Config is the same across clients — only the file and path differ.
{
"mcpServers": {
"autron": {
"args": [
"autron-mcp"
],
"command": "npx"
}
}
}Are you the author?
Add this badge to your README to show your security score and help users find safe servers.
const { generateKeypair, createDID, resolveDID, toStandardDID } = require('@autron/core');
Run this in your terminal to verify the server starts. Then let us know if it worked — your result helps other developers.
npx -y 'autron' 2>&1 | head -1 && echo "✓ Server started successfully"
After testing, let us know if it worked:
Five weighted categories — click any category to see the underlying evidence.
No known CVEs.
Checked autron against OSV.dev.
Be the first to review
Have you used this server?
Share your experience — it helps other developers decide.
Sign in to write a review.
Others in ai-ml / security
Persistent memory using a knowledge graph
Privacy-first. MCP is the protocol for tool access. We're the virtualization layer for context.
An open-source AI agent that brings the power of Gemini directly into your terminal.
Just a Better Chatbot. Powered by Agent & MCP & Workflows.
MCP Security Weekly
Get CVE alerts and security updates for io.github.hungnguyenhtbvn-max/autron-core and similar servers.
Start a conversation
Ask a question, share a tip, or report an issue.
Sign in to join the discussion.
The Open Identity Standard for AI Agents "OAuth for the Agentic Era"
resolveWebDID — async resolver for did:autron:web that fetches
.well-known/did.json with SSRF-safe DNS (rebinding defense at connect
time). did:autron:web is now first-class, not just metadata.AutronError + ValidationError,
AuthError, ReplayError, PaymentError, RateLimitError,
NotFoundError. Use instanceof or err.code to distinguish; stop
parsing message strings./metrics — opt-in on createSseServer({ metrics: true }).
Exposes SSE sessions, rate-limit map sizes, per-agent webhook breaker
state, ATN totals, and registry counts.14 security-audit rounds, 662 tests, production-deployed. See
examples/ for runnable recipes and CHANGELOG.md
for the full history.
npm install @autron/core
const { generateKeypair, createDID, resolveDID, toStandardDID } = require('@autron/core');
const keys = generateKeypair();
const did = createDID('key', keys);
console.log('Agent DID:', did);
// → did:autron:key:z6Mk...
const doc = resolveDID(did);
console.log('DID Document:', JSON.stringify(doc, null, 2));
// Compatible with standard DIDs
console.log('Standard:', toStandardDID(did));
// → did:key:z6Mk...
did:autron:* namespace with did:key/did:web compatibility mappingLayer 0: Crypto — Ed25519 / secp256k1 keypairs, JWK, multibase
Layer 1: DID — did:autron:key / web / dns
Layer 2: Agent Card — Short-lived identity tokens (agent-card+jwt)
Layer 3: Delegation — Scoped permission tokens (delegation+jwt)
Layer 4: Reputation — Endorsements & trust scores (endorsement+jwt)
Layer 5: Payment — On-chain payments & escrow (payment+jwt, escrow+jwt)
Layer 6: Nexus — Agent registry & marketplace (SQLite, MCP SSE)
Layers 0-4 work standalone. Layer 5 requires @solana/web3.js (lazy-loaded). Layer 6 adds a searchable agent registry with MCP remote access.
| Method | Format | Example |
|---|---|---|
key | Self-issued from keypair | did:autron:key:z6Mk... |
web | Domain-based | did:autron:web:api.example.com |
dns | DNS TXT record | did:autron:dns:myagent.example.com |
did:autron:web (v0.6.0+)Fetch the hosted DID Document from /.well-known/did.json on the
encoded domain:
const { resolveWebDID } = require('@autron/core');
const doc = await resolveWebDID('did:autron:web:api.example.com');
console.log(doc.verificationMethod[0].publicKeyMultibase);
// Path-based (hosted at /agents/bot/did.json):
await resolveWebDID('did:autron:web:api.example.com:agents:bot');
// Port-encoded (per spec: %3A = `:`):
await resolveWebDID('did:autron:web:api.example.com%3A8443');
// Local dev: opt into private-IP targets
await resolveWebDID('did:autron:web:127.0.0.1%3A3000', { allowPrivate: true });
The resolver is SSRF-safe: it re-validates th