# Averis Protocol

> Working capital for autonomous AI agents — USDC advances against verified job receivables on Arc.

- name: io.github.mosaro0224/averis-protocol
- version: 2.0.0
- connection class: R0 (autonomous)
- trust: 96/100
- quality: 80/100 (good)
- owner: not claimed
- descriptor: https://api.protogrid.dev/v1/servers/io.github.mosaro0224%2Faveris-protocol
- tools: https://api.protogrid.dev/v1/servers/io.github.mosaro0224%2Faveris-protocol/tools

**An agent can connect right now, no human step.** Remote endpoint, no authentication, reachable on the last probe.

## Connection (mcpServers)

```json
{
  "mcpServers": {
    "averis-protocol": {
      "type": "http",
      "url": "https://api.averisprotocol.xyz/mcp"
    }
  }
}
```


## Trust

- hygiene: 100
- liveness: 98
- freshness: 100
- provenance: 90
- drivers: +repository +namespace-matches-repo +website +reachable +uptime-96% +updated-30d-ago
- Derived from observable signals (official registry feed and our own credential-free probes); no code audit performed.

## Quality 80/100 (good)

### protocol: 75 (weight 25)

- warn `protocol.modern`: newest supported version is 2025-03-26; 2026-07-28 not supported, older versions are deprecated until 2027-07-28
- n/a `protocol.stateless`: only applies to 2026-07-28 servers
- pass `protocol.transport`: streamable HTTP
- n/a `protocol.list_ttl`: only applies to 2026-07-28 servers

### authorization: n/a (weight 15)

- n/a `auth.prm`, `auth.as_metadata`, `auth.cimd`: no remote uses OAuth
- n/a `auth.secret_in_url`: no templated URL

### tool hygiene: 86 (weight 30)

- pass `tools.descriptions`: every tool has a description
- pass `tools.description_length`: descriptions are concise
- pass `tools.schemas`: every tool has an object input schema
- warn `tools.annotations`: only 12 of 22 tools declare readOnlyHint or destructiveHint
- warn `tools.directory_hints`: 12 of 22 tools declare all four hints; missing: get_agent_policies (readOnlyHint, destructiveHint, idempotentHint, openWorldHint); get_agent_identity (readOnlyHint, destructiveHint, idempotentHint, openWorldHint); get_agent_capabilities (readOnlyHint, destructiveHint, idempotentHint, openWorldHint); …
- pass `tools.token_cost`: about 2,835 tokens to load every tool
- pass `tools.api_dump`: tools are not a one-to-one API dump

### stability: 75 (weight 15)

- warn `stability.changes`: 13 tool changes in 30 days
- pass `stability.rug_pull`: no tool changed its meaning under the same name

### dependencies: n/a (weight 15)

- n/a `deps.known_vulns`, `deps.mcp_sdk_version`, `deps.resolvable`: no npm or PyPI package

- tools: 22, about 2,835 tokens to load them all
- tool set hash: 2375fc7ff965fb53855d20e8452b23dd
- tools last changed: 2026-09-29T15:10:45.590Z
- badge: [![protogrid quality](https://protogrid.dev/badge/io.github.mosaro0224/averis-protocol.svg)](https://protogrid.dev/servers/io.github.mosaro0224/averis-protocol)
- Checks run on what our credential-free, read-only probes observe; tools are never called and no code audit is performed.

### Tool changes

- 2026-09-29 `averis_passport_prepare_policy_commit` added
  - Get unsigned calldata to commit a capability policy hash to AgentPolicyRegistry on Robinhood Chain Testnet (chain 46630). Returns a ready-to-broadcast unsigned transaction. The agent signs and broadcasts from their own wallet. Policy commitments are irreversible once confirmed onchain.
- 2026-09-29 `averis_passport_prepare_mint` added
  - Get unsigned calldata to mint an ERC-8004 identity token on Arc Testnet or Robinhood Chain Testnet (or both). The API returns a ready-to-broadcast unsigned transaction. The agent signs it from their own wallet and broadcasts it — the API never holds a key. Call averis_passport_verify_identity first to confirm identity does not already exist.
- 2026-09-29 `averis_passport_verify_identity` added
  - Check whether an agent wallet has a registered ERC-8004 identity on Arc Testnet and/or Robinhood Chain Testnet. Returns per-chain identity records, a verified boolean, and verifiedChains array. No auth required — anyone can verify any wallet.
- 2026-09-28 `get_agent_credit_capacity` added
  - Get current Averis credit capacity for an agent: available credit, exposure, credit limit, risk tier, advance rate, and vault liquidity. Combines Averis Bank data with Passport identity.
- 2026-09-28 `get_agent_receipts` added
  - Get verifiable economic receipts for an agent from AgentReceiptRegistry (onchain anchors) merged with offchain metadata. Verification states: SELF_REPORTED, AVERIS_VERIFIED, EXTERNAL_ATTESTER.
- 2026-09-28 `get_agent_counterparties` added
  - Get counterparty graph for an agent: agents/services they have transacted with, interaction count, volume, disputes, and relationship status.
- 2026-09-28 `get_agent_transactions` added
  - Get economic transaction history for an agent. Supports filtering by type, status, counterparty. Types: JOB_PAYMENT, FINANCING, CREDIT_REPAYMENT, ESCROW, REFUND, API_PURCHASE, COMPUTE_PURCHASE, AGENT_TO_AGENT, TRADING, OTHER.
- 2026-09-28 `get_agent_risk` added
  - Get risk profile for an agent from Averis Bank: risk tier (UNRATED/ELIGIBLE/ACTIVE/HIGH_UTILIZATION/AT_LIMIT), credit capacity, exposure, and contributing risk factors.
- 2026-09-28 `get_agent_reputation` added
  - Get evidence-based reputation for an agent: jobs completed/failed/disputed, payments, financing repaid, outstanding obligations, counterparties, receipts. Not a score — raw evidence.
- 2026-09-28 `get_agent_policies` added
  - Get onchain EIP-712 policy commitments for an agent from AgentPolicyRegistry (Robinhood Chain Testnet). Includes version, expiry, revocation status, and policy hashes.

Full history: https://api.protogrid.dev/v1/servers/io.github.mosaro0224%2Faveris-protocol/changes

## Remotes

- https://api.averisprotocol.xyz/mcp (streamable-http, auth none, reachable true, uptime30d 0.95652175)

## Packages

_none_

## Tools (22)

- `averis_check_eligibility`: Check whether an agent address is eligible for financing. Returns credit limit, current exposure, available credit, active job count, and remaining job slots.
- `averis_discover`: Discover Averis Protocol capabilities, contract addresses, financing parameters, authentication requirements, and the complete agent journey. Call this first to understand how to interact with Averis.
- `averis_get_quote`: Get a financing quote for a job. Returns the approved amount, financing fee, total repayment obligation, and the on-chain calldata the agent must submit to create the spending pool.
- `averis_passport_prepare_mint`: Get unsigned calldata to mint an ERC-8004 identity token on Arc Testnet or Robinhood Chain Testnet (or both). The API returns a ready-to-broadcast unsigned transaction. The agent signs it from their own wallet and broadcasts it — the API never holds a key. Call averis_passport_verify_identity first to confirm identity does not already exist.
- `averis_passport_prepare_policy_commit`: Get unsigned calldata to commit a capability policy hash to AgentPolicyRegistry on Robinhood Chain Testnet (chain 46630). Returns a ready-to-broadcast unsigned transaction. The agent signs and broadcasts from their own wallet. Policy commitments are irreversible once confirmed onchain.
- `averis_passport_verify_identity`: Check whether an agent wallet has a registered ERC-8004 identity on Arc Testnet and/or Robinhood Chain Testnet. Returns per-chain identity records, a verified boolean, and verifiedChains array. No auth required — anyone can verify any wallet.
- `averis_pool_status`: Get the current state of a job-specific spending pool: balance, amount spent, per-transaction limit, allowed recipients, expiry, and frozen status.
- `averis_position_status`: Get the financing position for a job: principal, fee, repayment status, pool address, and whether the position is active, repaid, or in default.
- `averis_protocol_status`: Get live protocol statistics: total value locked, available liquidity, outstanding principal, utilization rate, and Hood security status.
- `averis_repay`: For OBLIGATION-mode financing positions (jobs without on-chain lien), returns the repayObligation() calldata the agent must submit after job settlement to repay principal and fee. Requires EIP-712 auth.
- `averis_request_funding`: Validate a funding request and return the draw() calldata for the agent to submit on-chain. This creates the controlled spending pool. REQUIRES EIP-712 authentication: include agentAddress, nonce, expiry, and signature in arguments.
- `averis_verify_job`: Verify a job is eligible for Averis financing. Checks that the job exists, is funded, has not expired, the agent is the provider, and the payout receiver is set to the ReceivableRouter (lien established). Returns the maximum advance amount.
- `get_agent_capabilities`: Get declared capabilities for an agent (research, coding, payments, DeFi, etc.). Capabilities are self-declared and can reference attestation evidence.
- `get_agent_counterparties`: Get counterparty graph for an agent: agents/services they have transacted with, interaction count, volume, disputes, and relationship status.
- `get_agent_credit_capacity`: Get current Averis credit capacity for an agent: available credit, exposure, credit limit, risk tier, advance rate, and vault liquidity. Combines Averis Bank data with Passport identity.
- `get_agent_identity`: Resolve ERC-8004 identity for an agent across all supported chains (Robinhood Chain Testnet, Arc Testnet). Returns agentId, wallet, metadataURI, and verification status per chain.
- `get_agent_passport`: Get the complete Agent Economic Passport for a wallet address. Returns identity, capabilities, policies, reputation evidence, risk tier, and Averis Bank integration.
- `get_agent_policies`: Get onchain EIP-712 policy commitments for an agent from AgentPolicyRegistry (Robinhood Chain Testnet). Includes version, expiry, revocation status, and policy hashes.
- `get_agent_receipts`: Get verifiable economic receipts for an agent from AgentReceiptRegistry (onchain anchors) merged with offchain metadata. Verification states: SELF_REPORTED, AVERIS_VERIFIED, EXTERNAL_ATTESTER.
- `get_agent_reputation`: Get evidence-based reputation for an agent: jobs completed/failed/disputed, payments, financing repaid, outstanding obligations, counterparties, receipts. Not a score — raw evidence.
- `get_agent_risk`: Get risk profile for an agent from Averis Bank: risk tier (UNRATED/ELIGIBLE/ACTIVE/HIGH_UTILIZATION/AT_LIMIT), credit capacity, exposure, and contributing risk factors.
- `get_agent_transactions`: Get economic transaction history for an agent. Supports filtering by type, status, counterparty. Types: JOB_PAYMENT, FINANCING, CREDIT_REPAYMENT, ESCROW, REFUND, API_PURCHASE, COMPUTE_PURCHASE, AGENT_TO_AGENT, TRADING, OTHER.