fix: call command outputs raw text content instead of MCP envelope (#30)

Fixes #25

The call command was outputting the full MCP protocol envelope:
  { "content": [{ "type": "text", "text": "..." }] }

Now outputs raw text content directly, making it easier to pipe to
grep, head, jq, and other CLI tools without needing .content[0].text.

Changes:
- Use existing formatToolResult helper in call.ts
- Update SKILL.md examples (remove jq extraction patterns)
- Update CHANGELOG.md to reflect correct behavior
- Add e2e test to prevent regression

Author: philschmid

CHANGELOG.md

@@ -22,8 +22,8 @@
 
 - **3-Subcommand Architecture** - `info`, `grep`, `call`
   - Flexible format support: `server tool` and `server/tool`
-  - `call` always outputs raw JSON (for piping/scripting)
-  - `info`/`grep` always output human-readable format
+  - `call` outputs raw text content (CLI-friendly, pipe to grep/head/etc.)
+  - `info`/`grep` output human-readable format
 
 - **Improved Error Messages for LLMs**
   - AMBIGUOUS_COMMAND: Shows both `call` and `info` options

SKILL.md

@@ -52,40 +52,38 @@ cat args.json | mcp-cli call filesystem read_file
 # Search for tools
 mcp-cli grep "*file*"
 
-# Extract text from result
-mcp-cli call filesystem read_file '{"path": "./file"}' | jq -r '.content[0].text'
+# Output is raw text (pipe-friendly)
+mcp-cli call filesystem read_file '{"path": "./file"}' | head -10
 ```
 
 ## Advanced Chaining
 
 ```bash
 # Chain: search files → read first match
 mcp-cli call filesystem search_files '{"path": ".", "pattern": "*.md"}' \
-  | jq -r '.content[0].text | split("\n")[0]' \
+  | head -1 \
   | xargs -I {} mcp-cli call filesystem read_file '{"path": "{}"}'
 
 # Loop: process multiple files
 mcp-cli call filesystem list_directory '{"path": "./src"}' \
-  | jq -r '.content[0].text | split("\n")[]' \
   | while read f; do mcp-cli call filesystem read_file "{\"path\": \"$f\"}"; done
 
 # Conditional: check before reading
 mcp-cli call filesystem list_directory '{"path": "."}' \
-  | jq -e '.content[0].text | contains("README")' \
+  | grep -q "README" \
   && mcp-cli call filesystem read_file '{"path": "./README.md"}'
 
 # Multi-server aggregation
 {
   mcp-cli call github search_repositories '{"query": "mcp", "per_page": 3}'
   mcp-cli call filesystem list_directory '{"path": "."}'
-} | jq -s '.'
+}
 
 # Save to file
-mcp-cli call github get_file_contents '{"owner": "x", "repo": "y", "path": "z"}' \
-  | jq -r '.content[0].text' > output.txt
+mcp-cli call github get_file_contents '{"owner": "x", "repo": "y", "path": "z"}' > output.txt
 ```
 
-**jq tips:** `-r` raw output, `-e` exit 1 if false, `-s` slurp multiple inputs
+**Note:** `call` outputs raw text content directly (no jq needed for text extraction)
 
 ## Options
 

src/commands/call.ts

@@ -29,7 +29,7 @@ import {
   toolExecutionError,
   toolNotFoundError,
 } from '../errors.js';
-import { formatJson } from '../output.js';
+import { formatJson, formatToolResult } from '../output.js';
 
 export interface CallOptions {
   target: string; // "server/tool"
@@ -161,8 +161,9 @@ export async function callCommand(options: CallOptions): Promise<void> {
   try {
     const result = await connection.callTool(toolName, args);
 
-    // Always output raw JSON for programmatic use
-    console.log(formatJson(result));
+    // Extract text content from MCP response for CLI-friendly output
+    // Uses formatToolResult which extracts text from MCP content array
+    console.log(formatToolResult(result));
   } catch (error) {
     // Try to get available tools for better error message
     let availableTools: string[] | undefined;

tests/integration/cli.test.ts

@@ -241,6 +241,28 @@ describe('CLI Integration Tests', () => {
       // We just verify it doesn't crash
       expect(typeof result.exitCode).toBe('number');
     });
+
+    test('outputs raw text content, not MCP envelope (issue #25)', async () => {
+      // This test ensures the call command outputs raw text content
+      // instead of the full MCP protocol envelope like:
+      // { "content": [{ "type": "text", "text": "..." }] }
+      const result = await runCli([
+        'call',
+        'filesystem',
+        'read_file',
+        JSON.stringify({ path: testFilePath }),
+      ]);
+
+      expect(result.exitCode).toBe(0);
+
+      // Output should be the raw file content
+      expect(result.stdout).toContain('Hello from test file!');
+
+      // Output should NOT contain MCP envelope structure
+      expect(result.stdout).not.toContain('"content"');
+      expect(result.stdout).not.toContain('"type"');
+      expect(result.stdout).not.toContain('"text"');
+    });
   });
 
   describe('error handling', () => {