx",
"args": [
"-y",
"@bolyra/sdk"
]
}
}
}
{
"servers": {
"sdk": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@bolyra/sdk"
]
}
}
}
Authenticated local evidence paths for JavaScript and TypeScript coding agents.
JSON Schema, TypeScript types, mocks for AI agents
TypeScript inferred types, completions and type errors for AI coding agents
TypeScript inferred types, completions and type errors for AI coding agents
Shared visual canvas (Excalidraw) for collaborative whiteboarding between AI agents and humans.
Signed messages between AI agents. Dangerous actions wait for a human-signed approval.
Node.js and TypeScript debugging with 25+ tools for AI agents
Intent-bound action authorization for AI agents: policy, human approval, and a signed audit trail.
Answers built from our own checks of this server.