All Services

Analyzes feature availability records by filtering rows within a numeric interval and pivoting dates by dataset category, producing two local analytical reports from supplied data.

Runs two local analytical reports on feature availability data: a numeric interval filter and an equal-width histogram, for up to 200 rows at $0.01 USDC.

Filters feature availability records by a numeric interval and flags IQR-based outliers across populated_features or expected_features, returning two analytical reports for up to 200 rows.

Runs two local analytical reports on feature availability records — a numeric interval filter and a trailing mean series — over up to 200 supplied rows.

Runs two analytical reports on feature availability data — a numeric interval filter on populated_features or expected_features, plus a Pearson/correlation analysis between the two measures — for up to 200 supplied rows.

Generates two local analytical reports (numeric row ordering and date-by-category pivot) for supplied feature availability records with populated_features and expected_features fields, processing up to 200 rows.

Generates two local analytical reports — numeric row ordering and an equal-width histogram — for feature availability data (populated_features and expected_features) across up to 200 rows.

Runs two local analytical reports — numeric row ordering and two-measure correlation — on up to 200 feature availability records (populated_features vs expected_features) per call.

Runs two local analytical reports on feature availability data: a record quality audit and adjacent row change detection, for up to 200 rows.

Audits record quality and computes category-level frequency distributions for up to 200 feature availability records (populated_features, expected_features) using local analytical engines — no external lookups.

Runs two local analytical reports on feature availability data: a record quality audit and a daily sum series, for up to 200 rows of populated/expected feature counts.

Runs two local analytical reports on feature availability data: a record quality audit and a date-by-category pivot table, processing up to 200 rows per call.

Runs a record quality audit and duplicate key detection report on supplied feature availability data (populated_features, expected_features) for up to 200 rows.

Runs two independent analytical reports on supplied feature availability records: a record quality audit and exact row deduplication, for up to 200 rows per call.

Runs three analytical reports on feature availability records: record quality audit, exact row deduplication, and a base-100 index series — all computed locally against supplied data, no external lookups.

Runs three local analytical reports on feature availability data: a record quality audit, exact row deduplication, and a duplicate key report — all against up to 200 supplied rows.

Runs three independent analytical reports (record quality audit, exact row deduplication, and equal-width histogram) on supplied feature availability records containing populated_features and expected_features fields, for up to 200 rows.

Runs three local analytical reports on feature availability records: a record quality audit, exact row deduplication, and a grouped numeric summary of populated_features or expected_features values.

Runs three local analytical reports on feature availability records: a record quality audit, exact row deduplication, and IQR-based outlier flagging — for up to 200 rows of populated_features / expected_features data.

Runs three local analytical reports on feature availability data: a record quality audit, exact row deduplication, and numeric distribution analysis for populated_features or expected_features.

Runs three local analytical reports on feature availability records: record quality audit, exact row deduplication, and numeric interval filtering for populated_features or expected_features values.

Runs three local analytical reports on feature availability records: record quality audit, exact row deduplication, and numeric row ordering — all in a single call for up to 200 rows.

Runs two analytical reports on supplied feature availability records: a record quality audit and a grouped numeric summary, for up to 200 rows.

Runs a record quality audit and IQR-based outlier detection on up to 200 feature availability records (populated_features, expected_features), returning two independent analytical reports.

Runs two local analytical reports (record quality audit and numeric distribution summary) on up to 200 feature availability records containing populated_features and expected_features fields.

Runs two local analytical reports on feature availability records: a record quality audit and a numeric interval filter for populated_features or expected_features fields, covering up to 200 rows.

Audits data quality and normalises strings for up to 200 feature availability records, returning two independent analytical reports with no external lookups.

Runs three independent analytical reports (record quality audit, string normalisation, and adjacent row change detection) on up to 200 feature availability records containing populated_features and expected_features fields.

Runs three analytical reports (record quality audit, string normalisation, and category frequencies) on up to 200 feature availability records containing populated and expected feature counts.

Runs three local analytical reports on feature availability records — record quality audit, string normalisation, and exact row deduplication — for up to 200 rows of populated/expected feature data.

Runs three local analytical reports on feature availability records: a record quality audit, string normalisation, and IQR-based outlier detection — all against up to 200 supplied rows.

Runs three local analytical reports (record quality audit, string normalisation, and numeric distribution) on up to 200 feature availability records containing populated_features and expected_features fields.

Runs three bundled analytical reports (record quality audit, string normalisation, and secondary-measure weighted mean) on up to 200 feature availability records containing populated_features and expected_features fields.

Runs two local analytical reports on supplied feature availability data: a record quality audit and a trailing mean series, for up to 200 rows.

Runs two local analytical reports on feature availability data: string normalisation and daily sum series, for up to 200 rows.

Produces two analytical reports — string normalisation and grouped numeric summary — for supplied feature availability records (populated_features, expected_features) across up to 200 rows.

Runs two local analytical reports (string normalisation and numeric distribution) on up to 200 rows of feature availability data (populated_features, expected_features).

Computes trailing mean time-series and adjacent row change reports for feature availability data (populated_features vs expected_features) over up to 200 rows.

Computes a trailing mean time series and a date-by-category pivot table from supplied feature availability records (populated_features, expected_features) for up to 200 rows.

Computes a trailing moving-average time series and an equal-width histogram over feature availability data (populated_features or expected_features) for up to 200 rows, returning two independent analytical reports.

Computes a trailing moving average series and fills explicit missing values for feature availability records (populated_features / expected_features) over up to 200 rows.

Computes trailing mean time series and IQR-based outlier flags for feature availability records (populated_features or expected_features) across up to 200 rows, returning 2 independent analytical reports.

Computes a trailing mean time series and a keyed dataset comparison for feature availability records (populated_features vs expected_features) across up to 200 rows in two independent reports.

Computes a trailing mean time series and a two-measure correlation report for supplied feature availability data (populated_features vs expected_features) over up to 200 rows.

Computes Pearson correlation between populated_features and expected_features, and fills missing values in a chosen field using zero, mean, or median imputation — delivered as two separate analytical reports for up to 200 feature availability rows.

Computes confidence calibration bins for a naive-Bayes feedback theme classifier across quality, price, delivery, and support categories using up to 200 labelled text records.

Runs a grouped three-fold cross-validation with a naive-Bayes baseline classifier on up to 200 labelled feedback text records across four themes: quality, price, delivery, and support.

Audits up to 200 labelled text records for a 4-class feedback theme classifier (quality, price, delivery, support), computing evaluation metrics from supplied actual and predicted labels with class probabilities.

Computes the label distribution (class balance) across up to 200 labelled feedback text records categorized by quality, price, delivery, or support themes.

Exports up to 200 labelled customer feedback text records as a JSONL file, with each record tagged by feedback theme (quality, price, delivery, or support), for local ML evaluation and naive-Bayes baseline training.

Identifies low-confidence predictions in a naive-Bayes feedback theme classifier (quality/price/delivery/support) and returns a bounded review queue of up to 200 labelled records for human inspection.

Computes macro, micro, and weighted classification evaluation scores for up to 200 labelled feedback text records across four feedback themes.

Computes the multiclass Brier score for a feedback theme classifier across up to 200 labelled text records with actual labels, predicted labels, and class probabilities.

Computes multiclass log loss over up to 200 labelled feedback-theme text records using local naive-Bayes evaluation tools.

Computes per-label precision and recall metrics for a feedback theme classifier across up to 200 labelled text records with actual and predicted labels.

Evaluates a classifier's performance on feedback theme labels (quality, price, delivery, support) across user-supplied groups using local naive-Bayes metrics

Trains a local naive-Bayes text classifier on up to 200 labelled feedback records and classifies new query texts into quality, price, delivery, or support themes.

Fetches live blockchain fee and gas price data from on-chain consensus state via the AmanChain node, paid per call in USDC.

Monitors and audits remote MCP endpoints for security changes, cross-referencing SEC filings and domain signals to produce a vendor due-diligence verdict.

Scans an AI agent skill or tool and returns a consensus-based risk/quality assessment across multiple evaluation dimensions

Provides pay-per-call access to the Mythos Agent Toolkit, exposing 300+ MCP-compatible tools through a single proxied endpoint on the FiatDock marketplace.

Fetches and summarizes pricing or price-related content from a publicly accessible URL using a heuristic extraction approach

Validates and lints an MCP (Model Context Protocol) tool schema for correctness, completeness, and conformance

Generates a paid x402 compliance report for a target URL or service, checking whether it correctly implements the HTTP 402 payment-required protocol

Scans an AI agent skill or tool's supply chain for security and integrity risks, returning a risk assessment report.

Diagnoses and repairs MCP/API errors, returning corrected calls or actionable fixes for failed agent tool invocations

Generates a concise AI-powered research brief on a given topic for $0.01 per call via x402 micropayment

Looks up identity information for a given Base blockchain address — resolving who owns or controls it.

Checks whether a blockchain address is safe or flagged as risky, returning a safety assessment for a given address on a specified chain.

Evaluates up to 64 explicitly fictional strategy/game choices against caller-declared integer utilities, reporting best actions, chosen utility, regret, and observed-minus-declared error.

Returns official U.S. National Weather Service forecast periods or active alerts for a given latitude/longitude, targeted at technology industry buyers planning field work.

Extracts figure captions from a webpage or HTML that contain a specified literal search term, with optional attribute filtering.

Extracts and counts word frequency from HTML figure caption elements on a given webpage or supplied HTML snippet

Parses an HTML page to find <figure> elements whose specified attribute contains a given literal term, returning bounded matching results.

Extracts structured data from HTML <figure> elements on a public web page or supplied HTML, filtered by a search term and attribute value.

Computes adjacent (period-over-period) row-level changes for file ingestion metrics (loaded bytes or parse errors) across up to 200 supplied dated records.

Computes a base-100 indexed time series for file ingestion metrics (loaded bytes or parse errors) across up to 200 supplied records, returning local descriptive analytics with no enrichment or forecasting.

Computes category frequency counts for file ingestion records, summarizing how often each source category appears across up to 200 supplied typed rows.

Generates a date-by-category pivot report for file ingestion records, summarizing a chosen numeric metric (loaded bytes or parse errors) broken down by source category across dates.

Analyzes up to 200 file ingestion records and returns a duplicate key report identifying repeated row IDs across the dataset.

Computes grouped descriptive statistics (e.g. min, max, mean, count) for a chosen numeric field across up to 200 file ingestion records, segmented by source group.

Computes IQR-based outlier flags on file ingestion metrics (loaded_bytes or parse_errors) for up to 200 typed records

Compares two keyed datasets of file ingestion records (by row_id) and returns a descriptive analytics report highlighting differences in loaded_bytes and parse_errors.

Computes a descriptive numeric distribution report for a specified numeric field across up to 200 file ingestion records (loaded_bytes or parse_errors).

Filters file ingestion records to only those whose specified numeric field falls within a given [minimum, maximum] interval, returning a local descriptive analytics report.

Sorts up to 200 file ingestion records by a chosen numeric field (loaded_bytes or parse_errors) and returns a descriptive analytics report.

Performs a local descriptive analytics quality audit on up to 200 file ingestion records, reporting on parse errors and data completeness without enrichment or forecasting.

Computes a trailing (rolling) mean series over loaded_bytes or parse_errors for up to 200 file ingestion records, returning local descriptive analytics with no enrichment or forecasting.

Purchases and delivers a read-only Python balance checkpoint tool pinned to a finalized Base block, correcting v1 large-uint256 rounding errors by using integer arithmetic throughout.

Returns the current price of a cryptocurrency asset

Returns the current foreign exchange (forex) rate for a currency pair

Searches academic literature on financial fraud detection topics using Crossref publisher metadata, returning DOI references and source attributions.

Retrieves recent academic publications on financial fraud detection using Crossref publisher metadata, returning DOI references and source attributions

Retrieves recent academic publications on financial market microstructure using Crossref publisher metadata, returning DOI references and source attributions.

Retrieves recent fintech news articles covering payments, banking, and regulation, curated specifically for platform operators, with publisher links and publication dates.

Fetches recent fintech news articles about payments, banking, and regulation, curated specifically for software developers and engineers

Returns guidance on how to find and vet licensed contractors and local service providers in any geographic area for homeowners and shoppers.

Computes the SHA-512 cryptographic hash of a given input string

Redacts personally identifiable information (PII) from text input, returning a sanitized version with sensitive data removed or masked.

Searches recent Google News RSS coverage of fintech and payments topics relevant to agent builders, returning publisher links and publication dates.