Krasoft Russian Public Procurement

Поиск закупок (извещения)

search_tenders

Read-only

Поиск извещений о госзакупках РФ (44-ФЗ и 223-ФЗ) по тексту и фильтрам: регион, заказчик (ИНН), диапазон НМЦК, период. Возвращает список: номер и название извещения, НМЦК, заказчик, регион, ключевые даты (публикация, дедлайн подачи, итоги), победитель и цена контракта, если закупка разыграна. period по умолчанию "2y" — покрывает последние 2 года; "all" — весь корпус, заметно медленнее. includeTotal=true даёт точный счёт найденного (обрезан 10 000). Квоты: аноним — 20 поисков и 50 карточек в сутки; бесплатный аккаунт (ключ krsp_ с zakupki.krasoft.ru/me) — 100 поисков и 200 карточек; платный тариф — без лимитов. При превышении инструмент вернёт isError с инструкцией.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`fz`	No	Закон: 44 (госзакупки) и/или 223 (закупки госкомпаний)
`page`	No	Страница выдачи (0-based)
`query`	No	Текст поиска: предмет закупки, ключевые слова или номер извещения
`nmckTo`	No	НМЦК до, руб.
`period`	No	Период публикации: "2y" (default) — последние 2 года, "5y" — 5 лет, "older" — старше 5 лет, "all" — весь корпус (медленнее)	2y
`nmckFrom`	No	НМЦК от, руб.
`pageSize`	No	Размер страницы
`regionCodes`	No	Коды регионов РФ: 2 цифры ("77" — Москва) либо полный 13-значный код
`customerInns`	No	ИНН заказчиков
`includeTotal`	No	Точный счёт найденного (обрезан 10 000)

Schema Changelog

Changes observed during successful MCP inspections. Dates show when Glama detected each change.

Changed1 schema field changedJul 22, 2026

changedInput schema / properties / regionCodes / description

Previous value: -"Коды регионов РФ (2 цифры, напр. \"77\" — Москва)"New value: +"Коды регионов РФ: 2 цифры (\"77\" — Москва) либо полный 13-значный код"

First observedJul 21, 2026

TDQS

A4.7/5.0

Behavior5/5

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

Annotations declare readOnlyHint=true, and the description adds valuable behavioral details: quotas (anonymous vs free vs paid), performance warning for 'all' period, and error handling with instructions. No contradiction with annotations.

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

Conciseness5/5

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

The description is well-structured with key information front-loaded. Every sentence adds value, no fluff. It efficiently covers purpose, behavior, and parameter hints.

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

Completeness5/5

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

Given no output schema, the description adequately lists return fields. It covers all necessary context for usage: filters, defaults, quotas, error behavior, and performance. Complete for a search tool.

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 100%, so baseline is 3. The description adds value by clarifying default values, performance notes for 'period', and the cap of 10,000 for includeTotal. This goes beyond the schema descriptions.

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 clearly states it searches for Russian government procurement notices (44-ФЗ and 223-ФЗ) with filters like region, customer, NMCC range, and period. It lists return fields and distinguishes from sibling tools like search_contract_specs and get_tender.

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?

The description specifies default period ('2y') and notes performance implications for 'all'. It also explains quotas and error behavior on limit exceedance. However, it does not explicitly state when not to use this tool versus alternatives.

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

All Krasoft Russian Public Procurement tools Inspect

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

A4.4/5.0

Disambiguation5/5

Each tool targets a distinct aspect: customer profiles, execution summaries, contract cards, tender cards, market snapshots, and searches for specs, objects, and tenders. No two tools have overlapping purposes.

Naming Consistency4/5

Tool names mostly follow a verb_noun or noun_noun pattern (e.g., search_tenders, get_contract, market_snapshot). However, there is minor inconsistency with 'executions_summary' and 'market_snapshot' not using a verb prefix like the others.

Tool Count5/5

With 8 tools, the server covers search, retrieval, and aggregation for public procurement without being overwhelming or too sparse. Each tool serves a clear purpose.

Completeness4/5

The set covers search and retrieval for both tenders and contracts, plus profiles and aggregated summaries. Missing a dedicated supplier search tool, but the overall surface is solid for data access.

Resources

Need Help?