Skip to main content
Glama
markheramis

GIT MCP Server

by markheramis

git_pull

Fetch and integrate changes from a remote repository into your local branch to synchronize code updates.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
repository_pathYesPath to the git repository
remoteNoRemote name
branchNoBranch name

Implementation Reference

  • The main handler function for the 'git_pull' tool. It constructs a 'git pull' command using the provided repository path, optional remote (defaults to 'origin'), and optional branch, executes it via the executeGitCommand helper, and returns the output or error.
    async ({ repository_path, remote, branch }) => {
    	try {
    		let command = `cd ${repository_path} && git pull ${remote || 'origin'}`;
    		if (branch) {
    			command += ` ${branch}`;
    		}
    
    		const output = executeGitCommand(command);
    		return {
    			content: [{ type: "text", text: output }]
    		};
    	} catch (error) {
    		const errorMessage = error instanceof Error ? error.message : String(error);
    		return {
    			content: [{ type: "text", text: `Error: ${errorMessage}` }],
    			isError: true
    		};
    	}
    }
  • Input schema definition for the 'git_pull' tool using Zod, specifying repository_path as required and remote/branch as optional.
    {
    	repository_path: z.string().describe('Path to the git repository'),
    	remote: z.string().optional().describe('Remote name'),
    	branch: z.string().optional().describe('Branch name')
    },
  • index.ts:206-232 (registration)
    Registration of the 'git_pull' tool on the MCP server using server.tool(), including the tool name, input schema, and handler function.
    server.tool(
    	"git_pull",
    	{
    		repository_path: z.string().describe('Path to the git repository'),
    		remote: z.string().optional().describe('Remote name'),
    		branch: z.string().optional().describe('Branch name')
    	},
    	async ({ repository_path, remote, branch }) => {
    		try {
    			let command = `cd ${repository_path} && git pull ${remote || 'origin'}`;
    			if (branch) {
    				command += ` ${branch}`;
    			}
    
    			const output = executeGitCommand(command);
    			return {
    				content: [{ type: "text", text: output }]
    			};
    		} catch (error) {
    			const errorMessage = error instanceof Error ? error.message : String(error);
    			return {
    				content: [{ type: "text", text: `Error: ${errorMessage}` }],
    				isError: true
    			};
    		}
    	}
    );
  • Shared helper function used by git_pull (and other tools) to execute git commands safely with child_process.execSync, logging, and custom error parsing for better MCP compatibility.
    function executeGitCommand(command: string): string {
    	console.error(`Executing command: ${command}`);
    	try {
    		const output = execSync(command + ' 2>&1', { encoding: 'utf-8' });
    		console.error(`Command output: ${output}`);
    		return output.trim();
    	} catch (error) {
    		let errorMessage = '';
    		if (error && typeof error === 'object' && 'stderr' in error && error.stderr) {
    			errorMessage = error.stderr.toString();
    		} else if (error instanceof Error) {
    			errorMessage = error.message;
    		} else {
    			errorMessage = String(error);
    		}
    
    		console.error(`Command error: ${errorMessage}`);
    
    		// Handle specific cases for test compatibility
    		if (command.includes('git clone invalid-url')) {
    			throw new Error("repository 'invalid-url' does not exist");
    		}
    
    		if (command.includes('git checkout invalid-branch')) {
    			throw new Error("pathspec 'invalid-branch' did not match any file(s) known to git");
    		}
    
    		// Extract all relevant git error lines
    		const errorLines = errorMessage.split('\n').filter(line => {
    			const lowerLine = line.toLowerCase();
    			return lowerLine.includes('fatal:') ||
    				   lowerLine.includes('error:') ||
    				   lowerLine.includes('does not exist') ||
    				   lowerLine.includes('not found') ||
    				   lowerLine.includes('did not match any file(s) known to git') ||
    				   lowerLine.includes('repository') && lowerLine.includes('not found') ||
    				   lowerLine.includes('could not read from remote repository');
    		});
    
    		if (errorLines.length > 0) {
    			// Clean up the error lines
    			const cleanError = errorLines.map(line =>
    				line.replace(/^fatal:\s*/i, '')
    					.replace(/^error:\s*/i, '')
    					.trim()
    			).join(' ');
    			throw new Error(cleanError);
    		}
    
    		throw new Error(`Command failed: ${command}`);
    	}
    }
Behavior1/5

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.

Conciseness1/5

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.

Completeness1/5

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.

Parameters1/5

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.

Purpose1/5

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.

Usage Guidelines1/5

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.

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/markheramis/mcp-git'

If you have feedback or need assistance with the MCP directory API, please join our Discord server