Skip to main content
Glama

Temsor API — Turkey & EU business data

by com.temsor

Sanctions Screening

sanctions_screen

Screens a name against six official sanctions lists — US OFAC, UN, EU, UK OFSI, Switzerland SECO and Canada — with transliteration-aware fuzzy matching.

Six official lists are reduced to one schema, so a name is checked everywhere at once instead of six integrations. Cyrillic and Arabic names are transliterated, titles and corporate suffixes are stripped, and known spelling families are unified — "Abd al-Rahman", "Abdul Rahman" and "Abdulrahman" reach the same record. Every hit explains itself: which name matched, whether it was an alias the source flags as weak, and how the birth year and country compared. Supply birthYear whenever you have it; it removes most false positives. asOf screens against the lists as they stood on a past date, which is the question auditors actually ask — note that this is bounded by when our archive begins, reported in coverage.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
asOfNoScreen against the lists as they stood on this date. Limited by when our archive begins.
nameYesName to screen — person or organisation.
typeNoRestrict to one subject type. Narrowing this removes most false positives.any
limitNo
countryNoKnown country or nationality.
sourcesNoDefaults to all lists.
minScoreNoScore floor. 0.92+ reads as a match, 0.80+ as possible.
birthYearNoKnown birth year. The single strongest false-positive filter available.

TDQS

A4.3/5.0
Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the full burden and discloses the matching algorithm (transliteration, fuzzy matching), the explanation of hits, and the `asOf` archive limitation. It does not mention authentication, rate limits, or explicit read-only behavior, but for a screening tool the key behavioral aspects are well covered.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is two structured paragraphs with all sentences contributing new information—no filler. It is somewhat lengthy but appropriately detailed for an 8-parameter tool, and it is front-loaded with the main purpose.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a tool with no output schema, the description explains the hit explanation and `coverage` field, and provides parameter usage notes. It lacks explicit response structure details and error conditions, but is sufficiently complete for an experienced engineer.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 88%, giving a high baseline, and the description adds meaningful guidance: `birthYear` as the 'single strongest false-positive filter', `type` narrowing removes false positives, and `asOf` being bounded by archive coverage. This goes beyond the schema, though not all parameters receive such enhancements.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description opens with a specific verb ('Screens a name') and resource ('six official sanctions lists'), enumerating the exact lists (OFAC, UN, EU, OFSI, SECO, Canada). This clearly distinguishes it from sibling verification and parsing tools.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Provides clear guidance on when to supply `birthYear` (strongest false-positive filter) and `asOf` for auditor questions, implying intended contexts. However, it doesn't explicitly contrast with alternatives or state when not to use it, so it falls short of a 5.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All Temsor API — Turkey & EU business data toolsInspect
Try in Browser
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A4/5.0
Disambiguation4/5

Most tools have clearly distinct purposes (e.g., bic_validate vs vin_validate), but there is notable overlap: tr_validate bundles Turkish validations that are also covered individually by iban_validate and tin_validate. Also, lei_validate and lei_lookup are closely related but distinct enough. Overall, agents can usually pick the right tool, but a few pairs could confuse.

Naming Consistency4/5

Tool names are consistently snake_case with predominately verb_noun patterns (e.g., validate, lookup, screen, parse, build). Some nouns like mcp_index, model_archive, and series_history break the verb pattern but are still predictable. Minor deviations from the noun_verb form (tr_invoice_build, shipping_identify) don't cause confusion. Very readable and consistent overall.

Tool Count3/5

With 27 tools, the set is heavy, exceeding the typical 3–15 well-scoped range. However, the server covers a broad domain: international standards validation, Turkey-specific business data (fuel, labor, invoices, addresses), and even MCP/LLM model archives. The count is justifiable given the scope, but it stretches coherence and may overwhelm agents.

Completeness4/5

The tool surface is remarkably comprehensive for the stated Turkey & EU business data purpose: validators for most ID types, VAT, IBAN, phone, VIN, sanctions; plus Turkey-specific operations like invoice build/parse, labor calculations, fuel prices, business days, and address parsing. Minor gaps exist (e.g., no general exchange-rate conversion, no credit-note-specific builder), but agents can accomplish core workflows without dead ends.

Resources