Skip to main content

Agent Skill Instructions

When an AI agent connects to the Cred Protocol MCP server, it automatically receives the following instructions during initialization. These guide the agent on tool selection, score interpretation, and best practices.
These instructions are delivered via the MCP instructions field — no extra configuration needed. You can also use this page as a reference when building custom agents.

When to Use These Tools

Use Cred Protocol tools when users ask about:
  • Wallet creditworthiness, trust, or risk assessment
  • Financial health or portfolio analysis of an Ethereum address
  • Identity verification or attestation checks
  • DeFi lending eligibility or underwriting decisions
  • Comparing multiple wallets or batch assessments

Tool Selection Guide

Start here — pick the right tool for the job:
User IntentToolCost
”Is this wallet trustworthy?”get_credit_scoreCheapest
”Compare these wallets”get_credit_scores_batchCheapest
”Tell me everything about this wallet”get_financial_summaryMedium
”What identity does this wallet have?”get_identity_attestationsCheapest
”How much is this wallet worth?”get_portfolio_valueCheapest
”What does this wallet hold on Base?”get_chain_portfolio_valueCheapest
Escalation pattern: For a thorough analysis, start with get_credit_score (with include_factors: true), then get_financial_summary for the full picture. Only call get_identity_attestations or get_portfolio_value if the user needs those specific details — the financial summary already includes identity and asset data.

Sandbox vs Live Tools

  • Sandbox tools (e.g., get_credit_score): Use mock data. Free, instant, deterministic. Use for development, demos, and testing.
  • Live tools (e.g., get_live_credit_score): Use real blockchain data. Require CRED_API_KEY. Use for production decisions.
Generate your API key from the Cred Protocol Dashboard.
If a live tool returns an authentication error, fall back to the sandbox equivalent and inform the user that the results are simulated.

Understanding Credit Scores

Scores range from 300 to 1000 (like traditional credit scores):
RangeLabelMeaning
920-1000ExcellentTop-tier on-chain reputation. Minimal risk.
840-919Very GoodStrong history, diversified activity.
750-839GoodSolid track record, moderate experience.
640-749FairLimited history or some risk signals.
300-639LowNew wallet, thin file, or negative events.
Score factors (available with include_factors: true):
  • Borrowing History — Loan repayment track record across DeFi protocols
  • Wallet Composition — Asset diversity and stablecoin ratio
  • Wallet Health — Collateralization ratios and liquidation distance
  • Interactions — Protocol breadth and ecosystem participation
  • Trust — Identity attestations (ENS, Gitcoin Passport, POAPs)
  • New Credit — Recent changes in borrowing behavior

Reading Financial Summaries

Key fields in the financial summary report:
FieldMeaning
net_worth_usdTotal assets minus total debt
total_asset_usd / total_debt_usdGross positions
total_collateral_usdAssets locked as collateral in DeFi
count_transactionsTotal on-chain transactions (activity proxy)
count_active_loansCurrent open DeFi loans
count_liquidationsHistorical liquidation events (red flag if > 0)
global_percentilesHow this wallet compares to the population

Identity Attestations

Attestations are verified on-chain identity credentials:
AttestationWhat It Proves
ENS NameOwns an Ethereum Name Service domain
BasenameOwns a Base network name (username.base.eth)
Gitcoin PassportPassed humanity verification (score >= 20)
POAPsAttended real-world or virtual events
WorldcoinVerified unique human via biometric proof
BrightIDVerified through social graph analysis
More attestations generally indicate a more established, trustworthy identity.

Supported Chains

Data is aggregated across 10 EVM networks:
ChainIDNotes
Ethereum1Primary chain, richest data
Optimism10L2
BSC56Binance Smart Chain
Polygon137L2
Base8453Coinbase L2
Arbitrum42161L2
Celo42220Mobile-first chain
Avalanche43114
Scroll534352zkEVM L2
Linea59144Consensys zkEVM L2

Input Format

All tools accept either:
  • Ethereum addresses: 0x742d35Cc6634C0532925a3b844Bc9e7595f32345 (42 characters, hex)
  • ENS names: vitalik.eth, username.base.eth

Best Practices

1

Don't over-call

A single get_credit_score with include_factors: true answers most questions. Only escalate to get_financial_summary if the user needs the full breakdown.
2

Batch when possible

Use get_credit_scores_batch instead of looping get_credit_score for multiple addresses.
3

Interpret, don't just relay

Translate scores and data into actionable insights. “This wallet has an Excellent score of 945 with no liquidation history — it’s a strong candidate for undercollateralized lending.”
4

Flag red flags

Highlight liquidations, high debt-to-asset ratios, low scores, or missing identity attestations.
5

Respect the score range context

A 750 is “Good” — don’t call it average. A 640 is “Fair” — don’t call it bad. Use the labels.