> ## Documentation Index
> Fetch the complete documentation index at: https://docs.credprotocol.com/llms.txt
> Use this file to discover all available pages before exploring further.
# MCP Services Overview
> Access Cred Protocol credit scoring and agentic reputation through the Model Context Protocol for AI agents
# MCP Services
Cred Protocol provides **Model Context Protocol (MCP)** services that enable AI agents and assistants to access on-chain credit scoring, financial reporting, identity attestation, and agentic reputation data.
MCP is an open protocol that allows AI systems to securely interact with external tools and data sources.
[Learn more about MCP →](https://modelcontextprotocol.io)
## What is MCP?
The Model Context Protocol (MCP) is a standardized way for AI agents (like Claude, GPT, or custom LLM applications) to:
* **Discover** available tools and their capabilities
* **Call** tools with structured parameters
* **Receive** structured responses
Unlike traditional REST APIs that require manual integration, MCP allows AI agents to automatically understand and use your tools through natural language.
## Why Use MCP Services?
AI agents can discover and use Cred Protocol tools without custom code
Users can ask "What's this wallet's credit score?" and the agent handles it
Real blockchain data from 10+ EVM networks — credit scores, reports, identity, and more
Comprehensive coverage: scoring, reports, identity, sybil detection, agent reputation
## Available Tools (21 Total)
All tools return **live on-chain data** and require an API key (`Authorization: Bearer `).
| Tool | Description |
| --------------------------- | ------------------------------------------------------------------------ |
| **Credit Scoring** | |
| `get_credit_score` | Get credit score (300-1000) for an Ethereum address |
| `get_credit_scores_batch` | Get scores for multiple addresses at once |
| `get_aggregate_score` | Single aggregated score across multiple addresses |
| **Reports** | |
| `get_financial_summary` | Comprehensive financial report with assets, DeFi positions, and activity |
| `get_comprehensive_report` | Full multi-chain credit report with per-chain breakdowns |
| `get_summary_report` | Aggregated metrics without per-chain details |
| `get_chain_report` | Detailed report for a single blockchain |
| `get_chain_summary` | Summary metrics for a single blockchain |
| **Portfolio** | |
| `get_portfolio_value` | Total portfolio value in USD across all chains |
| `get_chain_portfolio_value` | Portfolio value on a specific blockchain |
| `get_portfolio_composition` | Portfolio breakdown by asset type (tokens, DeFi, stablecoins, debt) |
| **Identity** | |
| `get_identity_attestations` | Verified identity credentials (ENS, Gitcoin Passport, POAPs) |
| `get_sybil_score` | Sybil detection score with behavioral indicators |
| **Graph** | |
| `get_transaction_graph` | Token transfer graph visualization (nodes + edges) |
| **Agents (ERC-8004)** | |
| `get_agent_count` | Total registered agents in the Identity Registry |
| `list_agents` | Paginated list of all registered agents |
| `get_agent` | Get info for a specific agent by ID |
| `search_agents` | Search agents by name or description |
| `submit_agent_reputation` | Submit on-chain reputation feedback (10 CU) |
| `get_agent_reputation` | Read on-chain reputation summary (1 CU) |
| `get_reputation_status` | Track status of a reputation submission |
All tools require an API key. Generate one from the [Cred Protocol Dashboard](https://app.credprotocol.com/dashboard).
## Agentic Reputation (ERC-8004)
In addition to wallet credit scoring, Cred Protocol MCP services provide full access to the **ERC-8004 Identity and Reputation Registries** on Base — enabling AI agents to discover, assess, and rate other agents on-chain.
**7 agent tools** cover the complete lifecycle:
* **Discovery** — `get_agent_count`, `list_agents`, `search_agents`, `get_agent`
* **Reputation scoring** — `submit_agent_reputation` computes credit score, sybil risk, and identity attestations, then writes the results on-chain
* **Reputation reading** — `get_agent_reputation` reads aggregated feedback from the Reputation Registry
* **Tracking** — `get_reputation_status` tracks asynchronous on-chain submissions
ERC-8004 defines a standard for registering AI agent identities on-chain as ERC-721 tokens. Each agent has an owner address and metadata (name, description, image) stored via tokenURI. The registry lives on Base (chain ID 8453).
Unlike credit scoring tools which assess *wallet* reputation, the agent tools operate on the *agent* layer — helping AI systems discover, evaluate, and provide feedback on other AI agents in the ecosystem.
## Access Methods
Cred Protocol MCP services can be accessed two ways:
### 1. HTTP/REST Endpoints
Standard HTTP endpoints at `https://api.credprotocol.com/mcp/*` — works with any HTTP client:
```bash theme={null}
curl -H "Authorization: Bearer YOUR_API_KEY" \
"https://api.credprotocol.com/mcp/score/vitalik.eth"
```
### 2. MCP Protocol
Native MCP protocol for AI agents like Cursor, Claude Code, Claude Desktop, or custom MCP clients. Uses streamable-http transport — a single endpoint that handles both request/response and streaming:
```json theme={null}
{
"mcpServers": {
"cred-protocol": {
"url": "https://api.credprotocol.com/mcp",
"headers": {
"Authorization": "Bearer YOUR_API_KEY"
}
}
}
}
```
## Agent Skill Instructions
When an AI agent connects via MCP, the server automatically provides skill instructions that guide the agent on:
* **Which tool to use** for different user intents
* **How to interpret** credit scores, financial summaries, and attestations
* **When to escalate** from a quick score check to a full financial report
* **Best practices** like batching requests and flagging red flags
These instructions are delivered to agents during MCP initialization — no extra configuration needed. See the full [Agent Skill reference](/mcp-services/agent-skill).
## MCP vs REST API
| Feature | MCP Services | REST API |
| ------------------ | ---------------------------- | ----------------------- |
| **Data** | Live on-chain data | Live on-chain data |
| **Authentication** | API key required | API key required |
| **Purpose** | AI agents and assistants | Production applications |
| **Protocol** | MCP (streamable-http) + HTTP | HTTP |
| **Billing** | Consumes Cred Units | Consumes Cred Units |
## Next Steps
Connect your AI agent to Cred Protocol MCP
Explore all available MCP tools
See practical usage examples
Use the REST API directly