Skip to main content
Glama
aledlie

Doppler MCP Server

by aledlie

doppler_run

Execute commands with Doppler secrets automatically injected as environment variables to securely manage sensitive data during runtime.

Instructions

Run a command with Doppler secrets injected as environment variables

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
commandYesThe command to run with Doppler secrets
projectNoThe Doppler project name (optional if set via doppler setup)
configNoThe Doppler config name (optional if set via doppler setup)

Implementation Reference

  • Specific handler logic for 'doppler_run' tool: constructs the 'doppler run --project X --config Y -- command' CLI invocation.
    case "doppler_run":
      parts.push("run");
      if (getString("project")) parts.push("--project", getString("project")!);
      if (getString("config")) parts.push("--config", getString("config")!);
      parts.push("--", getString("command")!);
      // Note: doppler run doesn't support --json flag
      break;
  • Defines the name, description, and input schema (command required, project/config optional) for the doppler_run tool.
    {
      name: "doppler_run",
      description: "Run a command with Doppler secrets injected as environment variables",
      inputSchema: {
        type: "object",
        properties: {
          command: {
            type: "string",
            description: "The command to run with Doppler secrets",
          },
          project: {
            type: "string",
            description: "The Doppler project name (optional if set via doppler setup)",
          },
          config: {
            type: "string",
            description: "The Doppler config name (optional if set via doppler setup)",
          },
        },
        required: ["command"],
      },
    },
  • src/index.ts:27-31 (registration)
    Registers the list tools handler which returns all tool definitions, including doppler_run.
    server.setRequestHandler(ListToolsRequestSchema, async () => {
      return {
        tools: toolDefinitions,
      };
    });
  • MCP server request handler for calling any tool, including doppler_run, by invoking executeCommand with the tool name and arguments.
    server.setRequestHandler(CallToolRequestSchema, async (request) => {
      const { name, arguments: args } = request.params;
    
      try {
        const result = await executeCommand(name, args || {});
        return {
          content: [
            {
              type: "text",
              text: JSON.stringify(result, null, 2),
            },
          ],
        };
      } catch (error) {
        const errorMessage = error instanceof Error ? error.message : String(error);
        throw new McpError(ErrorCode.InternalError, `Doppler CLI error: ${errorMessage}`);
      }
    });
  • Core helper function that builds the CLI command (via buildDopplerCommand) and executes it using Node's execSync, handling output parsing and errors.
    export async function executeCommand(
      toolName: string,
      args: DopplerArgs
    ): Promise<any> {
      const command = buildDopplerCommand(toolName, args);
    
      try {
        const output = execSync(command, {
          encoding: "utf-8",
          stdio: ["pipe", "pipe", "pipe"],
          maxBuffer: 10 * 1024 * 1024, // 10MB buffer
        });
    
        // Try to parse as JSON, if it fails return raw output
        try {
          return JSON.parse(output);
        } catch {
          return { output: output.trim() };
        }
      } catch (error: any) {
        // Handle execution errors
        const stderr = error.stderr?.toString() || "";
        const stdout = error.stdout?.toString() || "";
        const message = stderr || stdout || error.message;
        throw new Error(`Doppler CLI command failed: ${message}`);
      }
    }
Behavior2/5

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

No annotations are provided, so the description carries the full burden. It states the tool runs a command with secret injection but lacks details on permissions, security implications, error handling, or output behavior. For a tool that executes commands with sensitive data, this is a significant gap in behavioral disclosure.

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 a single, efficient sentence that front-loads the core functionality without unnecessary words. Every part of the sentence directly contributes to understanding the tool's purpose.

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

Completeness2/5

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

Given the complexity of running commands with secret injection, no annotations, and no output schema, the description is incomplete. It fails to address critical aspects like security risks, execution environment, or what happens after the command runs, leaving significant gaps for an AI agent.

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

Parameters3/5

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

Schema description coverage is 100%, so the schema already documents all three parameters. The description adds no additional meaning beyond implying secret injection occurs, which is covered by the tool's purpose. Baseline 3 is appropriate as the schema does the heavy lifting.

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 ('Run a command') and resource ('with Doppler secrets injected as environment variables'), distinguishing it from sibling tools that manage configs, projects, or secrets rather than executing commands with secret injection.

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

Usage Guidelines2/5

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

No guidance is provided on when to use this tool versus alternatives like direct command execution or other Doppler tools. The description mentions optional parameters if set via 'doppler setup', but this is a technical note rather than usage context or exclusions.

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/aledlie/doppler-mcp'

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