Apex Log MCP Server
An MCP server that gives AI assistants tools to analyze Salesforce Apex debug logs for performance bottlenecks, slow methods, and governor limit usage.
README
Apex Log MCP Server
An MCP server that gives AI assistants tools to analyze Salesforce Apex debug logs for performance bottlenecks, slow methods, and governor limit usage.
<p align="center"> <img src="https://raw.githubusercontent.com/certinia/debug-log-analyzer-mcp/main/docs/images/apex-log-mcp.png" alt="Claude analyzing an Apex debug log for performance bottlenecks and governor limit concerns" width="800" /> </p>
Give your AI assistant — Claude, Copilot, or any MCP-compatible client — the ability to parse Apex debug logs and surface the performance insights that matter. Instead of scrolling through thousands of log lines, ask your assistant to find what's slow and why.
Quick Start | What You Can Do | Tools Reference | Configuration | How It Works | Documentation | Contributing | Contributors | License
Quick Start
Add to your MCP client configuration (claude_desktop_config.json, VS Code mcp.json, etc.):
{
"mcpServers": {
"apex-log-mcp": {
"command": "npx",
"args": ["-y", "@certinia/apex-log-mcp"]
}
}
}
That's it. Open a conversation and ask your AI assistant to analyze an Apex debug log.
What You Can Do
Ask your AI assistant to work with Apex debug logs using natural language:
- "Give me a summary of this debug log"
- "Show me the 5 slowest methods in the default namespace"
- "Are we approaching any governor limits in this transaction?"
- "Run this Apex against my scratch org and analyze the performance"
Tools Reference
analyze_apex_log_performance
Rank methods in an Apex debug log by self-execution time. Returns method names, durations (in ms), SOQL/DML counts, and optimization recommendations. Best for finding which specific methods to optimize.
| Parameter | Type | Required | Description |
|---|---|---|---|
logFilePath |
string | Yes | Absolute path to the Apex debug log file (.log) |
topMethods |
number | No | Number of slowest methods to return (default: 10) |
minDuration |
number | No | Minimum duration in milliseconds to include a method (default: 0) |
namespace |
string | No | Filter methods by namespace |
get_apex_log_summary
Get a high-level summary of an Apex debug log including total execution time (in ms), method count, SOQL/DML totals, governor limits, and active namespaces. Best for a quick overview before deeper analysis.
| Parameter | Type | Required | Description |
|---|---|---|---|
logFilePath |
string | Yes | Absolute path to the Apex debug log file (.log) |
find_performance_bottlenecks
Check whether an Apex log transaction is approaching governor limits (flags usage above 80%). Analyzes CPU time, SOQL/DML limits, query rows, and method execution patterns by namespace. Best for checking if a transaction is at risk of hitting governor limits.
| Parameter | Type | Required | Description |
|---|---|---|---|
logFilePath |
string | Yes | Absolute path to the Apex debug log file (.log) |
analysisType |
string | No | Type of analysis (default: all). See values below. |
analysisType values:
| Value | Description |
|---|---|
cpu |
Checks CPU time governor limit |
database |
Checks SOQL query, DML statement, and query row limits |
methods |
Groups methods by namespace with duration totals |
all |
Runs all three analysis types (default) |
execute_anonymous
Executes anonymous Apex code against any authenticated Salesforce org. Saves the resulting debug log to a local file and returns a summary with the file path. Use the file path with get_apex_log_summary, analyze_apex_log_performance, or find_performance_bottlenecks for deeper analysis.
| Parameter | Type | Required | Description |
|---|---|---|---|
apex |
string | Yes | The anonymous Apex to be executed |
targetOrg |
string | No | Alias or username of the target Salesforce org. Uses the project default if not specified. |
outputDir |
string | No | Directory to save the debug log file. Defaults to .apex-log-mcp/ in the project root. |
debugLevel |
string | object | No | Controls the trace flag debug levels. Use "default" to reset all categories to defaults, a log level string (e.g. "FINEST") to set all categories to that level, or an object to override specific categories. Omit to keep existing config. |
debugLevel as an object — override specific categories, the rest keep their defaults:
{ "database": "FINEST", "apexCode": "FINE" }
Each category accepts a log level: NONE, ERROR, WARN, INFO, DEBUG, FINE, FINER, FINEST
Default debug levels (used when debugLevel is omitted):
| Category | Default Level |
|---|---|
apexCode |
FINE |
apexProfiling |
FINE |
callout |
DEBUG |
database |
FINEST |
nba |
INFO |
system |
DEBUG |
validation |
DEBUG |
visualforce |
FINE |
wave |
INFO |
workflow |
FINE |
Example prompts:
- "Execute this Apex and show me the log:
System.debug('Hello');" - "Run a query for all Accounts and analyze the performance"
- "Execute this Apex with all debug levels set to FINEST"
- "Run this Apex against my QA org with database logging set to FINEST"
Note: Requires
--allowed-orgsto be configured. Uses the project's default org unlesstargetOrgis specified. The debug log is saved to a local file (default:.apex-log-mcp/) and the response includes the file path, org username (and alias, if set), and execution summary. Add.apex-log-mcp/to your.gitignoreto avoid committing debug logs.
Configuration
The Quick Start configuration is all you need for log analysis tools. The sections below cover enabling execute_anonymous.
Enabling execute_anonymous
The execute_anonymous tool is disabled by default. To enable it, pass --allowed-orgs with a comma-separated list of allowed orgs:
{
"mcpServers": {
"apex-log-mcp": {
"command": "npx",
"args": [
"-y",
"@certinia/apex-log-mcp",
"--allowed-orgs",
"ALLOW_ALL_ORGS"
]
}
}
}
Allowed org tokens
| Token | Description |
|---|---|
ALLOW_ALL_ORGS |
Permits execution against any authenticated org |
DEFAULT_TARGET_ORG |
Resolves the project/global default target-org from Salesforce CLI |
DEFAULT_TARGET_DEV_HUB |
Resolves the project/global default target-dev-hub from Salesforce CLI |
You can also pass org usernames or aliases directly:
"args": ["-y", "@certinia/apex-log-mcp", "--allowed-orgs", "dev@example.com,my-scratch-org"]
How It Works
This server implements the Model Context Protocol (MCP) to expose Apex log analysis as tools that any MCP-compatible AI client can call.
- Runs as a local process — your AI client spawns the server and communicates locally. No network requests, no API keys.
- Uses the same parser as the Apex Log Analyzer VS Code extension — battle-tested parsing of the Apex debug log format.
- Returns structured data — all durations in milliseconds, governor limits as used/limit pairs, methods with SOQL/DML counts — so your AI assistant can reason about the results.
Documentation
Related Projects
- Apex Log Analyzer VS Code Extension — Full-featured Apex log analyzer for VS Code
Contributing
We welcome contributions! Please see our Contributing Guide for details.
- Developing — Set up your development environment
- Code of Conduct — Community guidelines
Contributors
Thanks to our amazing contributors!
<p align="center"> <a href="https://github.com/certinia/debug-log-analyzer-mcp/graphs/contributors"> <img src="https://contrib.rocks/image?repo=certinia/debug-log-analyzer-mcp&max=25" /> </a> </p>
License
<p align="center"> Copyright © Certinia Inc. All rights reserved. </p> <p align="center"> <a href="https://opensource.org/licenses/BSD-3-Clause"> <img src="https://img.shields.io/badge/License-BSD_3--Clause-blue.svg?style=flat-square"/> </a> </p>
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。