AnswersGuidesMCP serverCompare yields →
For AI agents

TokenBank MCP server: live data on tokenized assets for ChatGPT, Claude and other AI agents

Yes, TokenBank has an MCP server: https://mcp.tokenbank.world. Free, no API key, Streamable HTTP, 16 read-only tools over ~8,700 tokenized assets and stablecoins — yields, KYC gates, issuers, chains, tokenized stocks and treasuries, and the official registers of 160+ countries.

Connect

ChatGPT

Turn on developer mode for connectors in ChatGPT’s settings, then create a custom connector: URL https://mcp.tokenbank.world, authentication none.

Claude (claude.ai and desktop)

Settings → Connectors → Add custom connector, URL https://mcp.tokenbank.world.

Mistral Le Chat

Connectors → add a custom MCP connector with the URL https://mcp.tokenbank.world, no authentication.

Grok (xAI API) and other model APIs

APIs that accept remote MCP servers as a tool (xAI, OpenAI Responses, Anthropic Messages) take the URL https://mcp.tokenbank.world with server label tokenbank and no headers.

Any other MCP client

Apps built on DeepSeek, Qwen, Kimi, GLM or local models connect the same way if they support remote MCP servers: transport Streamable HTTP, URL https://mcp.tokenbank.world, no key.

Claude Code

claude mcp add --transport http tokenbank https://mcp.tokenbank.world

Cursor (~/.cursor/mcp.json)

{ "mcpServers": { "tokenbank": { "url": "https://mcp.tokenbank.world" } } }

VS Code (.vscode/mcp.json)

{ "servers": { "tokenbank": { "type": "http", "url": "https://mcp.tokenbank.world" } } }

Also reachable at https://tokenbank.world/api/mcp. Listed in the official MCP Registry as world.tokenbank/tokenbank, on Glama and on GitHub.

Tools

find_answer
Matches a natural-language question (e.g.
yield_picks_of_the_week
Per category (treasury tokens, staking, private credit, yield stablecoins, reinsurance, stablecoin pools, fixed rate), the wallet-purchasable tokens with the highest stated yield right now, each with a risk level 1-5, the purchase route (DEX pool, deposit contract, Pendle market), contracts and page URL.
search_yield_products
Searches and filters TokenBank instruments for earning yield with crypto.
get_product_details
Full record for one instrument by ticker (case-insensitive): yield, risk, custody, availability, how to buy, source link, verification date.
get_agent_buying_guide
Reference data on how an AI agent or trading bot buys tokens with its own wallet: the six steps from wallet to confirmed purchase with the matching MCP/API call for each, the purchase paths (wallet only / owner onboarded once / platform account) with live counts, which asset classes a self-custody wallet can reach without an identity check, the highest-yield wallet-only candidates, decision checks with the fields that answer them (howToDecide: checks, not recommendations), common wallet-policy guardrails, and related guides with JSON URLs.
build_portfolio
Spreads an amount over several sources of yield.
get_purchase_steps
How an AI agent or bot buys one instrument on its own, step by step: the purchase path (wallet only / owner onboarded once / platform account), the three KYC gates, network and verified contract, the issuer route, the measured trading venues, the exit terms where researched (KYC to redeem, minimum, fee, settlement, from issuer documentation), the ordered steps (fund, verify contract, approve exact amount, simulate, deposit or swap, confirm, exit) and the guardrails a wallet policy should enforce.
compare_with_savings_account
Compares low-risk, instant-access crypto savings instruments with a typical bank savings rate, listing the trade-offs (custody, risk, access) next to the yield difference.
find_permissionless_assets
Instruments whose secondary market needs no KYC and which a self-custody wallet holds itself, read from verified gates.
compare_assets
Puts two to six instruments side by side on the fields that distinguish them: yield, risk, minimum, custody, the three KYC gates, target/area, issuer and verification date.
get_market_stats
Shape of the dataset: number of instruments by pillar, category and risk, how many need no KYC on the secondary market, and how fresh the figures are.
get_market_coverage
Per country, whether this dataset can read the local tokenized-asset market, and why not where it cannot (e.g.
get_country_registers
Official registers of tokenized assets and digital-asset firms for 250 jurisdictions (ISO 3166 + EU): supervising authority, public registers, which of them are read, and their entries.
search_realt_properties
The individual tokenized US rental properties behind the RealT entry, each with net rental yield (annual net rent / tokenized property value), token price, monthly rent and occupancy.
find_tokenized_security
Looks up whether a tokenized version of a company, ETF or bond exists, and from which issuer, by company name, ticker or ISIN.
compare_tokenized_access
For a security tokenized by more than one issuer, every token on it side by side (issuer, structure, KYC gates, custody, chain and each issuer's stated target/area), plus every Hyperliquid perpetual on it (fees, funding, leverage; no ownership).

Try asking

Without MCP: the same data as JSON at /api/v1/assets, every answer page at /api/v1/answers, and a map for language models at /llms.txt. How an agent buys a token on its own, step by step: /agents. Not investment advice.