Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@1c-buddy-mcp What is ТаблицаЗначений in 1С?"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Лёгкий standalone MCP-сервер для работы с 1C.ai из Codex и других MCP-клиентов. Запускается напрямую в Python через stdio: без Docker, веб-чата, OpenAI-совместимого шлюза и отдельного HTTP-сервера.
Проект основан на MCP/API-реализации
ROCTUP/1c-buddy. Последний проверенный
upstream commit: 7f2b0305cd80e3a9f2cebb2dc69603fd7c7ab054.
Инструмент | Назначение |
| Общие вопросы по платформе 1С и практическим сценариям |
| Объяснение объекта, метода, типа или конструкции 1С |
| Синтаксическая проверка или code review BSL-кода |
| Изменение BSL-кода по явному заданию |
| Поиск по документации платформы 1С:Предприятие |
| Поиск по базе знаний ИТС |
| Получение документа или раздела ИТС по |
| Сравнение документации между версиями платформы |
Related MCP server: 1C Buddy
Python 3.10 или новее;
Git;
действующий токен 1C.ai в переменной ONEC_AI_TOKEN;
Codex или другой MCP-клиент с поддержкой stdio.
git clone https://github.com/VVi3ard/1c-buddy-mcp.git "$HOME\.codex\mcp\1c-buddy-mcp"
Set-Location "$HOME\.codex\mcp\1c-buddy-mcp"
py -m venv .venv
& .\.venv\Scripts\python.exe -m pip install --upgrade pip
& .\.venv\Scripts\python.exe -m pip install .Сохраните токен в пользовательском окружении и перезапустите Codex:
[Environment]::SetEnvironmentVariable("ONEC_AI_TOKEN", "ВАШ_ТОКЕН", "User")Не добавляйте токен в Git, README или публичные конфигурации.
git clone https://github.com/VVi3ard/1c-buddy-mcp.git ~/.codex/mcp/1c-buddy-mcp
cd ~/.codex/mcp/1c-buddy-mcp
python3 -m venv .venv
./.venv/bin/python -m pip install --upgrade pip
./.venv/bin/python -m pip install .
export ONEC_AI_TOKEN='ВАШ_ТОКЕН'Для постоянного хранения переменной используйте защищённое хранилище или конфигурацию оболочки с ограниченным доступом.
Добавьте в C:\Users\<имя>\.codex\config.toml:
[mcp_servers.onec-ai-1c]
command = 'C:\Users\<имя>\.codex\mcp\1c-buddy-mcp\.venv\Scripts\python.exe'
args = ["-m", "onec_buddy_mcp"]
cwd = 'C:\Users\<имя>\.codex\mcp\1c-buddy-mcp'
startup_timeout_sec = 30
[mcp_servers.onec-ai-1c.env]
ONEC_AI_UI_LANGUAGE = "russian"
ONEC_AI_TIMEOUT = "30"
MCP_TOOL_CALL_MODE = "direct"Токен намеренно отсутствует в TOML: процесс получает ONEC_AI_TOKEN из
пользовательского окружения. После изменения конфигурации перезапустите Codex.
Для Linux/macOS укажите абсолютные пути к .venv/bin/python и каталогу
репозитория.
Установите зависимости разработки и запустите unit-тесты:
& .\.venv\Scripts\python.exe -m pip install -e ".[dev]"
& .\.venv\Scripts\python.exe -m pytest -m "not live" -qLive-тест выполняется только по явному запросу и использует токен окружения:
$env:RUN_LIVE_TESTS = "1"
& .\.venv\Scripts\python.exe -m pytest -m live -qПосле перезапуска Codex проверьте список MCP-инструментов и выполните, например:
ask_1c_ai: «Что такое ТаблицаЗначений?»;
check_1c_code: синтаксическая проверка короткой процедуры;
search_1c_documentation: поиск HTTPСоединение для нужной версии.
Переменная | Обязательная | Значение по умолчанию |
| да | — |
| нет |
|
| нет |
|
| нет |
|
| нет | пусто |
| нет | пусто |
| нет | пусто |
| нет |
|
| нет |
|
| нет |
|
| нет |
|
direct вызывает специализированные upstream-инструменты для синтаксиса,
документации и ИТС. standard формулирует обычный запрос к 1C.ai и полезен как
режим совместимости при изменениях upstream.
Успешный ответ каждого инструмента содержит секции Ответ, Ограничения инструмента и Требуемая проверка. Ограничения формируются MCP-сервером, а не
AI-моделью, и учитывают назначение конкретного инструмента. Чтобы вернуть ответы
в исходном виде, задайте ONEC_AI_INCLUDE_LIMITATIONS=false.
Проекты имеют разные структуры и не предназначены для полного git merge.
Изменения 1C.ai API и MCP-инструментов переносятся контролируемо по инструкции
docs/UPDATING_FROM_UPSTREAM.md.
ONEC_AI_TOKEN missing: задайте пользовательскую переменную и полностью
перезапустите Codex, чтобы новый процесс получил окружение.
HTTP 401/403: токен отклонён 1C.ai или не передан процессу.
HTTP 422: upstream изменил payload; сравните актуальные модули 1c-buddy по
руководству обновления.
Сервер не появляется в Codex: проверьте абсолютные command, cwd, наличие
.venv и запустите python -m onec_buddy_mcp вручную. В рабочем stdio-режиме
процесс ожидает MCP-ввод и ничего не печатает в stdout.
Поиск ИТС не возвращает данные: доступ зависит от возможностей аккаунта и текущих upstream-инструментов 1C.ai.
токен хранится как SecretStr и не включается в repr настроек;
ошибки MCP не возвращают заголовок Authorization;
логи пишутся в stderr, stdout зарезервирован для MCP;
.env, виртуальные окружения и тестовые артефакты исключены из Git.
Проект распространяется по GNU AGPL v3. Реализация API-взаимодействия,
схемы инструментов и часть prompt-логики производны от
ROCTUP/1c-buddy, также распространяемого
по GNU AGPL v3. Новый проект не является официальным продуктом фирмы «1С».
Общие вопросы по платформе 1С и практическим сценариям.
| Name | Required | Description | Default |
|---|---|---|---|
| question | Yes | ||
| programming_language | No | ||
| ssl_version | No | ||
| configuration | No |
| Name | Required | Description |
|---|---|---|
| result | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, and the one-line description discloses no behavioral traits (e.g., response format, limitations, authentication needs). The description carries no transparency value.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Single sentence is concise but severely under-specified. It does not earn its place as it provides minimal information.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given 4 parameters, no annotations, and sibling tools, the description is very incomplete. It does not explain return values even though output schema exists.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 0%, and the description does not add any meaning to the four parameters (question, programming_language, ssl_version, configuration). Agent has no context for parameter usage.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
Description states tool is for general questions about 1C platform and practical scenarios, but does not differentiate from siblings like explain_1c_syntax or search_1c_documentation. Purpose is somewhat vague.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool or its alternatives. No context about when not to use it.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Синтаксическая проверка или code review фрагмента BSL-кода.
| Name | Required | Description | Default |
|---|---|---|---|
| code | Yes | ||
| check_type | No | syntax | |
| extended | No |
| Name | Required | Description |
|---|---|---|
| result | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations exist, so the description must carry full burden. It only says the tool checks or reviews code, but does not disclose side effects, required permissions, destructive potential, or output characteristics. The 'extended' parameter is left unexplained.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single short sentence, making it concise. However, it is too terse for a tool with three parameters and 0% schema coverage; more detail is needed to be effective.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a tool with 3 parameters (1 required, 1 enum, 1 boolean) and an output schema, the description is insufficient. It lacks details on parameter options, extended behavior, and return value. Siblings like 'explain_1c_syntax' imply a need for clearer differentiation.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 0%, so the description should explain parameters. It mentions 'syntax check or code review' which partially maps to the 'check_type' enum but ignores 'logic' and 'performance'. The 'code' and 'extended' parameters are not described at all.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description states the tool does 'syntax check or code review' of BSL code, which is a clear verb-resource pair. However, it omits the 'logic' and 'performance' check types available in the schema, and does not distinguish from the sibling 'explain_1c_syntax'.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool versus alternatives like explain_1c_syntax. No prerequisites, exclusions, or context for invocation are provided.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Сравнение документации платформы между двумя версиями.
| Name | Required | Description | Default |
|---|---|---|---|
| version_a | Yes | ||
| version_b | Yes | ||
| query | No |
| Name | Required | Description |
|---|---|---|
| result | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations exist, and the description does not disclose behavioral traits such as whether it is read-only, output format, or performance implications. The agent gets no insight into side effects or limitations.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single sentence, which is concise but lacks structure. It does not front-load key information beyond the basic purpose.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
With three parameters and an output schema present, the description is too minimal. It fails to clarify the output nature or how the query parameter works. While the output schema might detail return values, the description adds no context to bridge the gap.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema has 0% description coverage, and the description does not explain the meaning of version_a, version_b, or query. The agent cannot infer expected formats (e.g., version strings, dates) or how the query parameter modifies behavior.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool compares platform documentation between two versions, which distinguishes it from sibling tools like search or explain. However, it lacks specificity about the nature of the comparison (e.g., textual diff, structural changes).
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is provided on when to use this tool versus alternatives like search_1c_documentation. There is no mention of prerequisites, use cases, or when not to use it.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Объяснение объекта, метода, типа или конструкции платформы 1С.
| Name | Required | Description | Default |
|---|---|---|---|
| syntax_element | Yes | ||
| context | No | ||
| ssl_version | No | ||
| configuration | No |
| Name | Required | Description |
|---|---|---|
| result | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden for behavioral disclosure. It only states the tool 'explains' without mentioning side effects, read-only nature, dependencies, or error scenarios. This is insufficient for an agent to understand the tool's behavior.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single short sentence, which is concise but drastically under-informative. Given the tool has four parameters and no annotation support, the description should be longer to convey essential guidance. It achieves brevity at the cost of utility.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The tool has four parameters and an output schema, but the description provides no contextual completeness. It does not explain what the output contains, how parameters affect results, or any example usage. The agent would be left guessing how to use this tool effectively.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 0%, meaning the parameter titles are empty of descriptions. The tool description does not elaborate on any of the four parameters (syntax_element, context, ssl_version, configuration). It fails to clarify the purpose of optional parameters or the required one.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool provides explanations of 1C platform syntax elements (object, method, type, or construct). It distinguishes from sibling tools like check_1c_code or search_1c_documentation, which have different purposes. However, it could be more specific about the exact nature of the explanation (e.g., usage, examples).
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
No usage guidelines are provided. The description does not indicate when to use this tool versus alternatives like ask_1c_ai or search_its. There is no mention of typical use cases or prerequisites.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Получение содержимого документа или раздела ИТС по идентификатору.
| Name | Required | Description | Default |
|---|---|---|---|
| id | No | root |
| Name | Required | Description |
|---|---|---|
| result | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided; description implies read-only fetch but lacks details on behavior for invalid IDs, authentication, or rate limits.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Single sentence contains all necessary information without fluff.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a simple fetch tool with one parameter and an output schema, the description is mostly adequate, though missing error handling details.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Only one parameter 'id' with default 'root'; description does not explain its meaning beyond 'identifier', and schema provides no descriptions.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
Description clearly states the tool fetches content of a document or section by identifier, with a specific verb and resource, distinguishing from sibling search_its.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool vs alternatives like search_its, nor any prerequisites or exclusions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Изменение BSL-кода по явному заданию пользователя.
| Name | Required | Description | Default |
|---|---|---|---|
| instruction | Yes | ||
| code | No |
| Name | Required | Description |
|---|---|---|
| result | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided. The description only says 'modification based on explicit user instruction' but does not disclose effects (e.g., overwriting, permissions), error handling, or return format. For a mutation tool, this is insufficient transparency.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single sentence with no redundancy, which is structurally fine. However, its brevity sacrifices necessary detail, making it under-specified rather than concise.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given 0% schema coverage, no annotations, and a complex task (code modification), the description is severely incomplete. An output schema exists but is not described. Many critical aspects are missing.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 0%. The description does not explain the parameters 'instruction' (required) or 'code' (optional, default ''). Without any context, an agent cannot infer acceptable values or formats.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description states 'Modification of BSL code based on explicit user instruction,' clearly indicating the verb (modify) and resource (BSL code). It distinguishes from siblings like 'check_1c_code' and 'explain_1c_syntax,' but could be more specific about the type of modification.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool vs. alternatives (e.g., 'ask_1c_ai' for code generation, 'explain_1c_syntax' for syntax help). The description lacks any usage context or exclusions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Поиск по документации платформы 1С:Предприятие указанной версии.
| Name | Required | Description | Default |
|---|---|---|---|
| query | Yes | ||
| version | No | v8.5.1 |
| Name | Required | Description |
|---|---|---|
| result | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations exist; description adds only basic purpose, no details on search behavior, version semantics, or return format.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Single sentence with no waste, but lacks depth to be fully informative.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Search tool with two parameters and no annotations requires more behavioral and output context; description is insufficient for correct invocation.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 0%; description only hints at version but does not explain query behavior or version format, leaving parameters minimally documented.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
Description clearly states the verb 'search' and resource 'documentation of 1C platform with specified version', but does not differentiate from sibling tools like ask_1c_ai or search_its.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool versus siblings, no exclusions or context provided.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Поиск материалов в базе знаний ИТС с идентификаторами источников.
| Name | Required | Description | Default |
|---|---|---|---|
| query | Yes | ||
| ssl_version | No | ||
| configuration | No |
| Name | Required | Description |
|---|---|---|
| result | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are present, so the description must fully disclose behavior. It only states the action (search) and resource (ITS knowledge base) but omits critical behavioral traits such as side effects, auth requirements, rate limits, or read-only nature. The phrase 'with source identifiers' gives some hint but is insufficient.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single concise sentence in Russian, which is efficient but lacks crucial details. It is appropriately sized for a simple tool, but the absence of parameter information makes it less useful. It earns its place but could be more informative.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
With 3 parameters, 0% schema coverage, and no annotations, the description is too brief to be complete. The existence of an output schema (not shown) partially mitigates the need to describe return values, but the description still fails to cover parameter usage or behavioral constraints. More detail is needed for reliable selection and invocation.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 0%, yet the description does not explain any of the three parameters (query, ssl_version, configuration). The phrase 'with source identifiers' might hint at one parameter but is ambiguous. Without parameter semantics, the agent cannot properly invoke the tool.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool searches for materials in the ITS knowledge base, which distinguishes it from sibling tools like search_1c_documentation. The mention of 'source identifiers' adds specificity. However, it does not explicitly differentiate from similar search tools.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides no guidance on when to use this tool versus alternatives such as search_1c_documentation or fetch_its. There is no mention of context, prerequisites, or when not to use it.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
v0.1.0ask_1c_aicheck_1c_codediff_1c_documentation_versionsexplain_1c_syntaxfetch_itsmodify_1c_codesearch_1c_documentationsearch_itsScored across 8 tools
Каждый инструмент нацелен на отдельное действие: общие вопросы (ask_1c_ai), проверка кода (check_1c_code), объяснение синтаксиса (explain_1c_syntax), изменение кода (modify_1c_code), поиск документации (search_1c_documentation), получение материалов ИТС (fetch_its) и т.д. Описания чётко разделяют сферы ответственности, исключая путаницу.
Все имена следуют единому шаблону verb_noun в snake_case (ask_1c_ai, check_1c_code, diff_1c_documentation_versions, explain_1c_syntax, fetch_its, modify_1c_code, search_1c_documentation, search_its). Отклонений нет, стиль однороден.
8 инструментов оптимально покрывают основные потребности в работе с платформой 1С: вопросы, разбор кода, документация, ИТС. Количество не избыточно и не недостаточно для заявленной цели.
Охвачены ключевые операции: поиск и получение документации, анализ и модификация кода, сравнение версий, общие вопросы. Отсутствует, например, запуск кода или создание с нуля, но это может быть вне области применения. В целом покрытие достаточное.
MCP server for AI dialogue using various LLM models via AceDataCloud
MCP server unifying ERPs, CRMs, APIs and knowledge base for Claude, ChatGPT and Gemini.
MCP server for querying Forkast documentation
