⚠️重要提示：此软件包目前处于开发阶段，尚未准备好投入生产使用。当前版本尚在开发中，可能包含不完整的功能或重大更改。
人工智能模型的自我诊断框架，使其能够诊断和修复与 MCP 相关的问题。
flowchart TB
Client["AI Model\n(e.g., Claude)"]
subgraph "MCP Troubleshooter Server"
LogTools["Log Management"]
ConnTools["Connection Testing"]
ConfigTools["Configuration Analysis"]
FixTools["Fix Implementation"]
subgraph "Log Analysis Engine"
LogReader["Log Reader"]
LogParser["Pattern Recognition"]
ErrorClassifier["Issue Classification"]
end
subgraph "Connection Diagnostics"
ConnTester["Transport Testing"]
PortScanner["Port Availability"]
HandshakeTester["Protocol Validation"]
end
subgraph "Configuration Manager"
ConfigReader["Config Parser"]
ConfigValidator["Schema Validation"]
TemplateLibrary["Template Repository"]
end
end
FileSystem["Host File System\n(Logs & Configs)"]
OtherMCPs["Target MCP Servers"]
Client <--> LogTools
Client <--> ConnTools
Client <--> ConfigTools
Client <--> FixTools
LogTools --> LogAnalysisEngine
ConnTools --> ConnectionDiagnostics
ConfigTools --> ConfigurationManager
LogReader --> FileSystem
ConfigReader --> FileSystem
ConnTester --> OtherMCPs
FixTools --> FileSystem
FixTools --> OtherMCPs
style Client fill:#f9f,stroke:#333,stroke-width:2px
style FileSystem fill:#bbf,stroke:#333,stroke-width:2px
style OtherMCPs fill:#bbf,stroke:#333,stroke-width:2px
style "MCP Troubleshooter Server" fill:#eff,stroke:#333,stroke-width:4pxRelated MCP server: OpenShift SRE Copilot
MCP Troubleshooter 是一个专门的 MCP 服务器，它将故障排除从仅限开发人员的任务转变为 AI 本身可以利用的功能，从而使 AI 模型能够：
分析 MCP 日志- 自动扫描常见错误模式并提供深刻的诊断
验证配置- 根据最佳实践检查服务器配置并识别问题
测试连接- 验证网络连接和服务器可用性
生成模板- 创建有效的 MCP 服务器配置以便快速设置
修复常见问题- 更新配置并直接实施解决方案
# Install the package globally
npm install -g @devlimelabs/mcp-troubleshooter
# Start the server
mcp-troubleshooter将其添加到您的 Claude Desktop 配置中：
{
"mcpServers": {
"troubleshooter": {
"command": "mcp-troubleshooter"
}
}
}read-mcp-logs ：检索并显示 MCP 日志文件
analyze-mcp-logs ：使用模式识别来识别常见的错误特征
read-mcp-config ：提取并验证 Claude Desktop 的 MCP 配置
update-mcp-config ：使用适当的备份机制安全地更新配置
valid-mcp-server-config ：执行服务器配置的深度验证
test-port-availability ：检查 MCP 服务器是否提供所需端口
check-mcp-server-process ：验证 MCP 服务器进程是否正常运行
generate-mcp-server-template ：为不同语言创建定制的服务器模板
generate-claude-desktop-config ：为 Claude Desktop 构建优化的配置文件
common-mcp-issues ：常见 MCP 问题及其解决方案的综合指南
mcp-config-templates ：各种 MCP 服务器设置的配置模板
User: My MCP server isn't connecting properly to Claude Desktop. Can you help diagnose it?
Claude: I'll help diagnose your MCP server connection issue. First, let me run some diagnostics.
[Uses check-mcp-server-process tool with the command from the user]
I've identified several possible issues with your MCP server:
1. **Connection Timeout**: The server isn't responding within the expected timeframe.
2. **JSON-RPC Format Error**: There seems to be a format issue in the JSON-RPC responses.
3. **Transport Mismatch**: Claude Desktop is expecting stdio transport, but your server might be using SSE.
Let me run a more specific connection test to confirm:
[Uses test-port-availability tool]
The connection test confirms that your server is starting, but it's timing out during the handshake phase. This is likely due to incorrect JSON-RPC message formatting in your server implementation.
Recommended fixes:
1. Ensure your server returns properly formatted JSON-RPC 2.0 responses
2. Check your transport implementation, it should be using proper stdio pipes
3. Verify that your server is correctly handling the initialize method
Would you like me to analyze a specific log file or check your server's code for these issues?User: Can you validate my Claude Desktop MCP configuration?
Claude: I'd be happy to validate your Claude Desktop MCP configuration.
[Uses read-mcp-config tool]
I've analyzed your Claude Desktop configuration file. Here are my findings:
✅ **Valid Configuration Structure**: The overall structure of your configuration is valid.
⚠️ **Path Issues**: 2 servers have invalid paths:
- "code-llm": The file path "/usr/local/bin/code-llm" doesn't exist
- "database-tool": The command "db-tool" is not in the PATH
❌ **Environment Variables**: 1 server has missing required environment variables:
- "firebase-mcp": Missing required FIREBASE_API_KEY
✅ **Transport Configuration**: All servers properly specify transport options
Recommended fixes:
1. Update the path for "code-llm" to the correct location
2. Install "db-tool" or correct its path
3. Add the missing FIREBASE_API_KEY to the "firebase-mcp" server configuration
Would you like me to help you implement any of these fixes?Windows ：访问%APPDATA%\Claude\中的日志和配置
macOS ：访问~/Library/Logs/Claude/中的日志和~/Library/Application Support/Claude/中的配置
Linux ：访问~/.local/share/Claude/logs/中的日志和~/.config/Claude/中的配置
# Clone the repository
git clone https://github.com/devlimelabs/master-mcps.git
cd master-mcps
# Install dependencies
pnpm install
# Build the package
pnpm -F @devlimelabs/mcp-troubleshooter build
# Run tests
pnpm -F @devlimelabs/mcp-troubleshooter test麻省理工学院
| Name | Required | Description | Default |
|---|---|---|---|
| serverName | No | Specific server name to analyze logs for |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Tool has no description.
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?
Tool has no description.
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?
Tool has no description.
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?
Tool has no description.
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?
Tool has no description.
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?
Tool has no description.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
| Name | Required | Description | Default |
|---|---|---|---|
| serverName | Yes | Name of the MCP server to check |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Tool has no description.
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?
Tool has no description.
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?
Tool has no description.
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?
Tool has no description.
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?
Tool has no description.
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?
Tool has no description.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
| Name | Required | Description | Default |
|---|---|---|---|
| serverConfigs | Yes | Array of server configurations |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Tool has no description.
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?
Tool has no description.
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?
Tool has no description.
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?
Tool has no description.
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?
Tool has no description.
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?
Tool has no description.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
| Name | Required | Description | Default |
|---|---|---|---|
| features | Yes | Features to include in the template | |
| serverName | Yes | Name for the MCP server | |
| serverType | Yes | Type of server to generate |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Tool has no description.
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?
Tool has no description.
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?
Tool has no description.
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?
Tool has no description.
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?
Tool has no description.
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?
Tool has no description.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Tool has no description.
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?
Tool has no description.
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?
Tool has no description.
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?
Tool has no description.
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?
Tool has no description.
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?
Tool has no description.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
| Name | Required | Description | Default |
|---|---|---|---|
| lines | No | Number of lines to read from the end | |
| serverName | No | Specific server name to filter logs for |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Tool has no description.
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?
Tool has no description.
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?
Tool has no description.
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?
Tool has no description.
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?
Tool has no description.
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?
Tool has no description.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
| Name | Required | Description | Default |
|---|---|---|---|
| port | Yes | Port number to test |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Tool has no description.
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?
Tool has no description.
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?
Tool has no description.
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?
Tool has no description.
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?
Tool has no description.
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?
Tool has no description.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
| Name | Required | Description | Default |
|---|---|---|---|
| config | Yes | JSON configuration to write (entire file content) |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Tool has no description.
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?
Tool has no description.
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?
Tool has no description.
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?
Tool has no description.
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?
Tool has no description.
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?
Tool has no description.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
| Name | Required | Description | Default |
|---|---|---|---|
| serverName | No | Specific server configuration to validate |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Tool has no description.
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?
Tool has no description.
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?
Tool has no description.
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?
Tool has no description.
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?
Tool has no description.
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?
Tool has no description.
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. Dates show when Glama detected each change.
v1.0.0analyze-mcp-logscheck-mcp-server-processgenerate-claude-desktop-configgenerate-mcp-server-templateread-mcp-configread-mcp-logstest-port-availabilityupdate-mcp-configvalidate-mcp-server-configMost tools have distinct purposes targeting different aspects of MCP troubleshooting (logs, config, server process, ports, templates). However, 'analyze-mcp-logs' and 'read-mcp-logs' could potentially overlap in function if both involve log inspection, creating some ambiguity about their specific differences.
All tool names follow a consistent verb-noun pattern with hyphen-separated lowercase words (e.g., 'analyze-mcp-logs', 'check-mcp-server-process'). The naming convention is uniform throughout the set, making it predictable and easy to parse.
With 9 tools, this server is well-scoped for MCP troubleshooting. The count is appropriate as it covers key areas like configuration, logs, server status, and testing without being overwhelming or too sparse for the domain.
The tool set provides good coverage for MCP troubleshooting, including reading/analyzing logs, managing configs, checking server processes, and testing ports. A minor gap might be the lack of tools for fixing or repairing issues (e.g., 'restart-mcp-server' or 'fix-mcp-config'), but core diagnostic and setup functions are well-represented.
Unclaimed servers have limited discoverability.
If you are the server author, to access and configure the admin panel.
MCP-native AI SRE: ask what's broken in production, get a reviewed GitHub fix PR.
Workflow diagnostics, capability routing, and x402 settlement for MCP-compatible agents.
AI-powered incident management and server monitoring via MCP.
Compliance frameworks (SOC 2, ISO 27001, CMMC, NIST, more) delivered to AI agents as MCP tools.
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/devlimelabs/mcp-troubleshooter-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server
