codelogic-mcp-server

An MCP Server to utilize Codelogic's rich software dependency data in your AI programming assistant.

Components

Tools

The server implements eleven tools: five original tools plus six graph tools backed by the CodeLogic graph HTTP API.

Code Analysis Tools

• codelogic-method-impact: Pulls an impact assessment from the CodeLogic server's APIs for your code.
  • Takes the given "method" that you're working on and its associated "class".
• codelogic-database-impact: Analyzes impacts between code and database entities.
  • Takes the database entity type (column, table, or view) and its name.

DevOps & CI/CD Integration Tools

• codelogic-docker-agent: Generates Docker agent configurations for CodeLogic scanning in CI/CD pipelines.
  • Supports .NET, Java, SQL, and TypeScript agents
  • Generates configurations for Jenkins, GitHub Actions, Azure DevOps, and GitLab CI
• codelogic-build-info: Generates build information and send commands for CodeLogic integration.
  • Supports Git information, build logs, and metadata collection
  • Provides both Docker and standalone usage examples
• codelogic-pipeline-helper: Generates complete CI/CD pipeline configurations for CodeLogic integration.
  • Creates comprehensive pipeline configurations with best practices
  • Includes error handling, notifications, and scan space management strategies

Graph API tools

These call POST / GET endpoints under /codelogic/server/ai-retrieval/graph/ on the same host as CODELOGIC_SERVER_HOST, using the same session auth as other MCP tools. If graph routes are not deployed, the server returns a clear “graph not available” style message (often after HTTP 404).

• codelogic-graph-capabilities: GET — discover supported relationship types, limits, and flags for the workspace materialized view (materializedViewId defaults from CODELOGIC_WORKSPACE_NAME like other tools).
• codelogic-graph-search: Search nodes by text query / q and/or identity_prefix; optional scan_space, limit, etc.
• codelogic-graph-impact: Dependency / blast-radius style traversal from seed_node_ids.
• codelogic-graph-path-explain: Shortest-path style explanation between from_node_id and to_node_id.
• codelogic-graph-validate-change-scope: Heuristic checklist / risk summary for a proposed change given seed nodes and proposed_change_summary.
• codelogic-graph-owners: Resolve a node by node_id or identity_prefix and surface property fields whose names contain "owner".

Tool arguments accept snake_case aliases (for example materialized_view_id, seed_node_ids) where noted in the MCP schema; request bodies sent to CodeLogic use camelCase JSON keys.

Install

Pre Requisites

The MCP server relies upon Astral UV to run, please install

MacOS Workaround for uvx

There 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: See issue #11

Failed to connect client closed

This appears to be a problem with Astral uvx running on MacOS. The following can be used as a workaround:

1. Clone this project locally.
2. Configure your mcp.json to use uv instead of uvx. For example:

{
  "mcpServers": {
    "codelogic-mcp-server": {
      "type": "stdio",
      "command": "<PATH_TO_UV>/uv",
      "args": [
        "--directory",
        "<PATH_TO_THIS_REPO>/codelogic-mcp-server-main",
        "run",
        "codelogic-mcp-server"
      ],
      "env": {
        "CODELOGIC_SERVER_HOST": "<url to the server e.g. https://myco.app.codelogic.com>",
        "CODELOGIC_USERNAME": "<my username>",
        "CODELOGIC_PASSWORD": "<my password>",
        "CODELOGIC_WORKSPACE_NAME": "<my workspace>",
        "CODELOGIC_DEBUG_MODE": "true"
      }
    }
  }
}

3. Restart Cursor.
4. Ensure the Cursor Global Rule for CodeLogic is in place.
5. Open the MCP tab in Cursor and refresh the codelogic-mcp-server.
6. Ask Cursor to make a code change in an existing class. The MCP server should now run the impact analysis successfully.

Configuration for Different IDEs

Visual Studio Code Configuration

To configure this MCP server in VS Code:

1. First, ensure you have GitHub Copilot agent mode enabled in VS Code.

2. Create a .vscode/mcp.json file in your workspace with the following configuration:

{
  "servers": {
    "codelogic-mcp-server": {
      "type": "stdio",
      "command": "uvx",
      "args": [
        "codelogic-mcp-server@latest"
      ],
      "env": {
        "CODELOGIC_SERVER_HOST": "<url to the server e.g. https://myco.app.codelogic.com>",
        "CODELOGIC_USERNAME": "<my username>",
        "CODELOGIC_PASSWORD": "<my password>",
        "CODELOGIC_WORKSPACE_NAME": "<my workspace>",
        "CODELOGIC_DEBUG_MODE": "true"
      }
    }
  }
}

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.

3. Alternatively, you can run the MCP: Add Server command from the Command Palette and provide the server information.

4. To manage your MCP servers, use the MCP: List Servers command from the Command Palette.

5. 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.

6. 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.

Claude Desktop Configuration

Configure Claude Desktop by editing the configuration file:

• On MacOS: ~/Library/Application\ Support/Claude/claude_desktop_config.json
• On Windows: %APPDATA%/Claude/claude_desktop_config.json
• On Linux: ~/.config/Claude/claude_desktop_config.json

Add the following to your configuration file:

"mcpServers": {
  "codelogic-mcp-server": {
    "command": "uvx",
    "args": [
      "codelogic-mcp-server@latest"
    ],
    "env": {
      "CODELOGIC_SERVER_HOST": "<url to the server e.g. https://myco.app.codelogic.com>",
      "CODELOGIC_USERNAME": "<my username>",
      "CODELOGIC_PASSWORD": "<my password>",
      "CODELOGIC_WORKSPACE_NAME": "<my workspace>"
    }
  }
}

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.

After adding the configuration, restart Claude Desktop to apply the changes.

Windsurf IDE Configuration

To run this MCP server with Windsurf IDE:

Configure Windsurf IDE:

To configure Windsurf IDE, you need to create or modify the ~/.codeium/windsurf/mcp_config.json configuration file.

Add the following configuration to your file:

"mcpServers": {
  "codelogic-mcp-server": {
    "command": "uvx",
    "args": [
      "codelogic-mcp-server@latest"
    ],
    "env": {
      "CODELOGIC_SERVER_HOST": "<url to the server e.g. https://myco.app.codelogic.com>",
      "CODELOGIC_USERNAME": "<my username>",
      "CODELOGIC_PASSWORD": "<my password>",
      "CODELOGIC_WORKSPACE_NAME": "<my workspace>"
    }
  }
}

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.

After adding the configuration, restart Windsurf IDE or refresh the tools to apply the changes.

Cursor Configuration

To configure the CodeLogic MCP server in Cursor:

1. Configure the MCP server by creating a .cursor/mcp.json file:

{
  "mcpServers": {
    "codelogic-mcp-server": {
      "command": "uvx",
      "args": [
        "codelogic-mcp-server@latest"
      ],
      "env": {
        "CODELOGIC_SERVER_HOST": "<url to the server e.g. https://myco.app.codelogic.com>",
        "CODELOGIC_USERNAME": "<my username>",
        "CODELOGIC_PASSWORD": "<my password>",
        "CODELOGIC_WORKSPACE_NAME": "<my workspace>",
        "CODELOGIC_DEBUG_MODE": "true"
      }
    }
  }
}

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.

2. Restart Cursor to apply the changes.

The CodeLogic MCP server tools will now be available in your Cursor workspace.

DevOps Integration

The CodeLogic MCP Server now includes powerful DevOps capabilities for integrating CodeLogic scanning into your CI/CD pipelines. These tools help DevOps teams:

Docker Agent Integration

• Generate Docker run commands for CodeLogic agents
• Create platform-specific configurations (Jenkins, GitHub Actions, Azure DevOps, GitLab CI)
• Set up proper environment variables and volume mounts
• Include build information collection

Build Information Management

• Send Git information, build logs, and metadata to CodeLogic servers
• Support multiple CI/CD platforms with platform-specific variables
• Handle log file management and rotation
• Provide both Docker and standalone usage options

Complete Pipeline Configuration

• Generate end-to-end CI/CD pipeline configurations
• Include error handling, notifications, and monitoring
• Support different scan space management strategies
• Follow DevOps best practices for security and performance

Example Usage

# Generate Docker agent configuration for .NET
codelogic-docker-agent --agent-type=dotnet --scan-path=/app --application-name=MyApp --ci-platform=jenkins

# Set up build information sending
codelogic-build-info --build-type=all --output-format=docker --ci-platform=github-actions

# Create complete pipeline configuration
codelogic-pipeline-helper --ci-platform=jenkins --agent-type=dotnet --scan-triggers=main,develop

AI Assistant Instructions/Rules

To 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:

When the graph API is available on your CodeLogic host, extend your rules with the same guidance the server already advertises in its MCP instructions: use codelogic-graph-* tools (search, impact, path-explain, validate-change-scope, owners, capabilities) for bounded graph discovery; if graph calls fail with “not available”, fall back to codelogic-method-impact / codelogic-database-impact.

VS Code (GitHub Copilot) Instructions

Create a .vscode/copilot-instructions.md file with the following content:

# CodeLogic MCP Server Instructions

When modifying existing code methods:
- Use codelogic-method-impact to analyze code changes
- Use codelogic-database-impact for database modifications
- When the CodeLogic graph API is available, use codelogic-graph-* tools (search, impact, path-explain, validate-change-scope, owners, capabilities) for bounded graph discovery; otherwise rely on method/database impact tools
- Highlight impact results for the modified methods

When modifying SQL code or database entities:
- Always use codelogic-database-impact to analyze potential impacts
- Highlight impact results for the modified database entities

For DevOps and CI/CD integration:
- Use codelogic-docker-agent to generate Docker agent configurations
- Use codelogic-build-info to set up build information sending
- Use codelogic-pipeline-helper to create complete CI/CD pipeline configurations
- Support Jenkins, GitHub Actions, Azure DevOps, and GitLab CI platforms

To use the CodeLogic tools effectively:
- For code impacts: Ask about specific methods or functions
- For database relationships: Ask about tables, views, or columns
- For DevOps: Ask about CI/CD integration, Docker agents, or build information
- Review the impact results before making changes
- Consider both direct and indirect impacts

Claude Desktop Instructions

Create a file ~/.claude/instructions.md with the following content:

# CodeLogic MCP Server Instructions

When modifying existing code methods:
- Use codelogic-method-impact to analyze code changes
- Use codelogic-database-impact for database modifications
- When the CodeLogic graph API is available, use codelogic-graph-* tools (search, impact, path-explain, validate-change-scope, owners, capabilities) for bounded graph discovery; otherwise rely on method/database impact tools
- Highlight impact results for the modified methods

When modifying SQL code or database entities:
- Always use codelogic-database-impact to analyze potential impacts
- Highlight impact results for the modified database entities

For DevOps and CI/CD integration:
- Use codelogic-docker-agent to generate Docker agent configurations
- Use codelogic-build-info to set up build information sending
- Use codelogic-pipeline-helper to create complete CI/CD pipeline configurations
- Support Jenkins, GitHub Actions, Azure DevOps, and GitLab CI platforms

To use the CodeLogic tools effectively:
- For code impacts: Ask about specific methods or functions
- For database relationships: Ask about tables, views, or columns
- For DevOps: Ask about CI/CD integration, Docker agents, or build information
- Review the impact results before making changes
- Consider both direct and indirect impacts

Windsurf IDE Rules

Create or modify the ~/.codeium/windsurf/memories/global_rules.md markdown file with the following content:

When modifying existing code methods:
- Use codelogic-method-impact to analyze code changes
- Use codelogic-database-impact for database modifications
- When the CodeLogic graph API is available, use codelogic-graph-* tools (search, impact, path-explain, validate-change-scope, owners, capabilities) for bounded graph discovery; otherwise rely on method/database impact tools
- Highlight impact results for the modified methods

When modifying SQL code or database entities:
- Always use codelogic-database-impact to analyze potential impacts
- Highlight impact results for the modified database entities

For DevOps and CI/CD integration:
- Use codelogic-docker-agent to generate Docker agent configurations
- Use codelogic-build-info to set up build information sending
- Use codelogic-pipeline-helper to create complete CI/CD pipeline configurations
- Support Jenkins, GitHub Actions, Azure DevOps, and GitLab CI platforms

To use the CodeLogic tools effectively:
- For code impacts: Ask about specific methods or functions
- For database relationships: Ask about tables, views, or columns
- For DevOps: Ask about CI/CD integration, Docker agents, or build information
- Review the impact results before making changes
- Consider both direct and indirect impacts

Cursor Global Rule

To configure CodeLogic rules in Cursor:

1. Open Cursor Settings
2. Navigate to the "Rules" section
3. Add the following content to "User Rules":

# CodeLogic MCP Server Rules
## Codebase
- The CodeLogic MCP Server is for java, javascript, typescript, and C# dotnet codebases
- don't run the tools on python or other non supported codebases
## AI Assistant Behavior
- When modifying existing code methods:
  - Use codelogic-method-impact to analyze code changes
  - Use codelogic-database-impact for database modifications
  - When the CodeLogic graph API is available, use codelogic-graph-* tools (search, impact, path-explain, validate-change-scope, owners, capabilities) for bounded graph discovery; otherwise rely on method/database impact tools
  - Highlight impact results for the modified methods
- When modifying SQL code or database entities:
  - Always use codelogic-database-impact to analyze potential impacts
  - Highlight impact results for the modified database entities
- To use the CodeLogic tools effectively:
  - For code impacts: Ask about specific methods or functions
  - For database relationships: Ask about tables, views, or columns
  - Review the impact results before making changes
  - Consider both direct and indirect impacts

Environment Variables

The following environment variables can be configured to customize the behavior of the server:

• CODELOGIC_SERVER_HOST: The URL of the CodeLogic server.
• CODELOGIC_USERNAME: Your CodeLogic username.
• CODELOGIC_PASSWORD: Your CodeLogic password.
• CODELOGIC_WORKSPACE_NAME: The name of the workspace to use.
• 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.

Tests only

• CODELOGIC_GRAPH_E2E_REQUIRED: Set to 1 when running graph MCP integration tests if you want missing graph APIs (HTTP 404 / “Graph API not available”) to fail the suite instead of skipping those tests.

Example Configuration

"env": {
  "CODELOGIC_SERVER_HOST": "<url to the server e.g. https://myco.app.codelogic.com>",
  "CODELOGIC_USERNAME": "<my username>",
  "CODELOGIC_PASSWORD": "<my password>",
  "CODELOGIC_WORKSPACE_NAME": "<my workspace>",
  "CODELOGIC_DEBUG_MODE": "true"
}

Pinning the version

instead 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 e.g.

    "args": [
      "codelogic-mcp-server@0.2.2"
    ],

Version Compatibility

This MCP server has the following version compatibility requirements:

• Version 0.3.1 and below: Compatible with all CodeLogic API versions
• Version 0.4.0 and above: Requires CodeLogic API version 25.10.0 or greater

If you're upgrading, make sure your CodeLogic server meets the minimum API version requirement.

Graph tools: Require your CodeLogic deployment to serve the graph endpoints under /codelogic/server/ai-retrieval/graph/. Older or partial deployments may return 404; the MCP tools surface that as a clear error instead of opaque failures.

Debug Logging

When CODELOGIC_DEBUG_MODE=true, debug files are written to the system temporary directory:

• Windows: %TEMP%\codelogic-mcp-server (typically C:\Users\{username}\AppData\Local\Temp\codelogic-mcp-server)
• macOS: /tmp/codelogic-mcp-server (or $TMPDIR/codelogic-mcp-server if set)
• Linux: /tmp/codelogic-mcp-server (or $TMPDIR/codelogic-mcp-server if set)

Debug files include:

• timing_log.txt - Performance timing information
• impact_data_*.json - Raw impact analysis data for troubleshooting

Finding your log directory:

import tempfile
import os
print("Log directory:", os.path.join(tempfile.gettempdir(), "codelogic-mcp-server"))

Testing

Running Unit Tests

The project uses unittest for testing. You can run unit tests without any external dependencies:

python -m unittest discover -s test -p "unit_*.py"

Unit tests use mock data and don't require a connection to a CodeLogic server.

Integration Tests (Optional)

If you want to run integration tests that connect to a real CodeLogic server:

1. Copy test/.env.test.example to test/.env.test and populate with your CodeLogic server details
2. Run the integration tests:

python -m unittest discover -s test -p "integration_*.py"

Note: Integration tests require access to a CodeLogic server instance.

Graph MCP end-to-end tests

test/integration_test_graph.py drives the real MCP handler path (handle_call_tool) for codelogic-graph-capabilities and a chained flow (search → impact → path → validate → owners) against CODELOGIC_SERVER_HOST. Configure credentials the same way as other integration tests (test/.env.test from test/.env.test.example).

• If the host does not expose graph routes, tests skip by default.
• Set CODELOGIC_GRAPH_E2E_REQUIRED=1 to turn missing graph APIs into hard failures (useful in CI when graph must be present).

From the repo root:

./scripts/run_graph_e2e.sh

Equivalent:

uv run python -m unittest test.integration_test_graph -v

Validation for Official MCP Registry

mcp-name: io.github.CodeLogicIncEngineering/codelogic-mcp-server