All services

Walks the visible book of every requested exchange for the given size, in both directions, and works out what remains of the raw spread: gross_spread_bps from top of book, then the taker fee of the entry tier on both sides, then the slippage the size causes on the buy book and on the sell book. net_spread_bps is the headline number, the gross value stands next to it because on its own it is misleading. Transfer costs are the part no public exchange interface publishes without a key: withdraw fee

Takes a route as an ordered list of waypoints, samples it at a chosen spacing and tests every sample against the currently active SIGMETs carrying a volcanic ash hazard. For each hit you get the affected segment as a from-to pair of waypoints, the SIGMET issuing centre and flight information region, the validity window, the reported base and top of the ash layer, and the raw text.

Verified residential US property record for one street address: assessed value, actual annual property tax, 5yr tax history, effective rate, deed/transfer history, and an owner-occupied (homestead-proxy) signal. Sourced from RentCast (county assessor + recorder records); not an official bill or valuation; never owner names/mailing. Commercial/uncovered addresses return a free charge-free diagnostic. npx @velinussage/locus-agent-skill add.

Takes one media file by URL or inline base64 and reads its C2PA manifest store. The answer says whether a manifest is present at all, whether the cryptographic checks pass — every failing check is returned with its code and explanation, so a hash mismatch on the image data is distinguishable from a broken claim signature — who the signing certificate names as issuer, its serial number, the signing algorithm and the signing time, the chain of ingredients a derived file inherited from, and every…

Takes two documents, by URL, inline base64 or raw text, extracts the text of each and compares them. Paragraphs are the unit: the answer lists every block that was removed, added, or kept but reworded, and for reworded blocks it names the individual words that went and came, so a single changed number in a long clause is visible instead of the whole clause being flagged. Alongside the content diff a structural comparison reports headings, paragraph, list and table-line counts on both sides.

Two answers in one call. Validation: the number is checked against the VIES service of the member state that issued it, with the consultation date returned. Treatment: given the supplier country, the customer country and whether the customer is a business, it states whether the supply is domestic with the local rate, an intra-community B2B supply where the reverse charge shifts the liability to the customer, a B2C supply taxed where the customer sits, or an export outside the EU.

Takes two to twelve answers and returns a field-by-field comparison. For JSON answers every leaf path is compared across responders: a path is agreed when all responders that supplied it carry the same value, conflicting when they differ, and partial when some omitted it. Numbers count as equal inside a relative tolerance you set.

Takes a list of MCP tool definitions, as returned by tools/list on any number of servers, and rewrites them into one common form. Servers disagree on where the schema lives — inputSchema, input_schema, parameters, schema or arguments are all in use — and a consumer reading only one of them loses the others silently; every spelling is accepted and the one found is reported.

Rebuilds an invoice from its lines and compares the result with the stated totals. Line by line it checks quantity times unit price against the line total, applies line and document discounts in the right order, groups the net amounts by tax rate and computes the tax per group, then compares net, tax and gross with what the document claims.

Compares a purchase order against a delivery note and an invoice, line by line. Lines are paired by article number where both sides carry one, and otherwise by text similarity — a text pairing is marked as such with its similarity score, because quietly matching on similar wording is exactly how a wrong invoice gets approved.

Computes what an import actually costs at the destination. The customs value is assembled from goods, freight and insurance on the chosen basis (CIF or FOB), duty is applied to it, and import VAT is applied to the duty-inclusive value, which is the ordering most calculations get wrong. Duty rates come from the live tariff: the UK Trade Tariff for GB and the USITC HTS for the US, with the commodity description returned so a wrong classification is visible.

Books a single POST to a URL you own, at a time you name, with a payload you supply. Delivery is retried up to five times with growing gaps and every attempt is recorded with its status. Lead time is between 10 seconds and 30 days, and at most 200 pending wakeups per target URL. The target must be a public https address: private, loopback and link-local addresses are refused, so this cannot be pointed at an internal network.

Key-value state for agents that need to survive between calls. Every write carries a time-to-live; the maximum is 30 days and there is no way to store something permanently. Values are opaque JSON up to 64 KB, at most 1000 live keys per namespace. Actions: set, get, list, delete. A get on a missing or expired key answers found=false, it is not an error. The namespace is a plain string chosen by the caller and is not authenticated — anyone who knows it can read it, so do not put secrets in it.

Plans the division of a long input for a given model. It reserves room for the system prompt, the expected answer and a safety margin, then works out how many chunks are needed and where to cut, preferring paragraph boundaries over line and sentence boundaries and never cutting inside a word. Optional overlap carries context across the seams.

Maps a caller-supplied Kp value to conventional G0–G5 bands, maps Dst to declared disturbance bands, and combines severity with geomagnetic latitude and infrastructure class. It does not retrieve observations, forecast a storm, model local ground conductivity, or predict equipment failure.

Tokenizes caller-supplied text and counts matches against a small declared English/German unigram lexicon. It reports coverage and a normalized polarity score; it does not understand context, sarcasm, negation, policy merit, or public opinion.

Validates output against a JSON Schema and reports each violation with its JSON path, the rule it broke and a sentence saying what to change. Accepts either a parsed object or the raw string a model returned: a payload wrapped in a code fence or surrounded by prose is unwrapped, and the wrapping is reported separately from schema errors so you fix the right layer. Draft 2020-12 and draft-07 are both supported, along with the common string formats.

Converts each OpenAPI operation into an MCP tool. Path, query and header parameters and the JSON request body are merged into one input schema, because MCP tools take exactly one; a name collision between a body field and a parameter is reported rather than silently overwritten. Internal $refs are expanded inline so each tool schema stands alone — an MCP client cannot resolve them.

Sorts unique scalar key/value entries through canonical JSON serialization and computes SHA-256. It verifies byte-level agreement with an optional claimed digest only; it does not prove block inclusion, timestamp, signer identity, or chain consensus.

Reads an OpenAPI 3.x document and reports what would stop a machine consumer. Errors: missing openapi, info or paths; a path that declares no method; an internal $ref that resolves to nothing; a parameter without a name, location or schema; a request body without content.

Takes the steps of one agent run and returns a scored report. It counts identical tool calls (same tool, same arguments) as loops, finds the longest run of consecutive failures, marks calls whose result was empty or null as wasted, and attributes cost per step and per tool so the expensive part is visible. Cost is taken from your figures when supplied, otherwise computed from token counts against the model price table.

Two checks in one. First the arguments are validated against the tool input schema and every violation is reported with its path and a sentence saying what to change. Second, values that satisfy the schema but look wrong are flagged: an unset required field filled with a placeholder like "string" or "TODO", a number at a suspicious order of magnitude, an address that fails its checksum shape, a destructive flag set to true, an empty string where content was expected.

Takes a machine definition, the current state, one event and an optional context, and computes a single step. Transitions may carry a guard, which is a declared comparison — field, operator, value — and never an expression: the field is a dotted path into context or payload, so a machine handed in by a stranger cannot execute anything on this server.

Scores every catalogue model against one task and returns a ranked shortlist. You state the task kind, optionally a per-call budget in USD, how much speed matters, the input size and any vendor restriction; the answer names a model, the estimated cost per call, and the sub-scores it was chosen on, so the ranking can be checked rather than trusted. Models that cannot hold the input are excluded and listed separately with the reason. Weights are yours to set and are echoed back.