Skip to content
verify mcp Beta VerifyMCP is currently in beta. If you notice any issues, get in touch and we’ll put it right.

TokenBank — tokenized real-world assets

REMOTE · MCP.TOKENBANK.WORLD

9,000 tokenized assets and DeFi yields: risk levels, AI-agent portfolios, how a bot buys each

0 this week 77 Trust /100

Last scanned (16 hours ago)

Scores higher than 67% of remote servers

Reachable. Last reached 21 Nov 2026.

Category Crypto and Web3

Trust breakdown (7 categories)

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. How we score → Why this is hard to score →

Endpoint Security63
  • The endpoint's TLS certificate is valid, in date, and uses a strong key. View diagnostics → Pass
  • No authorisation is required to call this server. Nothing on it is marked destructive, but we can't show that an anonymous caller can only read: full credit needs the server to list at least one tool and every tool to be verifiably read-only. We use a best-effort check of tool names and descriptions to tell read-only tools from tools that change things, so some genuinely read-only tools may not get full credit. Names that start with a read verb (get, list, read, search and similar) and accurate readOnlyHint annotations help. Meet that to earn full credit, or require authorisation. See how to fix → View diagnostics → Partial
  • HTTPS check failed: the endpoint is reachable over plaintext HTTP. See how to fix → View diagnostics → Fail
  • HSTS check failed: the Strict-Transport-Security header is absent. See how to fix → View diagnostics → Fail
  • DNSSEC check failed: this domain isn't protected by DNSSEC. See how to fix → View diagnostics → Fail
Transport & Reachability100
Schema Quality & AI Usability64
  • AI-judged instruction clarity (good).Pass
  • Context-footprint check failed: tool/resource definitions use about 2875 tokens (~179/item across 16 items; 16 tools + 0 resources), over budget; trim descriptions and params. See how to fix → Fail
  • Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management100
  • No destabilizing schema changes in the last 30 days.Pass
Tool Coverage100
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 100% of tool parameters carry a description.Pass
  • Structured output schemas are declared (75% of tools); any adoption earns full credit.Pass
Tool Safety100
  • No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
  • We read all 16 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
  • An AI judge read all 17 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities60
  • Spec-recency check failed: implements MCP spec 2025-06-18; the latest is 2026-07-28. See how to fix → Fail
What we tested

Checks we ran (13)

  • TLS certificate
  • Authorization
  • HTTPS
  • HSTS header
  • DNSSEC
  • Transport
  • Schema quality
  • Stability
  • Tool coverage
  • Injection markers
  • Destructive annotations
  • Judged manipulation
  • MCP protocol

Does not apply to this hosted endpoint (2)

  • Supply Chain SecurityScored on package channels only. This is a hosted endpoint, so there is nothing to install or inspect.
  • Provenance & TransparencyScored on package channels only. This is a hosted endpoint, so there is nothing to install or inspect.

The score does not measure everything. What the score does not measure →

Changelog

Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.

  • 17 Nov 26 0
    • HSTS header: unverified → fail ▼ security
    • HTTPS: pass → fail ▼ security
    • Authorization: unverified → partial ▲ security
    • Injection markers: unverified → pass ▲ security
    • Stability: unverified → pass ▲ security
    • Transport: fail → pass ▲ security
    • MCP protocol: unverified → fail ▼ functional
    • Endpoint reachability: unreachable → reachable ▲ functional
    • Tool coverage: unverified → 100 ▲ functional
  • 16 Nov 26 0
    • Endpoint reachability: reachable → unreachable ▼ security
    • HSTS header: fail → unverified ▼ security
    • Stability: pass → unverified ▼ security
    • Authorization: partial → unverified ▼ security
    • Tool safety: pass → unverified ▼ security
    • Transport: pass → fail ▼ security
    • HTTPS: fail → pass ▲ security
    • Capabilities: fail → unverified ▼ functional
    • Tool coverage: 100 → unverified ▼ functional
    • First check of Schema quality: unverified functional
  • 11 Nov 26 0
    • Stability: 0.97 → pass security
  • 10 Nov 26 0
    • The server rewrote its instructions, which are the text every model session reads security
    • Tool “build_portfolio” rewrote its description, which is the text the model reads security
    • Tool “compare_assets” rewrote its description, which is the text the model reads security
    • Tool “compare_tokenized_access” rewrote its description, which is the text the model reads security
    • Tool “compare_with_savings_account” rewrote its description, which is the text the model reads security
    • Tool “find_answer” rewrote its description, which is the text the model reads security
    • Tool “find_permissionless_assets” rewrote its description, which is the text the model reads security
    • Tool “find_tokenized_security” rewrote its description, which is the text the model reads security
    • Tool “get_agent_buying_guide” rewrote its description, which is the text the model reads security
    • Tool “get_country_registers” rewrote its description, which is the text the model reads security
    • Tool “get_market_coverage” rewrote its description, which is the text the model reads security
    • Tool “get_market_stats” rewrote its description, which is the text the model reads security
    • Tool “search_realt_properties” rewrote its description, which is the text the model reads security
    • Tool “search_yield_products” rewrote its description, which is the text the model reads security
    • Tool “yield_picks_of_the_week” rewrote its description, which is the text the model reads security
    • Schema quality: 222 → 179 ▲ functional
    • Schema quality: excellent → good functional
    • Stability: pass → 0.97 functional
    • Server version: 1.7.0 → 1.14.0 functional
    • “compare_tokenized_access” reworded the description of “offset” cosmetic
    • “find_permissionless_assets” reworded the description of “include_unverified” cosmetic
    • “find_permissionless_assets” reworded the description of “offset” cosmetic
    • “find_tokenized_security” reworded the description of “issuer” cosmetic
    • “find_tokenized_security” reworded the description of “offset” cosmetic
    • “get_country_registers” reworded the description of “offset” cosmetic
    • “search_realt_properties” reworded the description of “offset” cosmetic
    • “search_yield_products” reworded the description of “offset” cosmetic
    • “search_yield_products” reworded the description of “tier” cosmetic
  • 8 Nov 26 0
    • Tool coverage: 80% → 75% ▼ functional
    • New tool “yield_picks_of_the_week” functional
  • 6 Nov 26 0
    • We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
  • 28 Oct 26 0
    • The server rewrote its instructions, which are the text every model session reads security
    • Tool “get_agent_buying_guide” rewrote its description, which is the text the model reads security
    • Tool “find_answer” rewrote its description, which is the text the model reads security
    • Schema quality: 3016 → 3379 ▼ functional
    • Tool coverage: 86% → 80% ▼ functional
    • New tool “build_portfolio” functional
  • 26 Oct 26 0
    • The server rewrote its instructions, which are the text every model session reads security
    • Tool “find_answer” rewrote its description, which is the text the model reads security
    • Tool coverage: 92% → 86% ▼ functional
    • New tool “get_agent_buying_guide” functional
Diagnostics

Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.

Captured 21 Nov 2026 · Probed https://mcp.tokenbank.world

TLS valid

Negotiated TLS 1.3 with TLS_AES_128_GCM_SHA256 .

Subject Issuer Valid from Valid until Key Signature Serial
CN=tokenbank.world CN=WE1,O=Google Trust Services,C=US 5 Nov 2026 3 Feb 2027 ECDSA 256 ECDSA-SHA256 8c0ccd47d71f53050e58d92326605751
SANs: tokenbank.world, *.tokenbank.world
CN=WE1,O=Google Trust Services,C=US (CA) CN=GTS Root R4,O=Google Trust Services LLC,C=US 13 Dec 2023 20 Feb 2029 ECDSA 256 ECDSA-SHA384 7ff31977972c224a76155d13b6d685e3
CN=GTS Root R4,O=Google Trust Services LLC,C=US (CA) CN=GlobalSign Root CA,OU=Root CA,O=GlobalSign nv-sa,C=BE 15 Nov 2023 28 Jan 2028 ECDSA 384 SHA256-RSA 7fe530bf331343bedd821610493d8a1b

Background: What to check on a remote MCP endpoint →

DNSSEC insecure

Validation of mcp.tokenbank.world. — Not signed

Zone DS Keys Algorithms Outcome
. Trust anchor 20326, 38696 8, 8 Verified
world. DS published 422 8 Verified
tokenbank.world. No DS Unsigned (proven) parent-signed NSEC/NSEC3 proves an unsigned delegation
Authentication No authorisation required

The endpoint answered without asking for a token. Anyone who knows the URL can reach it.

Result No authorisation required
HTTP status 200

Background: How OAuth 2.1 works in the 2026 MCP spec →

Transports 2 probes
Transport URL Outcome Status Location
streamable-http https://mcp.tokenbank.world Verified 200
http (plaintext) http://mcp.tokenbank.world Served over HTTP 200
MCP tools · 16 exposed · ~2,789 tokens

The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →

Tool Tokens
build_portfolio ~222

Spreads an amount over several sources of yield. Returns the blocks (one product per category, no duplicate exposure, each checked at its own amount incl. gas, weight capped), an admixture above the risk budget (default 10 %), the median yield and risk per category, the blended yield compared with the single highest yield, the worst single failure as % of the amount, and an explainer on diversification (with failures on record), purchase order and rebalancing. Checks, not advice.

NameTypeReqDescription
admixture_pctnumber–Share above the risk budget, 0–20 % (default 10)
amount_usdnumber–Total to invest in USD (default 1000)
max_block_pctnumber–Highest weight of one block, % (default 30)
max_riskinteger–Highest risk level for the core blocks (default 3)
price_exposureboolean–Allow blocks that move with a crypto price, e.g. staking or pools with ETH (default false)

No output schema declared.

No examples provided.

compare_assets ~70

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.

NameTypeReqDescription
tickersarrayyese.g. ["USDY", "OUSG", "BUIDL"]
NameTypeReqDescription
comparedarrayyes–
notFoundarray––
readThisarray––

No examples provided.

compare_tokenized_access ~247

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). Also covers securities that exist on-chain only as a perpetual. Exact counts are in the response. targetArea describes the issuer's stated audience, not eligibility. Without `query` it lists every such security; sector and industry filters are available.

NameTypeReqDescription
industrystring–Only securities in this industry, e.g. "bitcoin-miners", "semiconductors", "memory-storage".
limitinteger–Max results (default 10)
offsetinteger–Number of matches to skip; the nextOffset of a previous answer continues from there (absent at the end).
querystring–Company name, underlying ticker or ISIN — e.g. "Apple", "AAPL", "US0378331005". Omit to list all.
sectorstring–Only securities in this sector, e.g. "crypto" or "funds".
NameTypeReqDescription
matchedintegeryes–
nextOffsetinteger–Pass as offset to fetch the next page; absent when there is no more
underlyingsarrayyes–

No examples provided.

compare_with_savings_account ~67

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.

NameTypeReqDescription
bank_rate_pctnumber–Your bank's rate in percent (default 2.0)
NameTypeReqDescription
bankRatePctnumberyes–
honestTradeoffsarray––
instrumentsarrayyes–

No examples provided.

find_answer ~172

Matches a natural-language question (e.g. "can I buy Tesla as a token", "best stablecoin yield on Base", "euro stablecoins MiCA", "pre-IPO OpenAI token") against TokenBank answer pages. Returns the best-matching questions with the first sentence of each computed answer (figures from the live dataset), the page URL and a JSON URL with every row, plus matching guides (e.g. how to verify a contract, what happens if an issuer fails), each with a JSON URL. Questions in Arabic, German, Spanish, Japanese, Chinese, Korean, Thai, Vietnamese or Indonesian also return pages written in that language (localPages).

NameTypeReqDescription
limitinteger–How many answers (default 3)
querystringyesThe question, in plain words

No output schema declared.

No examples provided.

find_permissionless_assets ~206

Instruments whose secondary market needs no KYC and which a self-custody wallet holds itself, read from verified gates. For real-world assets the gate to mint and the gate to trade on a secondary market often differ, so a fund can be permissioned at the issuer while its token trades freely. Instruments whose gate is unverified are excluded by default. This is a property of the token, not a statement about who may buy it; the issuer's terms and local law decide that.

NameTypeReqDescription
include_unverifiedboolean–Default false. When true, also returns instruments whose secondary-market gate is unknown, flagged as unverified.
limitinteger–Max results (default 20)
min_yield_pctnumber–Minimum comparable yield in percent
offsetinteger–Number of matches to skip; the nextOffset of a previous answer continues from there (absent at the end).
pillarstring–Limit to one category pillar
NameTypeReqDescription
confirmedOpeninteger–Secondary-market gate verified as no KYC
countintegeryes–
nextOffsetinteger–Pass as offset to fetch the next page; absent when there is no more
resultsarrayyes–
totalMatchinginteger––
unverifiedinteger–Possibly open, not confirmed — excluded from results

No examples provided.

find_tokenized_security ~358

Looks up whether a tokenized version of a company, ETF or bond exists, and from which issuer, by company name, ticker or ISIN. Sources: issuer catalogues (Backed / xStocks, Ondo Global Markets, Dinari, Robinhood, Coinbase, Backpack, Reality (Bitget), ST0x, Jarsy, Midas, Lofty), Swiss SME share registers (Aktionariat), Japanese security tokens, El Salvador's CNAD register (registered offerings; sale not confirmed), European and Asian digital bonds from official registers, and an aggregated tier (CoinGecko). One company can be tokenized several times (e.g. Apple as seven tokens); each row states issuer, legal form, chain and targetArea (the issuer's stated audience, not an eligibility check) and its source authority: aggregated rows only observe that a token exists and carry no KYC gate or custody claim. Identity data only: yield, minimum and risk grade are absent, not zero.

NameTypeReqDescription
include_haltedboolean–Include instruments Backed has flagged as trading-halted. Default false.
issuerstring–Restrict to one issuer. Omitted: all issuers.
limitinteger–Max results (default 20)
linestring–Backed only. xstocks = the xStocks line; btokens = the older bToken DeFi line.
offsetinteger–Number of matches to skip; the nextOffset of a previous answer continues from there (absent at the end).
querystringyesCompany name, ticker or ISIN — e.g. "Apple", "AAPL", "US0378331005", "Silver Trust"
NameTypeReqDescription
cataloguesarray––
instrumentsarrayyes–
issuedByMoreThanOneIssuerarray––
matchedintegeryes–
nextOffsetinteger–Pass as offset to fetch the next page; absent when there is no more
readThisarray––

No examples provided.

get_agent_buying_guide ~157

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.

NameTypeReqDescription
limitinteger–How many candidates (default 10)
min_yield_pctnumber–Only list candidates at or above this stated yield, in percent

No output schema declared.

No examples provided.

get_country_registers ~247

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. Supports a country view, a name search across all registers (query without country) and a filter by kind (e.g. issuance). A register entry records a licence, registration or approval by an authority; it is not proof that a token was issued and does not state who may buy. Provider registers list companies, not instruments.

NameTypeReqDescription
countrystring–ISO code (DE, HK), English name or slug (germany, hong-kong). Omit to search every register.
kindstring–issuance = individual issues; issuer = registered issuers; provider = licensed firms; sandbox = sandbox participants; event = decisions/letters; candidate = full-text search hits, unconfirmed
limitinteger–Max entries (default 25)
offsetinteger–Number of entries to skip; the nextOffset of a previous answer continues from there
querystring–Free-text match on entry name, issuer, ISIN or register number
NameTypeReqDescription
countryobject––
entriesarrayyes–
nextOffsetinteger–Pass as offset to fetch the next page; absent when there is no more
readThisarray––
registersSearchedinteger––
totalMatchingintegeryes–

No examples provided.

get_market_coverage ~147

Per country, whether this dataset can read the local tokenized-asset market, and why not where it cannot (e.g. a permissioned bank consortium chain in Japan, sandbox issuance in Korea, no local-currency stablecoin in India, Vietnam, Indonesia or Thailand). Covers questions such as "what is tokenized in Japan / Korea / Brazil". Without `country` it lists every market.

NameTypeReqDescription
countrystring–Country slug or name, e.g. japan, korea, brazil, india, switzerland. Omit to list all.
readable_onlyboolean–Only markets whose instruments we can actually read (default false — the closed ones are the point)
NameTypeReqDescription
marketobject––
marketsarray––
summaryobject––

No examples provided.

get_market_stats ~42

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.

Input schema present but exposes no named parameters.

NameTypeReqDescription
byTierobjectyes–
totalintegeryesEvery instrument, both tiers

No examples provided.

get_product_details ~58

Full record for one instrument by ticker (case-insensitive): yield, risk, custody, availability, how to buy, source link, verification date.

NameTypeReqDescription
tickerstringyese.g. USDY, stETH, PAXG
NameTypeReqDescription
namestring––
tickerstringyes–
tierstring––

No examples provided.

get_purchase_steps ~176

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. Read-only: it does not build, sign or send a transaction, and it does not say who may buy.

NameTypeReqDescription
amount_usdnumber–Optional amount, used only to word the approval step
tickerstringyese.g. sUSDS, USDY, USYC
NameTypeReqDescription
guardrailsarray––
pathstringyes–
stepsarrayyes–
tickerstringyes–

No examples provided.

search_realt_properties ~191

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. Filters by city, yield and token price.

NameTypeReqDescription
citystring–City name, e.g. Detroit, Cleveland, Chicago
limitinteger–Max results (default 20)
max_token_price_usdnumber–Maximum price per token in USD
min_yield_pctnumber–Minimum net rental yield in percent
offsetinteger–Number of matches to skip; the nextOffset of a previous answer continues from there (absent at the end).
rented_onlyboolean–Only properties with at least one rented unit (default true)
sortstring–Sort by net yield (default), token price (cheapest first) or monthly rent
NameTypeReqDescription
issuerstringyes–
medianNetYieldPctnumber|null––
nextOffsetinteger–Pass as offset to fetch the next page; absent when there is no more
portfolioTotalinteger––
portfolioUrlstring––
resultsarray––
snapshotDatestring––
totalMatchingintegeryes–

No examples provided.

search_yield_products ~270

Searches and filters TokenBank instruments for earning yield with crypto. The default scope is the curated tier (rows that state a yield, minimum and risk); the tier parameter extends it to the imported issuer-catalogue rows (tokenized treasuries, yield stablecoins, gold, real estate, tokenized stocks, staking, DeFi/CeFi earn, alternative funds), which carry identity and classification only. Returns compact records with paging.

NameTypeReqDescription
limitinteger–Max results (default 20)
max_riskinteger–Maximum risk on a 1-5 scale (1=very low, 3=medium, 5=high)
min_yield_pctnumber–Minimum headline yield in percent
offsetinteger–Number of matches to skip; the nextOffset of a previous answer continues from there (absent at the end).
pillarstring–Limit to one category pillar
querystring–Free-text match on name, ticker, issuer or type
tierstring–Which tier to search. Default "curated": instruments that state a yield, minimum and risk. "imported" and "all" add the issuer-catalogue rows, which carry identity and classification only (no yield).
NameTypeReqDescription
countintegeryesRows returned
nextOffsetinteger–Pass as offset to fetch the next page; absent when there is no more
resultsarrayyes–
tierstring––
totalMatchingintegeryesRows that matched before the limit

No examples provided.

yield_picks_of_the_week ~159

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. Categories are ordered from low to high risk. A ranking by stated yield under published rules, not a recommendation.

NameTypeReqDescription
max_riskinteger–Leave out picks above this risk level (default 5)
per_categoryinteger–Picks per category (default 2)
refstring–Your agent name, added to the page links as utm_source

No output schema declared.

No examples provided.

Install

How do I install the TokenBank — tokenized real-world assets MCP server?

TokenBank — tokenized real-world assets is a hosted endpoint at https://mcp.tokenbank.world/, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

remote · mcp.tokenbank.world

# add to Claude Code
claude mcp add --transport http world-tokenbank-tokenbank 'https://mcp.tokenbank.world/'
Common questions

What is the TokenBank — tokenized real-world assets MCP server?

TokenBank — tokenized real-world assets is an MCP server listed in the public MCP registry as world.tokenbank/tokenbank. 9,000 tokenized assets and DeFi yields: risk levels, AI-agent portfolios, how a bot buys each. This page covers its hosted endpoint (https://mcp.tokenbank.world).

Is the TokenBank — tokenized real-world assets MCP server safe to use?

TokenBank — tokenized real-world assets scores 77 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

What tools does the TokenBank — tokenized real-world assets MCP server expose?

TokenBank — tokenized real-world assets exposes 16 tools: find_answer, yield_picks_of_the_week, search_yield_products, get_product_details, get_agent_buying_guide, and 11 more. Their descriptions and schemas cost roughly 2,789 tokens of context every time the server is loaded.

Does the TokenBank — tokenized real-world assets MCP server require authentication?

No. We connected to TokenBank — tokenized real-world assets without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

Is the TokenBank — tokenized real-world assets MCP server still maintained?

TokenBank — tokenized real-world assets is still listed as active in the MCP registry. We last reached this channel on 21 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

What did VerifyMCP test on the TokenBank — tokenized real-world assets MCP server?

VerifyMCP ran 13 checks on TokenBank — tokenized real-world assets, covering TLS certificate, Authorization, HTTPS, HSTS header and 9 more. Supply Chain Security and Provenance & Transparency do not apply to a hosted endpoint, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.