mcp2cli：无需代码，将MCP/OpenAPI/GraphQL实时转换为命令行工具

mcp2cli by knowsuchagency/mcp2cli

530 周安装量

1,700 GitHub Stars

GitHub

安装命令

npx skills add https://github.com/knowsuchagency/mcp2cli --skill mcp2cli

开发自动化 API

🇨🇳中文介绍

mcp2cli

在运行时将任何 MCP 服务器、OpenAPI 规范或 GraphQL 端点转换为 CLI。无需代码生成。

安装

# 直接运行（无需安装）
uvx mcp2cli --help

# 或安装
pip install mcp2cli

核心工作流程

连接到源（MCP 服务器、OpenAPI 规范或 GraphQL 端点）
发现可用命令，使用 --list（或使用 --search 过滤）
检查特定命令，使用 <command> --help
执行命令并附带标志

# 通过 HTTP 的 MCP

mcp2cli --mcp https://mcp.example.com/sse --list
mcp2cli --mcp https://mcp.example.com/sse create-task --help
mcp2cli --mcp https://mcp.example.com/sse create-task --title "Fix bug"

# 通过 stdio 的 MCP
mcp2cli --mcp-stdio "npx @modelcontextprotocol/server-filesystem /tmp" --list
mcp2cli --mcp-stdio "npx @modelcontextprotocol/server-filesystem /tmp" read-file --path /tmp/hello.txt

# OpenAPI 规范（远程或本地，JSON 或 YAML）
mcp2cli --spec https://petstore3.swagger.io/api/v3/openapi.json --list
mcp2cli --spec ./openapi.json --base-url https://api.example.com list-pets --status available

# GraphQL 端点
mcp2cli --graphql https://api.example.com/graphql --list
mcp2cli --graphql https://api.example.com/graphql users --limit 10
mcp2cli --graphql https://api.example.com/graphql create-user --name "Alice"

广告位招租

在这里展示您的产品或服务

触达数万 AI 开发者，精准高效

联系我们

OAuth 身份验证（仅限 MCP HTTP）

# 授权码 + PKCE（打开浏览器）
mcp2cli --mcp https://mcp.example.com/sse --oauth --list

# 客户端凭证（机器对机器）
mcp2cli --mcp https://mcp.example.com/sse \
  --oauth-client-id "my-id" --oauth-client-secret "my-secret" \
  search --query "test"

# 指定作用域
mcp2cli --mcp https://mcp.example.com/sse --oauth --oauth-scope "read write" --list

令牌缓存在 ~/.cache/mcp2cli/oauth/ 中，并自动刷新。

传输选择（仅限 MCP HTTP）

# 默认：尝试 streamable HTTP，回退到 SSE
mcp2cli --mcp https://mcp.example.com/sse --list

# 强制使用 SSE 传输（跳过 streamable HTTP 尝试）
mcp2cli --mcp https://mcp.example.com/sse --transport sse --list

# 强制使用 streamable HTTP（无 SSE 回退）
mcp2cli --mcp https://mcp.example.com/sse --transport streamable --list

# 发现查询和变更
mcp2cli --graphql https://api.example.com/graphql --list

# 运行查询
mcp2cli --graphql https://api.example.com/graphql users --limit 10

# 运行变更
mcp2cli --graphql https://api.example.com/graphql create-user --name "Alice" --email "alice@example.com"

# 覆盖自动生成的选择集
mcp2cli --graphql https://api.example.com/graphql users --fields "id name email"

# 带身份验证
mcp2cli --graphql https://api.example.com/graphql --auth-header "Authorization:Bearer tok_..." users

# 按名称或描述过滤工具（不区分大小写）
mcp2cli --mcp https://mcp.example.com/sse --search "task"
mcp2cli --spec ./openapi.json --search "create"
mcp2cli --graphql https://api.example.com/graphql --search "user"

--search 隐含 --list —— 仅显示匹配的工具。

从 stdin 读取 JSON 体进行 POST 请求

echo '{"name": "Fido", "tag": "dog"}' | mcp2cli --spec ./spec.json create-pet --stdin

多部分文件上传

当 OpenAPI 规范声明了带有 format: binary 字段的 multipart/form-data 时，mcp2cli 会将其公开为文件路径 CLI 参数：

# 上传文件 —— 二进制字段接受本地文件路径
mcp2cli --spec ./spec.json upload-image --file /path/to/photo.png --caption "My photo"

# 同一多部分模式中的非二进制字段成为常规标志
mcp2cli --spec ./spec.json upload-image --file ./image.jpg --title "Cover" --alt-text "A sunset"

文件参数在 --help 输出中显示 (file path)。MIME 类型根据文件扩展名自动检测。

用于 stdio 服务器的环境变量

mcp2cli --mcp-stdio "node server.js" --env API_KEY=sk-... --env DEBUG=1 search --query "test"

烘焙模式 —— 保存的配置

将连接设置保存为命名配置，以避免重复标志：

# 创建烘焙工具
mcp2cli bake create petstore --spec https://api.example.com/spec.json \
  --exclude "delete-*,update-*" --methods GET,POST --cache-ttl 7200

mcp2cli bake create mygit --mcp-stdio "npx @mcp/github" \
  --include "search-*,list-*" --exclude "delete-*"

# 使用 @ 前缀
mcp2cli @petstore --list
mcp2cli @petstore list-pets --limit 10

# 管理
mcp2cli bake list
mcp2cli bake show petstore
mcp2cli bake update petstore --cache-ttl 3600
mcp2cli bake remove petstore
mcp2cli bake install petstore    # 创建 ~/.local/bin/petstore 包装脚本

过滤选项：--include（全局白名单），--exclude（全局黑名单），--methods（HTTP 方法，仅限 OpenAPI）。

配置存储在 ~/.config/mcp2cli/baked.json 中（可通过 MCP2CLI_CONFIG_DIR 覆盖）。

规范和 MCP 工具列表缓存在 ~/.cache/mcp2cli/ 中（1 小时 TTL）。本地文件从不缓存。

mcp2cli --spec https://api.example.com/spec.json --refresh --list    # 强制刷新
mcp2cli --spec https://api.example.com/spec.json --cache-ttl 86400 --list  # 24 小时 TTL

TOON 输出（对 LLM 令牌高效）

mcp2cli --mcp https://mcp.example.com/sse --toon list-tags

最适合大型统一数组 —— 比 JSON 少 40-60% 的令牌。

使用 --jq 过滤 JSON

对于 JSON 处理，优先使用 --jq 而非 Python 脚本 —— 它使用更少的令牌并避免脚本开销。

# 提取特定字段
mcp2cli --spec ./spec.json list-pets --jq '.[].name'

# 统计结果数量
mcp2cli --mcp https://example.com/sse list-items --jq 'length'

# 复杂过滤
mcp2cli --spec ./spec.json list-pets --jq '[.[] | select(.status == "available")] | length'

# 预览大型数据集（--head 在 --jq 处理之前截断）
mcp2cli --spec ./spec.json list-records --head 3 --jq '.'

使用 --head 截断大型响应

# 预览可能巨大数据集的前 3 条记录
mcp2cli --spec ./spec.json list-records --head 3 --pretty

# 结合 --jq 进行针对性检查
mcp2cli --spec ./spec.json list-records --head 1 --jq 'keys'

--head N 将 JSON 数组切片为前 N 个元素。对于包含超大字段的数据集（例如每个记录约 200KB 的 geo_shape 多边形）很有用。

从 API 生成技能

当用户要求从 MCP 服务器、OpenAPI 规范或 GraphQL 端点创建技能时，请遵循以下工作流程：

发现所有可用命令：

uvx mcp2cli --mcp https://target.example.com/sse --list
检查每个命令以了解参数：

uvx mcp2cli --mcp https://target.example.com/sse <command> --help
测试关键命令并探查边界情况：

uvx mcp2cli --mcp https://target.example.com/sse <command> --param value

 * 大型响应：使用 `--head 3` 预览 —— 是否有任何字段产生超大输出（例如 geo_shape、嵌入式 blob）？
 * 日期/时间字段：API 期望什么格式？（ISO 8601、Unix 时间戳、自定义语法如 `date'2022'`？）
 * 分页：API 返回所有结果还是需要 `--offset`/`--limit`？
 * 错误消息：无效参数会发生什么？错误信息是否具有参考价值？
 * 二进制与文本响应：是否有端点返回非 JSON 数据（xlsx、parquet、图像）？
 * 作用域混淆：数据是否包含超出预期的内容（例如，当你期望区域数据时却包含全国数据）？

4. 烘焙连接设置，以便技能无需重复标志：

    uvx mcp2cli bake create myapi \
  --mcp https://target.example.com/sse \
  --auth-header "Authorization:Bearer env:MYAPI_TOKEN" \
  --exclude "delete-*" --methods GET,POST

5. 安装包装脚本到技能的脚本目录：

    uvx mcp2cli bake install myapi --dir .claude/skills/myapi/scripts/

6. 创建 SKILL.md 在 .claude/skills/myapi/ 中，教导另一个 AI 代理如何使用此 API。SKILL.md 必须超越 --help 输出 —— 专注于只能通过测试和阅读文档获得的知识。

    ---
name: myapi
description: 与 MyAPI 服务交互
allowed-tools: Bash(bash *)
---

核心工作流程（发现 + 执行）：

    # 列出可用命令
bash ${CLAUDE_SKILL_DIR}/scripts/myapi --list
# 获取命令帮助
bash ${CLAUDE_SKILL_DIR}/scripts/myapi <command> --help
# 运行命令
bash ${CLAUDE_SKILL_DIR}/scripts/myapi <command> --param value --pretty

查询前 清单 —— 包含一个决策框架：

 * 我针对的是什么数据集/资源？
 * 我需要分页吗（`--offset`、`--limit`）？
 * 是否有产生大输出的字段我应该排除或截断（`--head`）？
 * 此端点期望什么日期/过滤器格式？

反模式与陷阱 —— 记录测试期间发现的每一个意外情况：

 * 日期语法怪癖（例如 `date'2022'` 与 `"2022"`）
 * 产生超大输出的字段（例如 geo_shape → 使用 `--head` 或 `--jq` 排除）
 * 跨端点的参数名称不一致
 * 作用域/过滤混淆（例如数据集包含全国数据，而不仅仅是区域数据）
 * 二进制导出损坏风险（例如不要通过文本编码管道传输二进制格式）

输出处理 —— 推荐使用 --jq 而非 Python 进行 JSON 过滤：

    # 提取特定字段
bash ${CLAUDE_SKILL_DIR}/scripts/myapi list-records --jq '.[].name'
# 统计结果数量
bash ${CLAUDE_SKILL_DIR}/scripts/myapi list-records --jq 'length'
# 按条件过滤
bash ${CLAUDE_SKILL_DIR}/scripts/myapi list-records --jq '[.[] | select(.status == "active")]'

对于 JSON 处理，优先使用 --jq 而非管道传输到 Python —— 它更令牌高效，并避免了不必要的脚本复杂性。

导出格式（如果 API 支持多种输出类型）：

 * 列出支持的格式（JSON、CSV、xlsx、parquet 等）
 * 注意哪些是文本安全的，哪些是二进制的
 * 对于二进制格式：`bash ${CLAUDE_SKILL_DIR}/scripts/myapi export --format xlsx --raw > output.xlsx`

知识增量原则： 不要复制 --help 中的参数列表。相反，记录哪些参数对于常见任务实际上很重要、令人惊讶的默认行为、不起作用的组合以及速率限制或响应大小限制。

生成的技能使用 mcp2cli 作为其执行层 —— 烘焙的包装脚本处理所有连接细节，因此 SKILL.md 保持简洁和可移植。

🇺🇸English

mcp2cli

Turn any MCP server, OpenAPI spec, or GraphQL endpoint into a CLI at runtime. No codegen.

Install

# Run directly (no install needed)
uvx mcp2cli --help

# Or install
pip install mcp2cli

Core Workflow

Connect to a source (MCP server, OpenAPI spec, or GraphQL endpoint)
Discover available commands with --list (or filter with --search)
Inspect a specific command with <command> --help
Execute the command with flags

# MCP over HTTP

mcp2cli --mcp https://mcp.example.com/sse --list
mcp2cli --mcp https://mcp.example.com/sse create-task --help
mcp2cli --mcp https://mcp.example.com/sse create-task --title "Fix bug"

# MCP over stdio
mcp2cli --mcp-stdio "npx @modelcontextprotocol/server-filesystem /tmp" --list
mcp2cli --mcp-stdio "npx @modelcontextprotocol/server-filesystem /tmp" read-file --path /tmp/hello.txt

# OpenAPI spec (remote or local, JSON or YAML)
mcp2cli --spec https://petstore3.swagger.io/api/v3/openapi.json --list
mcp2cli --spec ./openapi.json --base-url https://api.example.com list-pets --status available

# GraphQL endpoint
mcp2cli --graphql https://api.example.com/graphql --list
mcp2cli --graphql https://api.example.com/graphql users --limit 10
mcp2cli --graphql https://api.example.com/graphql create-user --name "Alice"

CLI Reference

mcp2cli [global options] <subcommand> [command options]

Source (mutually exclusive, one required):
  --spec URL|FILE       OpenAPI spec (JSON or YAML, local or remote)
  --mcp URL             MCP server URL (HTTP/SSE)
  --mcp-stdio CMD       MCP server command (stdio transport)
  --graphql URL         GraphQL endpoint URL

Options:
  --auth-header K:V       HTTP header (repeatable, value supports env:/file: prefixes)
  --base-url URL          Override base URL from spec
  --transport TYPE        MCP HTTP transport: auto|sse|streamable (default: auto)
  --env KEY=VALUE         Env var for stdio server process (repeatable)
  --oauth                 Enable OAuth (authorization code + PKCE flow)
  --oauth-client-id ID    OAuth client ID (supports env:/file: prefixes)
  --oauth-client-secret S OAuth client secret (supports env:/file: prefixes)
  --oauth-scope SCOPE     OAuth scope(s) to request
  --cache-key KEY         Custom cache key
  --cache-ttl SECONDS     Cache TTL (default: 3600)
  --refresh               Bypass cache
  --list                  List available subcommands
  --search PATTERN        Search tools by name or description (implies --list)
  --fields FIELDS         Override GraphQL selection set (e.g. "id name email")
  --pretty                Pretty-print JSON output
  --raw                   Print raw response body
  --toon                  Encode output as TOON (token-efficient for LLMs)
  --jq EXPR               Filter JSON output through jq expression
  --head N                Limit output to first N records (arrays)
  --version               Show version

Bake mode:
  bake create NAME [opts]   Save connection settings as a named tool
  bake list                 List all baked tools
  bake show NAME            Show config (secrets masked)
  bake update NAME [opts]   Update a baked tool
  bake remove NAME          Delete a baked tool
  bake install NAME         Create ~/.local/bin wrapper script
  @NAME [args]              Run a baked tool (e.g. mcp2cli @petstore --list)

Subcommands and flags are generated dynamically from the source.

Patterns

Authentication

# API key header (literal value)
mcp2cli --spec ./spec.json --auth-header "Authorization:Bearer tok_..." list-items

# Secret from environment variable (avoids exposing in process list)
mcp2cli --mcp https://mcp.example.com/sse \
  --auth-header "Authorization:env:API_TOKEN" \
  search --query "test"

# Secret from file
mcp2cli --mcp https://mcp.example.com/sse \
  --auth-header "x-api-key:file:/run/secrets/api_key" \
  search --query "test"

OAuth authentication (MCP HTTP only)

# Authorization code + PKCE (opens browser)
mcp2cli --mcp https://mcp.example.com/sse --oauth --list

# Client credentials (machine-to-machine)
mcp2cli --mcp https://mcp.example.com/sse \
  --oauth-client-id "my-id" --oauth-client-secret "my-secret" \
  search --query "test"

# With scopes
mcp2cli --mcp https://mcp.example.com/sse --oauth --oauth-scope "read write" --list

Tokens are cached in ~/.cache/mcp2cli/oauth/ and refreshed automatically.

Transport selection (MCP HTTP only)

# Default: tries streamable HTTP, falls back to SSE
mcp2cli --mcp https://mcp.example.com/sse --list

# Force SSE transport (skip streamable HTTP attempt)
mcp2cli --mcp https://mcp.example.com/sse --transport sse --list

# Force streamable HTTP (no SSE fallback)
mcp2cli --mcp https://mcp.example.com/sse --transport streamable --list

GraphQL

# Discover queries and mutations
mcp2cli --graphql https://api.example.com/graphql --list

# Run a query
mcp2cli --graphql https://api.example.com/graphql users --limit 10

# Run a mutation
mcp2cli --graphql https://api.example.com/graphql create-user --name "Alice" --email "alice@example.com"

# Override auto-generated selection set
mcp2cli --graphql https://api.example.com/graphql users --fields "id name email"

# With auth
mcp2cli --graphql https://api.example.com/graphql --auth-header "Authorization:Bearer tok_..." users

Tool search

# Filter tools by name or description (case-insensitive)
mcp2cli --mcp https://mcp.example.com/sse --search "task"
mcp2cli --spec ./openapi.json --search "create"
mcp2cli --graphql https://api.example.com/graphql --search "user"

--search implies --list — shows only matching tools.

POST with JSON body from stdin

echo '{"name": "Fido", "tag": "dog"}' | mcp2cli --spec ./spec.json create-pet --stdin

Multipart file uploads

When an OpenAPI spec declares multipart/form-data with format: binary fields, mcp2cli exposes them as file-path CLI arguments:

# Upload a file — binary fields accept local file paths
mcp2cli --spec ./spec.json upload-image --file /path/to/photo.png --caption "My photo"

# Non-binary fields in the same multipart schema become regular flags
mcp2cli --spec ./spec.json upload-image --file ./image.jpg --title "Cover" --alt-text "A sunset"

File parameters show (file path) in --help output. MIME types are auto-detected from the file extension.

Env vars for stdio servers

mcp2cli --mcp-stdio "node server.js" --env API_KEY=sk-... --env DEBUG=1 search --query "test"

Bake mode — saved configurations

Save connection settings as named configurations to avoid repeating flags:

# Create a baked tool
mcp2cli bake create petstore --spec https://api.example.com/spec.json \
  --exclude "delete-*,update-*" --methods GET,POST --cache-ttl 7200

mcp2cli bake create mygit --mcp-stdio "npx @mcp/github" \
  --include "search-*,list-*" --exclude "delete-*"

# Use with @ prefix
mcp2cli @petstore --list
mcp2cli @petstore list-pets --limit 10

# Manage
mcp2cli bake list
mcp2cli bake show petstore
mcp2cli bake update petstore --cache-ttl 3600
mcp2cli bake remove petstore
mcp2cli bake install petstore    # creates ~/.local/bin/petstore wrapper

Filter options: --include (glob whitelist), --exclude (glob blacklist), --methods (HTTP methods, OpenAPI only).

Configs stored in ~/.config/mcp2cli/baked.json (override with MCP2CLI_CONFIG_DIR).

Caching

Specs and MCP tool lists are cached in ~/.cache/mcp2cli/ (1h TTL). Local files are never cached.

mcp2cli --spec https://api.example.com/spec.json --refresh --list    # Force refresh
mcp2cli --spec https://api.example.com/spec.json --cache-ttl 86400 --list  # 24h TTL

TOON output (token-efficient for LLMs)

mcp2cli --mcp https://mcp.example.com/sse --toon list-tags

Best for large uniform arrays — 40-60% fewer tokens than JSON.

JSON filtering with --jq

Prefer --jq over Python scripts for JSON processing — it uses fewer tokens and avoids script overhead.

# Extract specific fields
mcp2cli --spec ./spec.json list-pets --jq '.[].name'

# Count results
mcp2cli --mcp https://example.com/sse list-items --jq 'length'

# Complex filtering
mcp2cli --spec ./spec.json list-pets --jq '[.[] | select(.status == "available")] | length'

# Preview large datasets (--head truncates before --jq processes)
mcp2cli --spec ./spec.json list-records --head 3 --jq '.'

Truncating large responses with --head

# Preview first 3 records from a potentially huge dataset
mcp2cli --spec ./spec.json list-records --head 3 --pretty

# Combine with --jq for targeted inspection
mcp2cli --spec ./spec.json list-records --head 1 --jq 'keys'

--head N slices JSON arrays to the first N elements. Useful for datasets with oversized fields (e.g. geo_shape polygons at ~200KB per record).

Generating a Skill from an API

When the user asks to create a skill from an MCP server, OpenAPI spec, or GraphQL endpoint, follow this workflow:

Discover all available commands:

uvx mcp2cli --mcp https://target.example.com/sse --list
Inspect each command to understand parameters:

uvx mcp2cli --mcp https://target.example.com/sse <command> --help
Test key commands and probe for edge cases:

uvx mcp2cli --mcp https://target.example.com/sse <command> --param value

Specifically test for:

 * Large responses: use `--head 3` to preview — do any fields produce oversized output (e.g. geo_shape, embedded blobs)?
 * Date/time fields: what format does the API expect? (ISO 8601, Unix timestamps, custom syntax like `date'2022'`?)
 * Pagination: does the API return all results or require `--offset`/`--limit`?
 * Error messages: what happens with invalid parameters? Are errors informative?
 * Binary vs text responses: do any endpoints return non-JSON (xlsx, parquet, images)?
 * Scope confusion: does the data contain more than expected (e.g. national data when you expect regional)?

4. Bake the connection settings so the skill doesn't need to repeat flags:

    uvx mcp2cli bake create myapi \
  --mcp https://target.example.com/sse \
  --auth-header "Authorization:Bearer env:MYAPI_TOKEN" \
  --exclude "delete-*" --methods GET,POST

5. Install the wrapper into the skill's scripts directory:

    uvx mcp2cli bake install myapi --dir .claude/skills/myapi/scripts/

6. Create a SKILL.md in .claude/skills/myapi/ that teaches another AI agent how to use this API. The SKILL.md must go beyond --help output — focus on knowledge that can only be learned through testing and reading documentation.

Frontmatter:

    ---
name: myapi
description: Interact with the MyAPI service
allowed-tools: Bash(bash *)
---

Core Workflow (discovery + execution):

    # List available commands
bash ${CLAUDE_SKILL_DIR}/scripts/myapi --list
# Get help for a command
bash ${CLAUDE_SKILL_DIR}/scripts/myapi <command> --help
# Run a command
bash ${CLAUDE_SKILL_DIR}/scripts/myapi <command> --param value --pretty

Before Querying checklist — include a decision framework:

 * What dataset/resource am I targeting?
 * Do I need pagination (`--offset`, `--limit`)?
 * Are there fields that produce large output I should exclude or truncate (`--head`)?
 * What date/filter format does this endpoint expect?

Anti-Patterns & Gotchas — document every surprise found during testing:

 * Date syntax quirks (e.g. `date'2022'` vs `"2022"`)
 * Fields that produce oversized output (e.g. geo_shape → use `--head` or `--jq` to exclude)
 * Parameter name inconsistencies across endpoints
 * Scope/filtering confusion (e.g. dataset contains national data, not just regional)
 * Binary export corruption risks (e.g. don't pipe binary formats through text encoding)

Output Processing — recommend --jq over Python for JSON filtering:

    # Extract specific fields
bash ${CLAUDE_SKILL_DIR}/scripts/myapi list-records --jq '.[].name'
# Count results
bash ${CLAUDE_SKILL_DIR}/scripts/myapi list-records --jq 'length'
# Filter by condition
bash ${CLAUDE_SKILL_DIR}/scripts/myapi list-records --jq '[.[] | select(.status == "active")]'

Prefer --jq over piping to Python for JSON processing — it is more token-efficient and avoids unnecessary script complexity.

Export Formats (if the API supports multiple output types):

 * List supported formats (JSON, CSV, xlsx, parquet, etc.)
 * Note which are text-safe vs binary
 * For binary formats: `bash ${CLAUDE_SKILL_DIR}/scripts/myapi export --format xlsx --raw > output.xlsx`

Knowledge Delta Principle: Do not duplicate parameter listings from --help. Instead, document which parameters actually matter for common tasks, default behaviors that are surprising, combinations that don't work, and rate limits or response size limits.

The generated skill uses mcp2cli as its execution layer — the baked wrapper script handles all connection details so the SKILL.md stays clean and portable.

Weekly Installs

506

Repository

knowsuchagency/mcp2cli

GitHub Stars

1.6K

First Seen

Mar 9, 2026

Security Audits

Gen Agent Trust HubWarn SocketWarn SnykFail

Installed on

opencode499

codex497

github-copilot496

gemini-cli496

kimi-cli493

amp493

agent-browser 浏览器自动化工具 - Vercel Labs 命令行网页操作与测试

136,300 周安装

mcp2cli：无需代码，将MCP/OpenAPI/GraphQL实时转换为命令行工具

🇨🇳中文介绍

mcp2cli

安装

核心工作流程

相关 Skills

CLI 参考

模式

身份验证

OAuth 身份验证（仅限 MCP HTTP）

传输选择（仅限 MCP HTTP）

GraphQL

工具搜索

从 stdin 读取 JSON 体进行 POST 请求

多部分文件上传

用于 stdio 服务器的环境变量

烘焙模式 —— 保存的配置

缓存

TOON 输出（对 LLM 令牌高效）

使用 --jq 过滤 JSON

使用 --head 截断大型响应

从 API 生成技能

🇺🇸English

mcp2cli

Install

Core Workflow

CLI Reference

Patterns

Authentication

OAuth authentication (MCP HTTP only)

Transport selection (MCP HTTP only)

GraphQL

Tool search

POST with JSON body from stdin

Multipart file uploads

Env vars for stdio servers

Bake mode — saved configurations

Caching

TOON output (token-efficient for LLMs)

JSON filtering with --jq

Truncating large responses with --head

Generating a Skill from an API

最新 Skills