1c-mcp-toolkit

1c-mcp-toolkit is a skill for Claude Code, Codex from Desko77/claude-code-skills-1c. It costs 330 tokens per session (6,764 once invoked), scanned B, original, MIT.

A local HTTP API for working with a running 1C:Enterprise database through the MCP Toolkit processing file. 1C:Enterprise is a platform for business applications, and this tool can access its live runtime context.

In plain words
What is it for?
Use it for live database queries, diagnostics, tests, metadata lookup, object-link navigation, and finding references to a 1C object.
Why use it?
It lets an agent query live data, run exported code, inspect metadata, and navigate object links when development-project tools are not enough.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions CLAUDE.md.

Good fit Use it for live database queries, diagnostics, tests, metadata lookup, object-link navigation, and finding references to a 1C object.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/desko77/claude-code-skills-1c/1c-mcp-toolkit
Install

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.

Any agent
npx skills add Desko77/claude-code-skills-1c --skill 1c-mcp-toolkit
Clone the repo
git clone --depth 1 https://github.com/Desko77/claude-code-skills-1c

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for 1c-mcp-toolkit

README.md
[![agentmods](https://agentmods.dev/badge/skills/desko77/claude-code-skills-1c/1c-mcp-toolkit/github.svg)](https://agentmods.dev/skills/desko77/claude-code-skills-1c/1c-mcp-toolkit)
Your own site
<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.

agentmods 80×15 button for 1c-mcp-toolkit

Your own site · 80×15
<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>
Per session 330 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 6,764 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 2 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
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 content
    Fix: 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.
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce 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

Measured 11d ago against content hash 0540190b431a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

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.

The scan reads SKILL.md. This mod also ships 3 executable files (scripts/health-probe.ps1, scripts/start-1c.ps1, scripts/stop-1c.ps1), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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"
Origin

Copies of this mod

1 near-identical copy found in the catalogue:

skills/1c-mcp-toolkit/SKILL.md · 505 lines

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":

  1. 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.

  2. 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
    
  3. 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.

  4. 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).

  5. Ошибка "функция не определена" / connection refused - чаще всего toolkit просто не запущен: сначала health-probe и перезапуск, потом разбор кода.

  6. Не предлагать рестарт rphost/rmngr при обычном обновлении конфигурации - это не нужно (зона администраторов).

Read the full file on GitHub · 505 lines

Files

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.

Changes

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.

  1. 11d ago First seen · 505 lines · 330 tokens per session scan B 0540190b431a

Subscribe to this mod's changes

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.