Codelogic MCP Server

1# codelogic-mcp-server
2 
3An [MCP Server](https://modelcontextprotocol.io/introduction) to utilize Codelogic's rich software dependency data in your AI programming assistant.
4 
5## Components
6 
7### Tools
8 
9The server implements five tools:
10 
11#### Code Analysis Tools
12- **codelogic-method-impact**: Pulls an impact assessment from the CodeLogic server's APIs for your code.
13  - Takes the given "method" that you're working on and its associated "class".
14- **codelogic-database-impact**: Analyzes impacts between code and database entities.
15  - Takes the database entity type (column, table, or view) and its name.
16 
17#### DevOps & CI/CD Integration Tools
18- **codelogic-docker-agent**: Generates Docker agent configurations for CodeLogic scanning in CI/CD pipelines.
19  - Supports .NET, Java, SQL, and TypeScript agents
20  - Generates configurations for Jenkins, GitHub Actions, Azure DevOps, and GitLab CI
21- **codelogic-build-info**: Generates build information and send commands for CodeLogic integration.
22  - Supports Git information, build logs, and metadata collection
23  - Provides both Docker and standalone usage examples
24- **codelogic-pipeline-helper**: Generates complete CI/CD pipeline configurations for CodeLogic integration.
25  - Creates comprehensive pipeline configurations with best practices
26  - Includes error handling, notifications, and scan space management strategies
27 
28### Install
29 
30#### Pre Requisites
31 
32The MCP server relies upon Astral UV to run, please [install](https://docs.astral.sh/uv/getting-started/installation/)
33 
34### MacOS Workaround for uvx
35 
36There is a known issue with `uvx` on **MacOS** where the CodeLogic MCP server may fail to launch in certain IDEs (such as Cursor), resulting in errors like:
37See [issue #11](https://github.com/CodeLogicIncEngineering/codelogic-mcp-server/issues/11)
38```
39Failed to connect client closed
40```
41 
42This appears to be a problem with Astral `uvx` running on MacOS. The following can be used as a workaround:
43 
441. Clone this project locally.
452. Configure your `mcp.json` to use `uv` instead of `uvx`. For example:
46 
47```json
48{
49  "mcpServers": {
50    "codelogic-mcp-server": {
51      "type": "stdio",
52      "command": "<PATH_TO_UV>/uv",
53      "args": [
54        "--directory",
55        "<PATH_TO_THIS_REPO>/codelogic-mcp-server-main",
56        "run",
57        "codelogic-mcp-server"
58      ],
59      "env": {
60        "CODELOGIC_SERVER_HOST": "<url to the server e.g. https://myco.app.codelogic.com>",
61        "CODELOGIC_USERNAME": "<my username>",
62        "CODELOGIC_PASSWORD": "<my password>",
63        "CODELOGIC_WORKSPACE_NAME": "<my workspace>",
64        "CODELOGIC_DEBUG_MODE": "true"
65      }
66    }
67  }
68}
69```
70 
713. Restart Cursor.
724. Ensure the Cursor Global Rule for CodeLogic is in place.
735. Open the MCP tab in Cursor and refresh the `codelogic-mcp-server`.
746. Ask Cursor to make a code change in an existing class. The MCP server should now run the impact analysis successfully.
75 
76## Configuration for Different IDEs
77 
78### Visual Studio Code Configuration
79 
80To configure this MCP server in VS Code:
81 
821. First, ensure you have GitHub Copilot agent mode enabled in VS Code.
83 
842. Create a `.vscode/mcp.json` file in your workspace with the following configuration:
85 
86```json
87{
88  "servers": {
89    "codelogic-mcp-server": {
90      "type": "stdio",
91      "command": "uvx",
92      "args": [
93        "codelogic-mcp-server@latest"
94      ],
95      "env": {
96        "CODELOGIC_SERVER_HOST": "<url to the server e.g. https://myco.app.codelogic.com>",
97        "CODELOGIC_USERNAME": "<my username>",
98        "CODELOGIC_PASSWORD": "<my password>",
99        "CODELOGIC_WORKSPACE_NAME": "<my workspace>",
100        "CODELOGIC_DEBUG_MODE": "true"
101      }
102    }
103  }
104}
105```
106 
107> **Note:** On some systems, you may need to use the full path to the uvx executable instead of just "uvx". For example: `/home/user/.local/bin/uvx` on Linux/Mac or `C:\Users\username\AppData\Local\astral\uvx.exe` on Windows.
108 
1093. Alternatively, you can run the `MCP: Add Server` command from the Command Palette and provide the server information.
110 
1114. To manage your MCP servers, use the `MCP: List Servers` command from the Command Palette.
112 
1135. Once configured, the server's tools will be available to Copilot agent mode. You can toggle specific tools on/off as needed by clicking the Tools button in the Chat view when in agent mode.
114 
1156. To use the Codelogic tools in agent mode, you can specifically ask about code impacts or database relationships, and the agent will utilize the appropriate tools.
116 
117### Claude Desktop Configuration
118 
119Configure Claude Desktop by editing the configuration file:
120 
121- On MacOS: `~/Library/Application\ Support/Claude/claude_desktop_config.json`
122- On Windows: `%APPDATA%/Claude/claude_desktop_config.json`
123- On Linux: `~/.config/Claude/claude_desktop_config.json`
124 
125Add the following to your configuration file:
126 
127```json
128"mcpServers": {
129  "codelogic-mcp-server": {
130    "command": "uvx",
131    "args": [
132      "codelogic-mcp-server@latest"
133    ],
134    "env": {
135      "CODELOGIC_SERVER_HOST": "<url to the server e.g. https://myco.app.codelogic.com>",
136      "CODELOGIC_USERNAME": "<my username>",
137      "CODELOGIC_PASSWORD": "<my password>",
138      "CODELOGIC_WORKSPACE_NAME": "<my workspace>"
139    }
140  }
141}
142```
143 
144> **Note:** On some systems, you may need to use the full path to the uvx executable instead of just "uvx". For example: `/home/user/.local/bin/uvx` on Linux/Mac or `C:\Users\username\AppData\Local\astral\uvx.exe` on Windows.
145 
146After adding the configuration, restart Claude Desktop to apply the changes.
147 
148### Windsurf IDE Configuration
149 
150To run this MCP server with [Windsurf IDE](https://codeium.com/windsurf):
151 
152**Configure Windsurf IDE**:
153 
154To configure Windsurf IDE, you need to create or modify the `~/.codeium/windsurf/mcp_config.json` configuration file.
155 
156Add the following configuration to your file:
157 
158```json
159"mcpServers": {
160  "codelogic-mcp-server": {
161    "command": "uvx",
162    "args": [
163      "codelogic-mcp-server@latest"
164    ],
165    "env": {
166      "CODELOGIC_SERVER_HOST": "<url to the server e.g. https://myco.app.codelogic.com>",
167      "CODELOGIC_USERNAME": "<my username>",
168      "CODELOGIC_PASSWORD": "<my password>",
169      "CODELOGIC_WORKSPACE_NAME": "<my workspace>"
170    }
171  }
172}
173```
174 
175> **Note:** On some systems, you may need to use the full path to the uvx executable instead of just "uvx". For example: `/home/user/.local/bin/uvx` on Linux/Mac or `C:\Users\username\AppData\Local\astral\uvx.exe` on Windows.
176 
177After adding the configuration, restart Windsurf IDE or refresh the tools to apply the changes.
178 
179### Cursor Configuration
180 
181To configure the CodeLogic MCP server in Cursor:
182 
1831. Configure the MCP server by creating a `.cursor/mcp.json` file:
184 
185```json
186{
187  "mcpServers": {
188    "codelogic-mcp-server": {
189      "command": "uvx",
190      "args": [
191        "codelogic-mcp-server@latest"
192      ],
193      "env": {
194        "CODELOGIC_SERVER_HOST": "<url to the server e.g. https://myco.app.codelogic.com>",
195        "CODELOGIC_USERNAME": "<my username>",
196        "CODELOGIC_PASSWORD": "<my password>",
197        "CODELOGIC_WORKSPACE_NAME": "<my workspace>",
198        "CODELOGIC_DEBUG_MODE": "true"
199      }
200    }
201  }
202}
203```
204 
205> **Note:** On some systems, you may need to use the full path to the uvx executable instead of just "uvx". For example: `/home/user/.local/bin/uvx` on Linux/Mac or `C:\Users\username\AppData\Local\astral\uvx.exe` on Windows.
206 
2072. Restart Cursor to apply the changes.
208 
209The CodeLogic MCP server tools will now be available in your Cursor workspace.
210 
211## DevOps Integration
212 
213The CodeLogic MCP Server now includes powerful DevOps capabilities for integrating CodeLogic scanning into your CI/CD pipelines. These tools help DevOps teams:
214 
215### Docker Agent Integration
216- Generate Docker run commands for CodeLogic agents
217- Create platform-specific configurations (Jenkins, GitHub Actions, Azure DevOps, GitLab CI)
218- Set up proper environment variables and volume mounts
219- Include build information collection
220 
221### Build Information Management
222- Send Git information, build logs, and metadata to CodeLogic servers
223- Support multiple CI/CD platforms with platform-specific variables
224- Handle log file management and rotation
225- Provide both Docker and standalone usage options
226 
227### Complete Pipeline Configuration
228- Generate end-to-end CI/CD pipeline configurations
229- Include error handling, notifications, and monitoring
230- Support different scan space management strategies
231- Follow DevOps best practices for security and performance
232 
233### Example Usage
234 
235```bash
236# Generate Docker agent configuration for .NET
237codelogic-docker-agent --agent-type=dotnet --scan-path=/app --application-name=MyApp --ci-platform=jenkins
238 
239# Set up build information sending
240codelogic-build-info --build-type=all --output-format=docker --ci-platform=github-actions
241 
242# Create complete pipeline configuration
243codelogic-pipeline-helper --ci-platform=jenkins --agent-type=dotnet --scan-triggers=main,develop
244```
245 
246## AI Assistant Instructions/Rules
247 
248To help the AI assistant use the CodeLogic tools effectively, you can add the following instructions/rules to your client's configuration. We recommend customizing these instructions to align with your team's specific coding standards, best practices, and workflow requirements:
249 
250### VS Code (GitHub Copilot) Instructions
251 
252Create a `.vscode/copilot-instructions.md` file with the following content:
253 
254```markdown
255# CodeLogic MCP Server Instructions
256 
257When modifying existing code methods:
258- Use codelogic-method-impact to analyze code changes
259- Use codelogic-database-impact for database modifications
260- Highlight impact results for the modified methods
261 
262When modifying SQL code or database entities:
263- Always use codelogic-database-impact to analyze potential impacts
264- Highlight impact results for the modified database entities
265 
266For DevOps and CI/CD integration:
267- Use codelogic-docker-agent to generate Docker agent configurations
268- Use codelogic-build-info to set up build information sending
269- Use codelogic-pipeline-helper to create complete CI/CD pipeline configurations
270- Support Jenkins, GitHub Actions, Azure DevOps, and GitLab CI platforms
271 
272To use the CodeLogic tools effectively:
273- For code impacts: Ask about specific methods or functions
274- For database relationships: Ask about tables, views, or columns
275- For DevOps: Ask about CI/CD integration, Docker agents, or build information
276- Review the impact results before making changes
277- Consider both direct and indirect impacts
278```
279 
280### Claude Desktop Instructions
281 
282Create a file `~/.claude/instructions.md` with the following content:
283 
284```markdown
285# CodeLogic MCP Server Instructions
286 
287When modifying existing code methods:
288- Use codelogic-method-impact to analyze code changes
289- Use codelogic-database-impact for database modifications
290- Highlight impact results for the modified methods
291 
292When modifying SQL code or database entities:
293- Always use codelogic-database-impact to analyze potential impacts
294- Highlight impact results for the modified database entities
295 
296For DevOps and CI/CD integration:
297- Use codelogic-docker-agent to generate Docker agent configurations
298- Use codelogic-build-info to set up build information sending
299- Use codelogic-pipeline-helper to create complete CI/CD pipeline configurations
300- Support Jenkins, GitHub Actions, Azure DevOps, and GitLab CI platforms
301 
302To use the CodeLogic tools effectively:
303- For code impacts: Ask about specific methods or functions
304- For database relationships: Ask about tables, views, or columns
305- For DevOps: Ask about CI/CD integration, Docker agents, or build information
306- Review the impact results before making changes
307- Consider both direct and indirect impacts
308```
309 
310### Windsurf IDE Rules
311 
312Create or modify the `~/.codeium/windsurf/memories/global_rules.md` markdown file with the following content:
313 
314```markdown
315When modifying existing code methods:
316- Use codelogic-method-impact to analyze code changes
317- Use codelogic-database-impact for database modifications
318- Highlight impact results for the modified methods
319 
320When modifying SQL code or database entities:
321- Always use codelogic-database-impact to analyze potential impacts
322- Highlight impact results for the modified database entities
323 
324For DevOps and CI/CD integration:
325- Use codelogic-docker-agent to generate Docker agent configurations
326- Use codelogic-build-info to set up build information sending
327- Use codelogic-pipeline-helper to create complete CI/CD pipeline configurations
328- Support Jenkins, GitHub Actions, Azure DevOps, and GitLab CI platforms
329 
330To use the CodeLogic tools effectively:
331- For code impacts: Ask about specific methods or functions
332- For database relationships: Ask about tables, views, or columns
333- For DevOps: Ask about CI/CD integration, Docker agents, or build information
334- Review the impact results before making changes
335- Consider both direct and indirect impacts
336```
337 
338### Cursor Global Rule
339 
340To configure CodeLogic rules in Cursor:
341 
3421. Open Cursor Settings
3432. Navigate to the "Rules" section
3443. Add the following content to "User Rules":
345 
346```markdown
347# CodeLogic MCP Server Rules
348## Codebase
349- The CodeLogic MCP Server is for java, javascript, typescript, and C# dotnet codebases
350- don't run the tools on python or other non supported codebases
351## AI Assistant Behavior
352- When modifying existing code methods:
353  - Use codelogic-method-impact to analyze code changes
354  - Use codelogic-database-impact for database modifications
355  - Highlight impact results for the modified methods
356- When modifying SQL code or database entities:
357  - Always use codelogic-database-impact to analyze potential impacts
358  - Highlight impact results for the modified database entities
359- To use the CodeLogic tools effectively:
360  - For code impacts: Ask about specific methods or functions
361  - For database relationships: Ask about tables, views, or columns
362  - Review the impact results before making changes
363  - Consider both direct and indirect impacts
364```
365 
366## Environment Variables
367 
368The following environment variables can be configured to customize the behavior of the server:
369 
370- `CODELOGIC_SERVER_HOST`: The URL of the CodeLogic server.
371- `CODELOGIC_USERNAME`: Your CodeLogic username.
372- `CODELOGIC_PASSWORD`: Your CodeLogic password.
373- `CODELOGIC_WORKSPACE_NAME`: The name of the workspace to use.
374- `CODELOGIC_DEBUG_MODE`: Set to `true` to enable debug mode. When enabled, additional debug files such as `timing_log.txt` and `impact_data*.json` will be generated. Defaults to `false`.
375 
376### Example Configuration
377 
378```json
379"env": {
380  "CODELOGIC_SERVER_HOST": "<url to the server e.g. https://myco.app.codelogic.com>",
381  "CODELOGIC_USERNAME": "<my username>",
382  "CODELOGIC_PASSWORD": "<my password>",
383  "CODELOGIC_WORKSPACE_NAME": "<my workspace>",
384  "CODELOGIC_DEBUG_MODE": "true"
385}
386```
387 
388### Pinning the version
389 
390instead of using the **latest** version of the server, you can pin to a specific version by changing the **args** field to match the version in [pypi](https://pypi.org/project/codelogic-mcp-server/) e.g.
391 
392```json
393    "args": [
394      "codelogic-mcp-server@0.2.2"
395    ],
396```
397 
398### Version Compatibility
399 
400This MCP server has the following version compatibility requirements:
401 
402- Version 0.3.1 and below: Compatible with all CodeLogic API versions
403- Version 0.4.0 and above: Requires CodeLogic API version 25.10.0 or greater
404 
405If you're upgrading, make sure your CodeLogic server meets the minimum API version requirement.
406 
407## Debug Logging
408 
409When `CODELOGIC_DEBUG_MODE=true`, debug files are written to the system temporary directory:
410 
411- **Windows**: `%TEMP%\codelogic-mcp-server` (typically `C:\Users\{username}\AppData\Local\Temp\codelogic-mcp-server`)
412- **macOS**: `/tmp/codelogic-mcp-server` (or `$TMPDIR/codelogic-mcp-server` if set)  
413- **Linux**: `/tmp/codelogic-mcp-server` (or `$TMPDIR/codelogic-mcp-server` if set)
414 
415**Debug files include**:
416- `timing_log.txt` - Performance timing information
417- `impact_data_*.json` - Raw impact analysis data for troubleshooting
418 
419**Finding your log directory**:
420```python
421import tempfile
422import os
423print("Log directory:", os.path.join(tempfile.gettempdir(), "codelogic-mcp-server"))
424```
425 
426## Testing
427 
428### Running Unit Tests
429 
430The project uses unittest for testing. You can run unit tests without any external dependencies:
431 
432```bash
433python -m unittest discover -s test -p "unit_*.py"
434```
435 
436Unit tests use mock data and don't require a connection to a CodeLogic server.
437 
438### Integration Tests (Optional)
439 
440If you want to run integration tests that connect to a real CodeLogic server:
441 
4421. Copy `test/.env.test.example` to `test/.env.test` and populate with your CodeLogic server details
4432. Run the integration tests:
444 
445```bash
446python -m unittest discover -s test -p "integration_*.py"
447```
448 
449Note: Integration tests require access to a CodeLogic server instance.
450 
451## Validation for Official MCP Registry
452 
453mcp-name: io.github.CodeLogicIncEngineering/codelogic-mcp-server
454