Skip to main content
Glama

interceptor_spawn

Spawn a command with pre-configured proxy environment variables to route traffic through the MITM proxy for interception and modification.

Instructions

Spawn a command with proxy env vars pre-configured (HTTP_PROXY, HTTPS_PROXY, SSL_CERT_FILE, NODE_EXTRA_CA_CERTS, CURL_CA_BUNDLE, and 15+ more). Traffic automatically routes through the MITM proxy.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
commandYesCommand to run (e.g., 'curl', 'node', 'python')
argsNoCommand arguments
cwdNoWorking directory (default: current)
envNoAdditional env vars to set

Implementation Reference

  • MCP tool registration for 'interceptor_spawn' using server.tool() with Zod schema for command, args, cwd, env.
    server.tool(
      "interceptor_spawn",
      "Spawn a command with proxy env vars pre-configured (HTTP_PROXY, HTTPS_PROXY, SSL_CERT_FILE, NODE_EXTRA_CA_CERTS, CURL_CA_BUNDLE, and 15+ more). Traffic automatically routes through the MITM proxy.",
      {
        command: z.string().describe("Command to run (e.g., 'curl', 'node', 'python')"),
        args: z.array(z.string()).optional().default([]).describe("Command arguments"),
        cwd: z.string().optional().describe("Working directory (default: current)"),
        env: z.record(z.string()).optional().describe("Additional env vars to set"),
      },
      async ({ command, args, cwd, env }) => {
        try {
          const proxyInfo = requireProxy();
          const result = await interceptorManager.activate("terminal", {
            ...proxyInfo,
            command,
            args,
            cwd,
            env,
          });
          return {
            content: [{
              type: "text",
              text: JSON.stringify({ status: "success", ...result }),
            }],
          };
        } catch (e) {
          return { content: [{ type: "text", text: JSON.stringify({ status: "error", error: errorToString(e) }) }] };
        }
      },
    );
  • Handler function that calls requireProxy() to get proxy info and interceptorManager.activate('terminal') to spawn the command with proxy env vars.
    async ({ command, args, cwd, env }) => {
      try {
        const proxyInfo = requireProxy();
        const result = await interceptorManager.activate("terminal", {
          ...proxyInfo,
          command,
          args,
          cwd,
          env,
        });
        return {
          content: [{
            type: "text",
            text: JSON.stringify({ status: "success", ...result }),
          }],
        };
      } catch (e) {
        return { content: [{ type: "text", text: JSON.stringify({ status: "error", error: errorToString(e) }) }] };
      }
    },
  • Zod input schema: command (string, required), args (array of strings, optional), cwd (string, optional), env (record of strings, optional).
    {
      command: z.string().describe("Command to run (e.g., 'curl', 'node', 'python')"),
      args: z.array(z.string()).optional().default([]).describe("Command arguments"),
      cwd: z.string().optional().describe("Working directory (default: current)"),
      env: z.record(z.string()).optional().describe("Additional env vars to set"),
  • requireProxy() helper: validates proxy is running and returns proxyPort, certPem, and certFingerprint used by interceptor_spawn handler.
    function requireProxy(): { proxyPort: number; certPem: string; certFingerprint: string } {
      if (!proxyManager.isRunning()) {
        throw new Error("Proxy is not running. Start it first with proxy_start.");
      }
      const cert = proxyManager.getCert();
      if (!cert) {
        throw new Error("No certificate available. Start the proxy first.");
      }
      return {
        proxyPort: proxyManager.getPort()!,
        certPem: cert.cert,
        certFingerprint: cert.fingerprint,
      };
    }
  • TerminalInterceptor.activate(): core logic that spawns the child process with proxy env vars (HTTP_PROXY, HTTPS_PROXY, SSL_CERT_FILE, etc.) and returns targetId.
    async activate(options: ActivateOptions): Promise<ActivateResult> {
      const { proxyPort, certPem, certFingerprint } = options;
      const command = options.command as string | undefined;
      const args = options.args as string[] | undefined;
      const cwd = options.cwd as string | undefined;
      const env = options.env as Record<string, string> | undefined;
    
      if (!command) {
        throw new Error("'command' option is required for terminal interceptor");
      }
    
      // Write cert to temp file for SSL_CERT_FILE and friends
      const certPath = await writeCertTempFile(certPem);
    
      const proxyUrl = `http://127.0.0.1:${proxyPort}`;
    
      // Build env with proxy vars
      const proxyEnv: Record<string, string> = {
        ...process.env as Record<string, string>,
        ...env,
        // Standard proxy vars (both cases for compatibility)
        HTTP_PROXY: proxyUrl,
        HTTPS_PROXY: proxyUrl,
        http_proxy: proxyUrl,
        https_proxy: proxyUrl,
        // SSL certificate file (many tools check this)
        SSL_CERT_FILE: certPath,
        // Node.js
        NODE_EXTRA_CA_CERTS: certPath,
        NODE_TLS_REJECT_UNAUTHORIZED: "0",
        // Python requests
        REQUESTS_CA_BUNDLE: certPath,
        // curl
        CURL_CA_BUNDLE: certPath,
        // AWS SDK
        AWS_CA_BUNDLE: certPath,
        // Deno
        DENO_CERT: certPath,
        DENO_TLS_CA_STORE: "system",
        // Git
        GIT_SSL_CAINFO: certPath,
        GIT_SSL_NO_VERIFY: "true",
        // npm/yarn
        npm_config_proxy: proxyUrl,
        npm_config_https_proxy: proxyUrl,
        npm_config_cafile: certPath,
        npm_config_strict_ssl: "false",
        // Certificate fingerprint (for reference)
        PROXY_MCP_CERT_FINGERPRINT: certFingerprint,
      };
    
      const child = spawn(command, args ?? [], {
        cwd,
        env: proxyEnv,
        stdio: ["ignore", "pipe", "pipe"],
        detached: false,
      });
    
      const targetId = `proc_${child.pid ?? Date.now()}`;
    
      const entry: SpawnedProcess = {
        target: {
          id: targetId,
          description: `${command} ${(args ?? []).join(" ")}`.trim(),
          activatedAt: Date.now(),
          details: {
            pid: child.pid,
            command,
            args: args ?? [],
            cwd: cwd ?? process.cwd(),
            proxyUrl,
            certPath,
          },
        },
        process: child,
        stdout: "",
        stderr: "",
        exitCode: null,
        exited: false,
      };
    
      // Capture stdout/stderr in ring buffers
      child.stdout?.on("data", (chunk: Buffer) => {
        entry.stdout += chunk.toString("utf-8");
        if (entry.stdout.length > MAX_OUTPUT_BUFFER) {
          entry.stdout = entry.stdout.slice(-MAX_OUTPUT_BUFFER);
        }
      });
    
      child.stderr?.on("data", (chunk: Buffer) => {
        entry.stderr += chunk.toString("utf-8");
        if (entry.stderr.length > MAX_OUTPUT_BUFFER) {
          entry.stderr = entry.stderr.slice(-MAX_OUTPUT_BUFFER);
        }
      });
    
      child.on("exit", (code) => {
        entry.exitCode = code;
        entry.exited = true;
      });
    
      child.on("error", (err) => {
        entry.stderr += `\n[spawn error] ${err.message}`;
        entry.exited = true;
      });
    
      this.spawned.set(targetId, entry);
    
      return {
        targetId,
        details: {
          pid: child.pid,
          command,
          args: args ?? [],
          proxyUrl,
          certPath,
        },
      };
    }
Behavior3/5

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

No annotations provided, so description carries full burden. It discloses that traffic routes through MITM proxy, but lacks details on command execution behavior (e.g., synchronous vs asynchronous, output handling) and required proxy state.

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?

Two sentences, no fluff. First sentence front-loads the core purpose; second adds key behavioral context. Highly efficient.

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

Completeness3/5

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

Given 4 parameters and no output schema, description covers the basic purpose and one behavioral aspect, but omits critical details like return value, error handling, and dependency on proxy being active. Adequate but incomplete.

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

Parameters4/5

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

Input schema provides full coverage for all parameters. Description adds value by listing specific env variables (HTTP_PROXY, HTTPS_PROXY, etc.) and indicating there are more, enhancing parameter understanding beyond schema.

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?

Description clearly states it spawns a command with proxy env vars pre-configured. It distinguishes itself from sibling tools by focusing on running arbitrary commands with proxy settings, unlike browser or Android specific tools.

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

Usage Guidelines3/5

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

No explicit when-to-use or when-not-to-use guidance. It implies usage for running commands through the proxy, but does not mention alternatives or prerequisites like ensuring the proxy is running.

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/yfe404/proxy-mcp'

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