Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add Desko77/claude-code-skills-1c --skill 1c-mcp-toolkitgit clone --depth 1 https://github.com/Desko77/claude-code-skills-1cWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/desko77/claude-code-skills-1c/1c-mcp-toolkit)<a href="https://agentmods.dev/skills/desko77/claude-code-skills-1c/1c-mcp-toolkit"><img src="https://agentmods.dev/badge/skills/desko77/claude-code-skills-1c/1c-mcp-toolkit/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/desko77/claude-code-skills-1c/1c-mcp-toolkit"><img src="https://agentmods.dev/badge/skills/desko77/claude-code-skills-1c/1c-mcp-toolkit.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 5 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium analysis-evasion · line 1 Suspicious Unicode normalization or mixed-script contentFix: Review the flagged content for security risks. Ensure no credentials, secrets, or sensitive data are exposed.
- medium Data Exfiltration · line 49 Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
- medium Data Exfiltration · line 159 Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
- medium Data Exfiltration · line 199 Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
- medium Data Exfiltration · line 383 Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00330 | $0.06764 |
| Opus 5 | $0.00165 | $0.03382 |
| Sonnet 5 | $0.00066 | $0.01353 |
| Haiku 4.5 | $0.00033 | $0.00676 |
Grade B, and why
1c-mcp-toolkit scanned grade B with 2 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 11d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Sends data to an external URLmediumData exfiltration
A POST to an outside endpoint may be telemetry or may be exfiltration; either way the mod talks to somewhere, and you should know where.
curl ... -d '{"query":"ВЫБРАТЬ 1"}' Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -sS -m 2 "http://localhost:$p/health" >/dev/null 2>&1 && echo "порт $p жив" Copies of this mod
1 near-identical copy found in the catalogue:
- 1c-mcp-toolkit — 91% identical, 199 lines differ
How it starts
The opening of the file, as written. The whole thing — 505 lines — stays where its author put it; the contents beside it link to each section on GitHub.
1C MCP Toolkit - прямой HTTP API к живой базе 1С
REST API на http://localhost:6003/api/* через обработку MCP_Toolkit.epf,
запущенную в тонком (или толстом) клиенте 1С. Встроенный HTTP-сервер реализован
нативной компонентой MCPHttpTransport. Без модификации конфигурации, без COM,
без публикации через web-сервер.
Обработка MCP_Toolkit.epf - разработка ROCTUP, репозиторий: https://github.com/ROCTUP/1c-mcp-toolkit (там же исходники нативной компоненты и документация).
Используется когда LLM-агент работает с живой базой (тесты, диагностика, прямой вызов экспортных функций), и при этом классические EDT-инструменты не подходят (нет dev-проекта, нужны данные runtime, нужен реальный пользовательский контекст).
Протокол: агент делает сам, порты не переспрашивает
Правила против холостых ходов "запусти / проверь / какой порт":
-
Карта портов проекта. Сначала взять карту "среда/ИБ -> порт" из CLAUDE.md ТЕКУЩЕГО проекта (секция "MCP Toolkit") или памяти проекта. Есть карта - работать с нужным портом, probe пропустить. Нет карты - после probe предложить пользователю добавить ее в CLAUDE.md.
-
Health-probe вместо вопросов. Не спрашивать "toolkit запущен? какой порт?":
pwsh scripts/health-probe.ps1(обход типовых 6003/6004/6005/6010/6013/6023/6033/7003) или bash-цикл:for p in 6003 6004 6005 6010 6013 6023 6033 7003; do curl -sS -m 2 "http://localhost:$p/health" >/dev/null 2>&1 && echo "порт $p жив" done -
Ничего не живо - запустить самому.
scripts/start-1c.ps1 -AutoStart, если параметры базы (платформа, путь, пользователь) известны из карты/памяти. Спрашивать пользователя только при неизвестных параметрах. -
Полный цикл - самостоятельно. Обновить ИБ и проверить данные = один заход без ручного handoff:
stop-1c.ps1(или execute_code ЗавершитьРаботуСистемы) ->update_database(EDT MCP) ->start-1c.ps1 -AutoStart-> health -> запросы. Пользователя дергать только если неизвестны платформа/база/учетка ИЛИ он явно просил паузу (демо, живой показ). -
Ошибка "функция не определена" / connection refused - чаще всего toolkit просто не запущен: сначала health-probe и перезапуск, потом разбор кода.
-
Не предлагать рестарт rphost/rmngr при обычном обновлении конфигурации - это не нужно (зона администраторов).
What ships with it
6 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 11d ago First seen · 505 lines · 330 tokens per session scan B 0540190b431a
1c-mcp-toolkit is a skill published in the GitHub repository Desko77/claude-code-skills-1c (61 stars, last pushed today), licensed MIT. It adds 330 tokens to every session and 6,764 once invoked, about $0.0016 per session on Opus 5. A static security scan graded it B with 2 findings (sends data to an external url, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
kd2-rules
A skill for creating and editing data-exchange rules in the 1C Data Conversion 2.0 application through an HTTP toolkit. It exports the resulting rules as XML for use in another 1C configuration.
composing-1c-queries
A guide to writing queries in the 1C:Enterprise query language, which reads and combines data from a 1C configuration. It requires checking the configuration's actual metadata before writing a query.
kd31-rules
A skill for creating and editing data-exchange rules in 1C Data Conversion 3.1 through an HTTP-based toolkit. It can inspect rule structures, configure formats, and obtain EnterpriseData extension files.
1c-xdto-compile
A builder that creates a 1C XDTO package from an XML Schema (XSD). XDTO packages describe XML data structures used for integrations, web services, and external XML formats.
1c-xdto-decompile
A converter that turns a 1C XDTO package into a readable, editable XML Schema (XSD) file. XDTO is 1C's format for describing XML data used in integrations.
1c-subsystem-compile
A generator that creates a 1C subsystem—a section of the application menu—from a JSON definition. It writes the subsystem's XML files and registers it in the configuration or a parent subsystem.