Control a headless browser with cryptographic audit trails and signed proof bundles for AI agents. Ideal for developers building trustworthy automation that requires verifiable evidence of actions taken.
io.github.bkauto3/conduit
Local install
STDIO
No auth required
How models use it and what it is built for.
Control a headless browser with cryptographic audit trails and signed proof bundles for AI agents. Ideal for developers building trustworthy automation that requires verifiable evidence of actions taken.
Local install — runs as a subprocess.
Where to find authoritative docs and source for Bkauto3 Conduit.
Paste any of these into Agent Studio after connecting Bkauto3 Conduit.
Common questions about connecting and running Bkauto3 Conduit.
What is a proof bundle and why would I need one?
A proof bundle is an Ed25519-signed collection of evidence from browser actions. It's useful when you need cryptographic proof that an AI agent performed specific actions, for compliance, auditing, or verification purposes.
How do SHA-256 audit trails work in this server?
Each browser action is hashed using SHA-256, creating an immutable record of what occurred. This allows you to verify that actions haven't been tampered with and to audit the exact sequence of events.
Do I need to set up keys for Ed25519 signing?
Yes, you'll need to configure Ed25519 signing keys via environment variables. Check the install documentation for required env vars like key paths or secrets needed to generate signed proof bundles.
Can I use this for regular web scraping without the cryptographic features?
The registry data doesn't specify whether cryptographic features are optional. Review the documentation after installation to confirm whether audit trails and signing are mandatory or can be disabled.
What's the difference between this and a standard headless browser like Puppeteer?
This server adds cryptographic audit trails and Ed25519-signed proof bundles on top of headless browser capabilities. If you need verifiable, tamper-proof evidence of AI agent actions, this is the differentiator; for basic automation, standard browsers may suffice.
MCP Playground runs 10,000+ hosted MCP servers — GitHub, Linear, Notion, Stripe, Sentry and more — across Claude, GPT, Gemini, DeepSeek and 60+ AI models. Compare model answers side-by-side, save agent presets, share runs. Zero install.
Open Agent StudioJudges Panel
45 judges that evaluate AI-generated code for security, cost, and quality with built-in AST.
Addozhang Nexus
Query Sonatype Nexus Repository (OSS/Pro) for Maven, Python, and Docker artifacts
Cyanheads MCP Ts Template
TypeScript template for building MCP servers with declarative tooling, observability, and auth.
Chernistry Bernstein
Declarative agent orchestration for engineering teams