io.github.f-tiger/agiscorecard-web3-workbench
Measured conclusion: Deep-tested. L2 outcome: tools_ok.
AGI Scorecard Web3 Workbench: ten free deterministic review tools (stablecoin, gas, zkML, agents).
| Author | io.github.f-tiger |
|---|---|
| Access | remote |
| Publisher key required | No |
| Measured state | Deep-tested |
| L1 liveness | alive |
| L1 latency | 2497 ms |
| Last measured | 2026-10-24 |
Add to your agent
Copy this into your MCP client config:
{
"mcpServers": {
"agiscorecard-web3-workbench": {
"url": "https://web3.agiscorecard.com/mcp",
"transport": "streamable-http"
}
}
}
Measured tools (12)
searchread-onlySearch this server’s public AI/Web3 tools and citation pages. English and Chinese names supported. Empty query lists the available worksheets.
Parameters:
query(required) — string
Hints: read-only yes · destructive no · idempotent yes · open-world no
fetchread-onlyRetrieve a public tool reference by the ID returned from search. Contains methodology, limits, official source links and fictional worked examples; no user records. Cite the returned canonical URL.
Parameters:
id(required) — string
Hints: read-only yes · destructive no · idempotent yes · open-world no
reconcile_stablecoin_recordsread-onlyStable Reconcile compares your declared invoices with recorded stablecoin transfers. It separates partial payments, pending transfers and wrong-network records, with exact decimal totals. Use it for a local exception review before updating your books. No wallet sync, automatic matching, FX, refund processing, tax accounting or independent finality checks. Retrieve reconcile with fetch or read its example resource to obtain exact inputs. Parameters are processed remotely without application persistence.
Parameters:
invoices(required) — array — Invoicestransfers(required) — array — Transfers
Hints: read-only yes · destructive no · idempotent yes · open-world no
review_agent_evidenceread-onlyAgent Evidence reviews imported task outcomes within one task, version and date window. It deduplicates sample labels and shows failures, exclusions and uncertainty. It helps review a supplier comparison; it does not run evaluations or verify reviewer identities. No public reputation ranking, identity verification, calibrated prediction or Sybil detection. Retrieve evidence with fetch or read its example resource to obtain exact inputs. Parameters are processed remotely without application persistence.
Parameters:
task(required) — string — Task (preserve source text; decimal amounts must stay strings)version(required) — string — Version (preserve source text; decimal amounts must stay strings)asOf(required) — string — Review date (UTC) (preserve source text; decimal amounts must stay strings)maxAgeDays(required) — number — Maximum evidence age (days)records(required) — array — Records
Hints: read-only yes · destructive no · idempotent yes · open-world no
plan_fallback_routesread-onlyRoute Lab compares short supplier sequences using entered cost, success and latency assumptions. It checks the worst-case total against your budget before sorting feasible options by expected cost. It is an offline planning tool; no model or payment is called. Offline planning only. No live requests, model judge, payment, dynamic bandit or production routing. Retrieve route with fetch or read its example resource to obtain exact inputs. Parameters are processed remotely without application persistence.
Parameters:
currency(required) — string — Currency (preserve source text; decimal amounts must stay strings)budget(required) — string — Total budget (preserve source text; decimal amounts must stay strings)maxLatencyMs(required) — number — Total latency bound (ms)minSuccess(required) — number — Minimum success probability (0–1)maxAttempts(required) — number — Maximum attemptscandidates(required) — array — Candidates
Hints: read-only yes · destructive no · idempotent yes · open-world no
read_protocol_profilesread-onlyProtocol Ledger is a free, dated reference for five payment, agent-identity and token interfaces. Each record preserves its official specification, review date and interpretation limits. Filter the same snapshot in the browser or retrieve it through the JSON API. Five initial profiles; no market prices, exhaustive schema coverage, real-time protocol monitoring or paid endpoint. Retrieve protocol with fetch or read its example resource to obtain exact inputs. Parameters are processed remotely without application persistence.
Parameters:
purpose(required) — string — Purpose (preserve source text; decimal amounts must stay strings)status(required) — string — Status (preserve source text; decimal amounts must stay strings)asOf(required) — string — Review date (UTC) (preserve source text; decimal amounts must stay strings)maxAgeDays(required) — number — Maximum evidence age (days)
Hints: read-only yes · destructive no · idempotent yes · open-world no
check_data_permissionsread-onlyData Permit compares an intended AI use with your recorded grant conditions: region, expiry, revocation and consent status. It calculates a proposed split of received revenue and keeps incompatible shares unallocated. Matching fields does not establish a legal license. No legal opinion, rights verification, consent collection, access enforcement, token issuance or payment. Retrieve permit with fetch or read its example resource to obtain exact inputs. Parameters are processed remotely without application persistence.
Parameters:
use(required) — string — Use (preserve source text; decimal amounts must stay strings)region(required) — string — Region (preserve source text; decimal amounts must stay strings)asOf(required) — string — Review date (UTC) (preserve source text; decimal amounts must stay strings)currency(required) — string — Currency (preserve source text; decimal amounts must stay strings)receivedRevenue(required) — string — Revenue already received (preserve source text; decimal amounts must stay strings)datasets(required) — array — Datasets
Hints: read-only yes · destructive no · idempotent yes · open-world no
compare_compute_costsread-onlyCompute Lens compares measured workload runs using total entered compute, setup, storage and egress costs per accepted output. It filters mismatched workload labels, currencies, quality and memory limits. All examples are fictional; no live GPU quotes are supplied. No live GPU inventory, automatic benchmarking, reservation, infrastructure management or verified savings. Retrieve compute with fetch or read its example resource to obtain exact inputs. Parameters are processed remotely without application persistence.
Parameters:
workload(required) — string — Workload (preserve source text; decimal amounts must stay strings)model(required) — string — Model (preserve source text; decimal amounts must stay strings)currency(required) — string — Currency (preserve source text; decimal amounts must stay strings)minimumPassRate(required) — number — Minimum accepted fraction (0–1)runs(required) — array — Runs
Hints: read-only yes · destructive no · idempotent yes · open-world no
model_contributor_rewardsread-onlyIncentive Lab separates customer revenue from token subsidy, then allocates a declared reward budget using accepted work and quality weights. Contributor caps and exact budget conservation keep the scenario inspectable. The worksheet does not establish Sybil resistance or distribute tokens. No live subnet data, fraud detection, Bittensor emission replication, staking recommendation or token distribution. Retrieve incentives with fetch or read its example resource to obtain exact inputs. Parameters are processed remotely without application persistence.
Parameters:
currency(required) — string — Currency (preserve source text; decimal amounts must stay strings)customerRevenue(required) — string — Customer Revenue (preserve source text; decimal amounts must stay strings)tokenSubsidy(required) — string — Token Subsidy (preserve source text; decimal amounts must stay strings)computeCost(required) — string — Compute Cost (preserve source text; decimal amounts must stay strings)reviewCost(required) — string — Review Cost (preserve source text; decimal amounts must stay strings)otherCost(required) — string — Other Cost (preserve source text; decimal amounts must stay strings)budget(required) — string — Total budget (preserve source text; decimal amounts must stay strings)capPercent(required) — number — Maximum contributor share (%)contributors(required) — array — Contributors
Hints: read-only yes · destructive no · idempotent yes · open-world no
plan_zkml_costsread-onlyProof Plan estimates proving compute and onchain verification costs from your own measurements. It checks a per-job latency target and preserves model, input and verification-key hashes. It plans an integration; it does not generate or verify a zero-knowledge proof. No ZK proof generation or cryptographic verification. File hashing verifies bytes only; it is not proof of model correctness. Retrieve proof with fetch or read its example resource to obtain exact inputs. Parameters are processed remotely without application persistence.
Parameters:
statement(required) — string — Statement (preserve source text; decimal amounts must stay strings)modelHash(required) — string — Model Hash (preserve source text; decimal amounts must stay strings)inputHash(required) — string — Input Hash (preserve source text; decimal amounts must stay strings)verificationKeyHash(required) — string — Verification Key Hash (preserve source text; decimal amounts must stay strings)verifierVersion(required) — string — Verifier Version (preserve source text; decimal amounts must stay strings)jobs(required) — number — JobsproveSeconds(required) — number — Proving time (seconds)verifyMs(required) — number — Verification time (ms)proofBytes(required) — number — Proof size (bytes)gasPerVerify(required) — number — Gas per verificationgasPriceGwei(required) — number — Gas Price GweinativePriceUsd(required) — number — Native token price (USD)computeHourlyUsd(required) — number — Proving compute (USD/hour)budgetUsd(required) — number — Budget (USD)latencySlaSeconds(required) — number — Latency target (seconds)
Hints: read-only yes · destructive no · idempotent yes · open-world no
decode_token_callread-onlyCall Lens decodes supported token-call shapes locally and compares the recipient, spender and atomic amount with your expectations. It distinguishes ERC-20 allowances from ERC-721 token IDs using the declared standard. It never connects a wallet or evaluates contract safety. No chain simulation, malicious-contract detection, token identity lookup, balance inspection or safety verdict. Retrieve calls with fetch or read its example resource to obtain exact inputs. Parameters are processed remotely without application persistence.
Parameters:
network(required) — string — Network (preserve source text; decimal amounts must stay strings)tokenStandard(required) — string — Token Standard (preserve source text; decimal amounts must stay strings)to(required) — string — Target contract (preserve source text; decimal amounts must stay strings)data(required) — string — Hex calldata (preserve source text; decimal amounts must stay strings)nativeValueAtomic(required) — string — Native value (atomic units) (preserve source text; decimal amounts must stay strings)expectedRecipient(required) — string — Expected recipient / spender (preserve source text; decimal amounts must stay strings)maxAtomicAmount(required) — string — Amount limit (atomic units) (preserve source text; decimal amounts must stay strings)
Hints: read-only yes · destructive no · idempotent yes · open-world no
compare_rwa_disclosuresread-onlyRWA Notes compares two sets of supplied asset disclosure fields while retaining units, dates and source references. It flags missing values and incompatible comparisons. It does not verify reserves, issuer solvency or redemption rights. No live asset feed, reserve audit, redemption verification, credit rating or investment recommendation. Retrieve disclosures with fetch or read its example resource to obtain exact inputs. Parameters are processed remotely without application persistence.
Parameters:
asOf(required) — string — Review date (UTC) (preserve source text; decimal amounts must stay strings)maxAgeDays(required) — number — Maximum evidence age (days)before(required) — array — Beforeafter(required) — array — After
Hints: read-only yes · destructive no · idempotent yes · open-world no
Measured by MCPYP probing. Untested fields are omitted, never estimated. Listing is always free; MCPYP never proxies calls or stores user tokens.