chainaware-ai-mcp.yml
ChainAware operates ONE hosted MCP server, reachable at two hostnames that serve the same 25,293-byte landing page and the same tool set: prediction.mcp.chainaware.ai (the name every provider document uses — docs, README, server.json, the MCP registry, AGENTS.md, SKILL.md) and mcp.chainaware.ai (the name in llms.txt and the site sitemap). Transport is legacy HTTP+SSE: GET /sse opens the stream and emits an endpoint event naming POST /messages/?session_id=
One-click install for Cursor, VS Code, Claude, and 20+ other MCP clients, powered by API Commons MCP Install — visit install.apicommons.org for more information.
Documentation
Documentation link · transport
Tools
predictive_fraud— AI fraud probability score (0-1) and AML forensic flags for a single wallet. Networks ETH, BNB, POLYGON, TON, BASE, TRON, HAQQ.predictive_fraud_batch— Schedule fraud analysis for up to 1,000 wallets; returns job_id + signature immediately.predictive_behaviour— Next-action predictions, risk profile, DeFi category segmentation and personalised recommendations for a wallet. Networks ETH, BNB, BASE, HAQQ, SOLANA.predictive_behaviour_batch— Schedule behaviour analysis for up to 1,000 wallets; returns job_id + signature immediately.predictive_rug_pull— Forecasts whether a liquidity pool or contract is likely to rug pull; returns risk indicators and liquidity events. Networks ETH, BNB, BASE, HAQQ.credit_score— AI-driven crypto trust score (1-9) combining inflows/outflows, fraud signals and social graph. ETH only.token_rank_list— Paginated, filterable list of tokens ranked by holder community strength (limit/offset, sort, category filter, name search). Networks ETH, BNB, BASE, SOLANA.token_rank_single— Community rank and top holders for a single token contract address and network.run_token_audit— Get-or-create: returns a cached full audit immediately, or queues a new one returning a job_id. Lowercase network ids eth, bsc, base, arbitrum, avalanche, optimism, polygon.get_token_audit_result— Poll for a completed token audit; full risk report when audit_status = "complete".agents_trust_score_list— Paginated list of ERC-8004 AI agents with 0-1000 on-chain trust scores and tiers (page/limit, sort_by, sort_order, registered_after).agents_trust_score_single— Detailed trust report for a single ERC-8004 agent by agent_id and chain_id.check_job_status— Progress of a batch job (completed / failed / pending counts). Requires job_id + signature.get_job_results— Wallet address list from a completed or partial batch job. Call only when status is completed or partial.
About MCP
The Model Context Protocol (MCP) is an open protocol Anthropic introduced for connecting LLM-based agents to external tools and data sources. Providers publish MCP servers that expose their API surface as structured, discoverable tools — an MCP-compatible client (Claude Desktop, Cursor, Cline, Continue, etc.) can connect to the server and call its tools without any per-provider integration code.
Browse every MCP server on the APIs.io network or compare with the broader Agent Skill surfaces of the same providers.
Work with this as data
Every MCP server here is available over the APIs.io API and to AI agents over MCP.