Cred Protocol

The Model Context Protocol (MCP) is a standardized way for AI agents (like Claude, GPT, or custom LLM applications) to:

- Discoveravailable tools and their capabilities
- Calltools with structured parameters
- Receivestructured responses

Unlike traditional REST APIs that require manual integration, MCP allows AI agents to automatically understand and use your tools through natural language.

All tools returnlive on-chain dataand require an API key (Authorization: Bearer <your-api-key>).

In addition to wallet credit scoring, Cred Protocol MCP services provide full access to theERC-8004 Identity and Reputation Registrieson Base — enabling AI agents to discover, assess, and rate other agents on-chain.

7 agent toolscover the complete lifecycle:

- Discovery—get_agent_count,list_agents,search_agents,get_agent
- Reputation scoring—submit_agent_reputationcomputes credit score, sybil risk, and identity attestations, then writes the results on-chain
- Reputation reading—get_agent_reputationreads aggregated feedback from the Reputation Registry
- Tracking—get_reputation_statustracks 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 assesswalletreputation, the agent tools operate on theagentlayer — helping AI systems discover, evaluate, and provide feedback on other AI agents in the ecosystem.

Cred Protocol MCP services can be accessed two ways:

Standard HTTP endpoints athttps://api.credprotocol.com/mcp/— works with any HTTP client:

curl -H "Authorization: Bearer YOUR_API_KEY" \ "https://api.credprotocol.com/mcp/score/vitalik.eth"

Each/mcp/route is a pass-through to the equivalent/api/v2/*endpoint, so it accepts the same credentials — an API key, an x402X-PAYMENT, or an MPPAuthorization: Payment …— and returns the same402challenge when none is supplied. Prices are listed atGET /mcp/tools; seeMachine Payments.

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:

{ "mcpServers": { "cred-protocol": { "url": "https://api.credprotocol.com/mcp", "headers": { "Authorization": "Bearer YOUR_API_KEY" } } } }

When an AI agent connects via MCP, the server automatically provides skill instructions that guide the agent on:

- Which tool to usefor different user intents
- How to interpretcredit scores, financial summaries, and attestations
- When to escalatefrom a quick score check to a full financial report
- Best practiceslike batching requests and flagging red flags

These instructions are delivered to agents during MCP initialization — no extra configuration needed. See the fullAgent Skill reference.

Allows users to generate music videos using Freebeat through MCP

Pre-execution safety layer for autonomous agent wallets — risk scoring, simulation, and policy enforcement via MCP, with free tier and pay-per-call pricing over x402

AgentBuy MCP enables both agents and humans to publish, discover, buy, and sell digital assets through a common machine-first protocol.

Connection your Amazon Seller Central and Ads accounts to your AI

MCP that knows everything about LEGO sets, parts, minifigures, and pricing. Help you manage your collections across popular sites such as Rebrickable and BrickEconomy

Allows access to DFIR / forensics data that was collected from endpoints. Used for SOC and forensic investigations.

Official hosted (remote) MCP server for restaurant menu management, exposing 39 tools over the DuckHub REST API so AI agents can build and publish a full menu.

Crypto research & trading MCP — swaps, earn, perps, Polymarket across major chains.

MCP server for AI agent payments — fund wallets, set spend limits, issue AgentCards, and settle x402 micropayments autonomously.