SuperAPI AI Directory
Partner with us中文AI newsFavorites
Skillsbt-mcp-tools

bt-mcp-tools

Agents & models

View repository

Updated 10-15 21:47

About this skill

Baota Panel MCP Tool Quick Reference (98 Tools)

General Conventions

  • Return structure：{"status": bool, "msg": string, ...}, failure status=false
  • Risk level：
    • low Read-only query (green)
    • medium Has side effects (yellow)
    • high High-risk operation (red, delete/overwrite/execute command)
  • Total tools 98, grouped into 19 categories

I. Basic Tools (10, dedicated to remote Agent)

Tool Risk Function
Read low Read file (file_path, offset, limit）
Edit high Precise modification (old_string, new_string, replace_all）
Write high Write/overwrite
Glob low Find files by name
Grep low Content search (regex)
LS low List directory
Bash high Execute Shell (run_in_background）
BashStatus low Query background tasks
BashStop medium Terminate background tasks
Upload medium Client upload file

II. Website (15)

Tool Risk Function
SiteList low Website list
SiteGetConfig low Site configuration
SiteLogs low Access log
SiteTraffic low Site traffic
SiteCreate medium Create website (domain, port, php_version）
SiteDelete high Delete website
OneClickDeploy medium One-click CMS deployment
TrafficAnalysis low Site-wide traffic analysis
SiteCertList low Certificate store list
SiteSSLDeploy medium Deploy SSL
SiteSSLApply medium Apply for SSL
DomainManage high Add/remove domains
SiteConfig medium PHP/pseudo-static
SiteControl medium Start/stop site
SiteBackup medium Back up site

III. Network (3)

WebFetch（low）/ ServerIP（low）/ Upload（medium）

IV. Database (6)

Tool Risk Function
DatabaseList low Database list
DatabaseCreate medium Create (name, db_user, password）
DatabaseDelete high Delete
DatabaseBackup medium Back up
MysqlQuery low Read-only SQL
MysqlExecute high Write SQL

V. Service (2)

ServiceStatus（low）/ ServiceControl（medium）

VI. Docker (10)

ContainerList（low）/ ContainerLogs（low）/ ContainerInspect（low）/ ComposeList（low）/ ImageList（low）/ VolumeList（low）/ NetworkList（low）/ ContainerControl（medium）/ ContainerDelete（high）/ ImagePull（medium）

VII. System (1)

SystemInfo(low): CPU/memory/disk/load/uptime

VIII. Software Store (3)

SoftwareList（low）/ SoftwareInstall（medium）/ SoftwareUninstall（high）

IX. Firewall (5)

FirewallStatus（low）/ FirewallPortList（low）/ FirewallIpList（low）/ FirewallPortSet（high）/ FirewallIpSet（high）

X. Java Projects (6)

JavaJdk（medium）/ JavaProjectCreate（medium）/ JavaProjectInfo（low）/ JavaProjectControl（medium）/ JavaProjectModify（medium）/ JavaProjectDelete（high）

XI. NodeJS Projects (6)

NodeVersion（medium）/ NodeProjectCreate（medium）/ NodeProjectInfo（low）/ NodeProjectControl（medium）/ NodeProjectModify（medium）/ NodeProjectDelete（high）

XII. Python Projects (8)

PythonVersion（medium）/ PythonEnv（medium）/ PythonProjectCreate（medium）/ PythonProjectInfo（low）/ PythonProjectControl（medium）/ PythonProjectService（medium）/ PythonProjectModify（medium）/ PythonProjectDelete（high）

XIII. Go Projects (6)

GoVersion（medium）/ GoProjectCreate（medium）/ GoProjectInfo（low）/ GoProjectControl（medium）/ GoProjectModify（medium）/ GoProjectDelete（high）

XIV. Reverse Proxy (5)

ProxyProjectCreate（medium）/ ProxyProjectInfo（low）/ ProxyProjectModify（medium）/ ProxyWriteConfig（medium）/ ProxyProjectDelete（high）

XV. HTML Static Projects (4)

HtmlProjectInfo（low）/ HtmlProjectCreate（medium）/ HtmlProjectModify（medium）/ HtmlProjectDelete（high）

XVI. SSH (3)

SSHInfo（low）/ SSHConfig（high）/ SSHIntrusion（low）

XVII. Security (1)

SecurityCheck(low): security score, 10 checks, SSH dangerous command history

XVIII. Scheduled Tasks (2)

GetCrontab（low）/ ManageCrontab（high）

XIX. Notification (3)

GetChannel（low）/ ManageChannel（high）/ SendMessage（medium）

Tool Selection Decision Tree

目标是什么？
├─ 只读查询
│  ├─ 本机 → 用通用工具（Bash + grep + read）更轻量
│  └─ 远端 → MCP low 工具
├─ 创建资源（站点/数据库/项目）
│  ├─ 本机 → 通用工具 + 手工命令
│  └─ 远端 → MCP medium 工具（先确认）
└─ 修改/删除资源
   ├─ 本机 → 通用工具（高危，需授权）
   └─ 远端 → MCP high 工具（**每次二次确认**）

Risk Level Quick Reference

Read-only（low）：SiteList / DatabaseList / SystemInfo / ServiceStatus / ContainerList / FirewallStatus / GetCrontab / GetChannel / TrafficAnalysis / *ProjectInfo / SSHInfo / SSHIntrusion / SecurityCheck

Medium risk（medium）：SiteCreate / DatabaseCreate / ServiceControl / SoftwareInstall / *ProjectCreate / *ProjectControl / *ProjectModify(except Delete) / SiteSSL* / SiteConfig / ContainerControl / ImagePull / BashStop / SendMessage / Upload

High risk(high, explicit user confirmation required every time):Edit / Write / Bash / SiteDelete / DomainManage / DatabaseDelete / MysqlExecute / ContainerDelete / SoftwareUninstall / FirewallPortSet / FirewallIpSet / *ProjectDelete / SSHConfig / ManageCrontab / ManageChannel

When to use

✅ Applicable:

  1. The user explicitly wants to select Baota MCP tools by risk level and generate a call plan.
  2. The necessary context has been provided or can be safely obtained, and a verifiable mcp-tool-plan。
  3. It needs to be executed in a least-privilege, rollback-capable manner, with audit evidence retained.

⚠️ Clarify first:

  1. When the target environment, authorization boundary, or success criteria are missing, first provide a read-only assumption-based plan and list the missing items.
  2. When production environment changes are involved, first confirm backups, maintenance windows, and rollback paths.
  3. When the input may contain sensitive information, only reference field names and redacted fragments; do not copy complete credentials.

❌ Not applicable:

  1. Bypassing tool risk classification to directly execute high-risk operations.
  2. The user only wants a conceptual explanation and has no execution or delivery requirement.
  3. Requests that require bypassing authentication, certificate validation, manual confirmation, or other security controls.

Workflow

Step 1: Confirm the goal, environment, authorization scope, and immutable constraints; when information is insufficient, first produce an assumption-based read-only version.

Step 2: Inventory the current state and dependencies, read only the necessary data, and do not record tokens, passwords, Cookies, or complete personal data.

Step 3: Choose the path with the least impact, and clearly mark high-risk actions, external network calls, and reversible steps.

Step 4: Generate or execute mcp-tool-plan, binding each step to inputs, expected outputs, and failure conditions.

Step 5: Verify structure, factual sources, and target state; do not fabricate success conclusions based on missing evidence.

Step 6: On failure, stop expanding the impact and output completed steps, failure evidence, recovery points, and conditions for the next safe retry.

Step 7: Deliver a summary, verification evidence, remaining risks, and follow-up actions; production changes must state whether rollback has been verified.

Rules

  • Read-only by default; write operations, high-risk operations, and paid calls must obtain explicit authorization matching the action.
  • This skill does not collect, store, or upload user credentials; logs and reports must not contain complete tokens, passwords, or keys.
  • Do not disable TLS validation, do not execute scripts of unknown origin, and do not download via a pipe and execute directly.
  • Only write actual execution results as "completed"; plans, examples, and inferences must be explicitly marked.
  • Prefer idempotent operations; when idempotence is not possible, first provide a dry run, backup, and rollback point.

Validation checklist

  • The goal, environment, and authorization scope are all stated.
  • 工具、参数、风险、授权和预期输出一一对应 Verified by reproducible evidence.
  • Sensitive data has been redacted, and the output contains no complete credentials.
  • Failure and timeout paths are covered, with no infinite retries.
  • Change-type tasks have backup or rollback instructions.
  • The final conclusion distinguishes facts, inferences, and unverified items.

Gotchas

  1. Authorization does not equal reachability: when permissions exist but the network, certificate, or allowlist requirements are not met, you should still stop and report the connection evidence.
  2. A success code does not equal business success: you must check 工具、参数、风险、授权和预期输出一一对应, and cannot rely only on the command exit code or HTTP 200.
  3. Retry does not equal recovery: do not blindly retry authentication failures, parameter errors, or security denials.
  4. Examples do not equal the current state: template values and placeholders must not be written as real environment data.
  5. Output does not equal delivery: Structural verification, risk description, and reproducible verification still need to be completed.
  6. Cannot be copied across environments: Parameters must be reconfirmed when the operating system, version, region, or host capabilities differ.

Progressive materials

  • Read before making path selections references/decisions/decision-guide.md。
  • Read when encountering exceptions, timeouts, or partial success references/operations/failure-matrix.md。
  • Read before completing delivery references/operations/validation-checklist.md。
  • When reproducible input is needed, refer in order to examples/basic.md、examples/failure.md、examples/advanced.md。