Skip to main content
Glama

mcp_call_conda_info

Retrieve Conda installation details and environment information to diagnose Python configuration issues and understand system setup.

Instructions

Get comprehensive information about the Conda installation on this system.

If env_name is provided, it will return the information for the specified
environment as well.

Returns detailed information including:
- Conda version and configuration
- Python version and virtual packages
- Base environment location
- Channel URLs and package cache locations
- Platform and system details
- Complete list of all Conda environments with their paths
- Complete list of all packages in the specified environment and their versions

This is useful for diagnosing Conda-related issues or understanding
the Python environment configuration on this system.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
env_nameNo

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
resultYes

Implementation Reference

  • Main handler function decorated with @mcp.tool(name="mcp_call_conda_info"). Orchestrates loading conda info, environment list, and optionally package list for the specified environment.
    @mcp.tool(name="mcp_call_conda_info")
    async def mcp_call_conda_info(env_name=None) -> str:
        """Get comprehensive information about the Conda installation on this
        system.
    
        If env_name is provided, it will return the information for the specified
        environment as well.
    
        Returns detailed information including:
        - Conda version and configuration
        - Python version and virtual packages
        - Base environment location
        - Channel URLs and package cache locations
        - Platform and system details
        - Complete list of all Conda environments with their paths
        - Complete list of all packages in the specified environment and their versions
    
        This is useful for diagnosing Conda-related issues or understanding
        the Python environment configuration on this system.
        """
        conda_info = load_conda_info()
        conda_env_list = load_conda_env_list()
        # check None and if it is a string
        if env_name and isinstance(env_name, str):
            conda_env_package_list = load_conda_env_package_list(env_name)
            return f"{conda_info}\n\n{conda_env_list}\n\nPackages in {env_name}:\n\n{conda_env_package_list}"
    
        return conda_info + "\n\n" + conda_env_list
  • Helper function to execute 'conda info' and retrieve basic conda installation information.
    def load_conda_info():
        """Get basic conda info if available."""
        conda_path = find_conda_executable()
        if not conda_path:
            return "Conda not found"
    
        try:
            result = subprocess.run([conda_path, "info"], capture_output=True, text=True)
            if result.returncode == 0:
                return result.stdout
            else:
                return f"Error getting conda info: {result.stderr}"
        except Exception as e:
            return f"Error: {str(e)}"
  • Helper function to list all conda environments, preferring JSON output for parsing, with fallback to standard format.
    def load_conda_env_list():
        """Get conda environment list with improved detection."""
        conda_path = find_conda_executable()
    
        if not conda_path:
            # Provide more detailed information about the system
            system_info = f"System: {platform.system()} {platform.release()} ({platform.machine()})\n"
            paths_info = "PATH directories:\n" + "\n".join([f"- {p}" for p in os.environ.get("PATH", "").split(":")])
    
            error_message = "Conda executable not found. Please ensure Conda is installed."
    
            return f"{error_message}\n{system_info}\n{paths_info}"
    
        try:
            # First try the JSON format for better parsing
            result = subprocess.run([conda_path, "env", "list", "--json"], capture_output=True, text=True)
            if result.returncode == 0 and result.stdout.strip():
                try:
                    env_data = json.loads(result.stdout)
                    output = f"Conda found at: {conda_path}\n\nConda Environments:\n"
                    for env in env_data.get("envs", []):
                        env_name = os.path.basename(env) if not env.endswith("base") else "base"
                        output += f"- {env_name} ({env})\n"
                    return output
                except json.JSONDecodeError:
                    pass
    
            # Fallback to standard format if JSON fails
            result = subprocess.run([conda_path, "env", "list"], capture_output=True, text=True)
            if result.returncode == 0:
                output = f"Conda found at: {conda_path}\n\n{result.stdout}"
                if not result.stdout.strip():
                    return f"Conda found at: {conda_path}\n\nNo conda environments found."
                return output
            else:
                return f"Conda found at: {conda_path}\n\n" f"Error listing conda environments: {result.stderr}"
        except Exception as e:
            return f"Error retrieving conda environments: {str(e)}"
  • Helper function to list packages in a specific conda environment, with input validation and support for both named envs and paths.
    def load_conda_env_package_list(env_name: str):
        """Get the list of packages in the specified conda environment."""
        conda_path = find_conda_executable()
    
        # Validate environment name for security
        if not env_name:
            return "Environment name cannot be empty."
    
        # Sanitize input to prevent command injection
        if not (env_name.startswith("/") or env_name.isalnum() or all(c.isalnum() or c in "_-." for c in env_name)):
            return "Invalid environment name. Use alphanumeric characters, _, -, or . only."
    
        # Path validation for security
        if env_name.startswith("/"):
            # Extra validation for paths to prevent traversal attacks
            normalized_path = os.path.normpath(env_name)
            if ".." in normalized_path or not os.path.exists(normalized_path):
                return f"Invalid or non-existent environment path: {env_name}"
    
        if not conda_path:
            return "Conda executable not found. Please ensure Conda is installed."
    
        try:
            if env_name.startswith("/"):
                # Use --prefix for paths
                result = subprocess.run(
                    [conda_path, "list", "--prefix", env_name],
                    capture_output=True,
                    text=True,
                )
            else:
                # Use --name for named environments
                result = subprocess.run([conda_path, "list", "--name", env_name], capture_output=True, text=True)
    
            if result.returncode == 0:
                return result.stdout
            else:
                return f"Error listing packages in {env_name}: {result.stderr}"
        except Exception as e:
            return f"Error: {str(e)}"
  • Core helper function used by all conda loaders to locate the conda executable on macOS, checking PATH, common paths, Homebrew, etc.
    def find_conda_executable():
        """Find the conda executable path even when conda is not activated."""
        # Common paths where conda might be installed on macOS
        possible_conda_paths = [
            # Standard Anaconda/Miniconda locations
            os.path.expanduser("~/miniconda3/bin/conda"),
            os.path.expanduser("~/anaconda3/bin/conda"),
            os.path.expanduser("~/opt/miniconda3/bin/conda"),
            os.path.expanduser("~/opt/anaconda3/bin/conda"),
            "/opt/miniconda3/bin/conda",
            "/opt/anaconda3/bin/conda",
            # Add miniforge/mambaforge common paths
            os.path.expanduser("~/miniforge3/bin/conda"),
            os.path.expanduser("~/mambaforge/bin/conda"),
            # Applications directory on macOS
            "/Applications/anaconda3/bin/conda",
            "/Applications/miniconda3/bin/conda",
            # Add M1/M2 Mac specific paths
            "/opt/homebrew/anaconda3/bin/conda",
            "/opt/homebrew/miniconda3/bin/conda",
        ]
    
        found_paths = []
    
        # First check if conda is in PATH
        try:
            result = subprocess.run(["which", "conda"], capture_output=True, text=True)
            if result.returncode == 0 and result.stdout.strip():
                path = result.stdout.strip()
                found_paths.append(f"Found in PATH: {path}")
    
                # Extract the actual path if it's a function
                if "conda ()" in path:
                    # Try to find the actual executable by inspecting shell aliases
                    try:
                        alias_result = subprocess.run(["type", "conda"], capture_output=True, text=True, shell=True)
                        if alias_result.returncode == 0:
                            path_lines = alias_result.stdout.strip().split("\n")
                            for line in path_lines:
                                if "/conda" in line and ("bin/" in line or "Scripts/" in line):
                                    potential_path = line.split("'")[-2] if "'" in line else line.split()[-1]
                                    if os.path.isfile(potential_path):
                                        found_paths.append(f"Extracted from alias: {potential_path}")
                                        return potential_path
                    except Exception as e:
                        found_paths.append(f"Error analyzing conda alias: {str(e)}")
                else:
                    # Direct path found in PATH
                    return path
        except Exception as e:
            found_paths.append(f"Error checking PATH: {str(e)}")
    
        # Check common installation paths
        for path in possible_conda_paths:
            if os.path.isfile(path):
                found_paths.append(f"Found in common paths: {path}")
                return path
    
        # Check for Conda installed via Homebrew
        try:
            result = subprocess.run(["brew", "--prefix", "conda"], capture_output=True, text=True)
            if result.returncode == 0 and result.stdout.strip():
                brew_path = os.path.join(result.stdout.strip(), "bin", "conda")
                if os.path.isfile(brew_path):
                    found_paths.append(f"Found via Homebrew: {brew_path}")
                    return brew_path
        except Exception as e:
            found_paths.append(f"Error checking Homebrew: {str(e)}")
    
        # Look for conda-related files in the home directory
        try:
            home = Path.home()
            for conda_dir in home.glob("*conda*"):
                if conda_dir.is_dir():
                    bin_dir = conda_dir / "bin"
                    if bin_dir.is_dir():
                        conda_path = bin_dir / "conda"
                        if conda_path.is_file():
                            found_paths.append(f"Found in home directory: {str(conda_path)}")
                            return str(conda_path)
        except Exception as e:
            found_paths.append(f"Error searching home directory: {str(e)}")
    
        # If we reach here, we didn't find conda
        return None
Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries the full burden of behavioral disclosure. It effectively describes what the tool returns (detailed information across multiple categories), its optional parameter behavior ('If env_name is provided...'), and its practical use cases. It doesn't mention performance characteristics or error conditions, but covers the core behavior well.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is well-structured with clear sections: purpose statement, parameter behavior explanation, detailed return value breakdown, and use case. Every sentence adds value, and the bulleted list efficiently communicates scope without unnecessary verbosity.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's complexity (system diagnostic tool with detailed output), the description provides comprehensive coverage: purpose, parameter semantics, detailed output breakdown, and use cases. With an output schema present, the description appropriately focuses on explaining what information is returned rather than technical return values.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

With 0% schema description coverage and only one parameter, the description adds significant value beyond the schema. It explains that 'env_name' is optional and specifies what happens when it's provided ('returns the information for the specified environment as well'), including that it affects the package list output.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the specific action ('Get comprehensive information about the Conda installation') and resource ('this system'), distinguishing it from sibling tools like GPU availability or system profiler calls. It provides a detailed scope of what information is retrieved.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description explicitly states when to use this tool ('useful for diagnosing Conda-related issues or understanding the Python environment configuration'), providing clear context. However, it doesn't specify when NOT to use it or mention alternatives to this tool.

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/zhongmingyuan/mcp-my-mac'

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