Stop AI Agents fromRunning Wild
Give your agents identity and limits. Shield your APIs and resources from unauthorized access. Every decision signed and verifiable. Power agent-to-agent commerce — with signed terms and verifiable receipts.
No credit card required.
Your Trust Infrastructure at a Glance
Issue passports, enforce guardrails, verify agents, and track every decision — all from one dashboard.
with Avatron
- Every agent carries a signed, scoped credential
- Spending caps, rate limits, and access rules enforced before every action
- APIs and tools verify agent identity before granting access
- Every decision — allow or deny — is signed and auditable
- Revoke any agent’s access instantly
- Agents discover services and transact with cryptographic proof
Unprotected
- Agents share API keys with god-mode access
- APIs have no way to verify which agent is calling
- Rules live in prompts and hope
- No audit trail when things go wrong
- No way to revoke a single agent’s access
- No way to prove what happened or who did it
Built for Both Sides of the Agent Stack
Whether You Deploy Agents or Host What They Access
If You Deploy AI Agents
Control what your agents can do, access, and spend. Give each agent a signed credential and keep a tamper-proof log of every decision.
- Scoped permissions per agent
- Real-time spending controls
- Tamper-proof audit trail
- Revoke credentials instantly
If You Run APIs, MCP Servers, or Tools
Verify which agent is calling you before giving access. Enforce your rules locally — no network round-trip — and return signed decision records.
- Verify agent identity at the edge
- Enforce constraints locally
- No external dependencies for verification
- Signed decision records
From Zero to Verified in Four Steps
Create Your Signing Identity(Issuer)
Generate the Ed25519 keypair that will issue credentials to your agents. The private key never leaves your machine.
Issue an Agent Credential(Passport)
Give an agent its identity, permissions, spending rules, and expiration. Signed by your issuer.
e.g., cap spending at $50/day, deny requests after 24 hours
Protect Your Tool or API(Gate)
Add Avatron in front of your MCP server, API, or internal service. Choose L1 (dev), L2 (production), or L3 (high security).
e.g., require proof-of-possession for production APIs
Log Every Decision(Attestation)
Every allow, deny, and rule check is signed, sequenced, and recorded. Gap-filling attacks are impossible.
Integrate in Minutes
Add agent identity and authorization with one config file. Connect through MCP for Claude and GPT integrations, or use the REST API directly.
{ "mcpServers": { "avatron": { "command": "npx", "args": ["avatron-mcp"], "env": { "AVATRON_API_KEY": "avt_live_xxxxxxxx" } } }}What Avatron Gives You
Everything you need to secure agent actions in production.
Prove Which Agent Made the Request
Every passport, attestation, and catalog is cryptographically signed with Ed25519. Verify trust without a network call.
Set Rules for What Agents Can Do
Spending caps, rate limits, domain allowlists, approval workflows. 17 built-in constraint evaluators, all enforced automatically.
e.g., cap spending at $50/day, only allow calls to Stripe and GitHub
Choose the Right Security Level
L1 for development, L2 for production with trusted issuers, L3 for high assurance with proof-of-possession.
e.g., require proof-of-possession for production APIs
Keep Signed Audit Logs
Every enforcement decision creates a signed attestation. Sequential numbering prevents gap-filling. Export anytime.
Works with Claude, GPT, and Any MCP Client
First-class Model Context Protocol support. 22 tools available out of the box.
No Vendor Lock-In
Built on the Uniplex open standard. Run your own gates. Verify credentials independently. Migrate anytime.
Let Agents Buy and Sell Services Safely
Publish pricing and terms, meter usage with signed receipts, and settle transactions with cryptographic proof.
Agents Find and Compare Services
Agents discover services and compare pricing, SLAs, and capabilities before committing.
Pricing Locked in Signed Catalogs
Per-call, per-minute, and subscription pricing locked into signed catalogs. No bait-and-switch.
Uptime and Response Commitments Enforced
Uptime and response time commitments enforced and verifiable. Agents choose services that meet their requirements.
Both Sides Hold Signed Receipts
Both sides hold signed receipts for every transaction. Disputes resolved with cryptographic proof.
Example: Service Listing
Simple, Transparent Pricing
Free to start. Scale when you're ready.
Free
For testing and personal projects
- 3 gates
- 10 passports
- 1k decisions/mo
Pro
For teams running agents in production
- 20 gates
- 100 passports
- 50k decisions/mo
Teams
For organizations managing many agents and services
- Unlimited gates & passports
- 500k decisions/mo
- Up to 15 seats
No credit card required.
Start Securing Agent Actions
in Minutes
Give your agents identity, permissions, and proof. Free to start for individual developers.
Built on the Uniplex open standard. No credit card required.