codelogic-mcp-server

# codelogic-mcp-server

An [MCP Server](https://modelcontextprotocol.io/introduction) to utilize Codelogic's rich software dependency data in your AI programming assistant.

## Components

### Tools

The server implements **eight** tools: two impact 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.

#### 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](https://docs.astral.sh/uv/getting-started/installation/)

### 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](https://github.com/CodeLogicIncEngineering/codelogic-mcp-server/issues/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:

```json
{
  "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:

```json
{
  "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:

```json
"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](https://codeium.com/windsurf):

**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:

```json
"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:

```json
{
  "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.

## 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:

```markdown
# 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

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 graph discovery: Prefer codelogic-graph-* tools when available
- Review the impact results before making changes
- Consider both direct and indirect impacts
``