Remove mcp_config input in favor of --mcp-config in claude_args (#485)

* Remove mcp_config input in favor of --mcp-config in claude_args

BREAKING CHANGE: The mcp_config input has been removed. Users should now use --mcp-config flag in claude_args instead.

This simplifies the action's input surface area and aligns better with the Claude Code CLI interface. Users can still add multiple MCP configurations by using multiple --mcp-config flags.

Migration:
- Before: mcp_config: '{"mcpServers": {...}}'
- After: claude_args: '--mcp-config {"mcpServers": {...}}'

🤖 Generated with [Claude Code](https://claude.ai/code)

Co-Authored-By: Claude <noreply@anthropic.com>

* Add outer action MCP tests to workflow

- Add test-outer-action-inline-mcp job to test inline MCP config via claude_args
- Add test-outer-action-file-mcp job to test file-based MCP config via claude_args
- Keep base-action tests unchanged (they still use mcp_config parameter)
- Test that MCP tools are properly discovered and can be executed through the outer action

🤖 Generated with [Claude Code](https://claude.ai/code)

Co-Authored-By: Claude <noreply@anthropic.com>

* Fix: Add Bun setup to outer action MCP test jobs

The test jobs for the outer action were failing because Bun wasn't installed.
Added Setup Bun step to both test-outer-action-inline-mcp and test-outer-action-file-mcp jobs.

🤖 Generated with [Claude Code](https://claude.ai/code)

Co-Authored-By: Claude <noreply@anthropic.com>

* Add id-token permission to outer action MCP test jobs

The outer action needs id-token: write permission for OIDC authentication
when using the GitHub App. Added full permissions block to both
test-outer-action-inline-mcp and test-outer-action-file-mcp jobs.

🤖 Generated with [Claude Code](https://claude.ai/code)

Co-Authored-By: Claude <noreply@anthropic.com>

* Use github_token parameter instead of id-token permission

Replace id-token: write permission with explicit github_token parameter
for both outer action MCP test jobs. This simplifies authentication by
using the provided GitHub token directly.

🤖 Generated with [Claude Code](https://claude.ai/code)

Co-Authored-By: Claude <noreply@anthropic.com>

* Use RUNNER_TEMP environment variable consistently

Changed from GitHub Actions expression syntax to environment variable
for consistency with the rest of the workflow file.

🤖 Generated with [Claude Code](https://claude.ai/code)

Co-Authored-By: Claude <noreply@anthropic.com>

* Use execution_file output from action instead of hardcoded path

Updated outer action test jobs to:
- Add step IDs (claude-inline-test, claude-file-test)
- Use the execution_file output from the action steps
- This is more reliable than hardcoding the output file path

🤖 Generated with [Claude Code](https://claude.ai/code)

Co-Authored-By: Claude <noreply@anthropic.com>

* tmp

* Fix MCP test assertions to match actual output format

Updated the test assertions to match the actual JSON structure:
- Tool calls are in assistant messages with type='tool_use'
- Tool results are in user messages with type='tool_result'
- The test tool returns 'Test tool response' not 'Hello from test tool'

🤖 Generated with [Claude Code](https://claude.ai/code)

Co-Authored-By: Claude <noreply@anthropic.com>

* Make inline MCP test actually use the tool instead of just listing

Changed the inline MCP test to:
- Request that Claude uses the test tool (not just list it)
- Add --allowedTools to ensure the tool can be used
- Check that the tool was actually called and returned expected result
- Output the full JSON for debugging

This makes both tests (inline and file-based) consistent in their approach.

🤖 Generated with [Claude Code](https://claude.ai/code)

Co-Authored-By: Claude <noreply@anthropic.com>

---------

Co-authored-by: Claude <noreply@anthropic.com>

.github/workflows/issue-triage.yml

@@ -101,7 +101,8 @@ jobs:
         with:
           prompt_file: /tmp/claude-prompts/triage-prompt.txt
           allowed_tools: "Bash(gh label list),mcp__github__get_issue,mcp__github__get_issue_comments,mcp__github__update_issue,mcp__github__search_issues,mcp__github__list_issues"
-          mcp_config: /tmp/mcp-config/mcp-servers.json
+          claude_args: |
+            --mcp-config /tmp/mcp-config/mcp-servers.json
           anthropic_api_key: ${{ secrets.ANTHROPIC_API_KEY }}
         env:
           GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}

.github/workflows/test-mcp-servers.yml

@@ -158,3 +158,134 @@ jobs:
           fi
 
           echo "✓ All MCP server checks passed with --mcp-config flag!"
+
+  # Test the outer action with inline MCP config
+  test-outer-action-inline-mcp:
+    runs-on: ubuntu-latest
+    steps:
+      - name: Checkout repository
+        uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 #v4
+
+      - name: Setup Bun
+        uses: oven-sh/setup-bun@735343b667d3e6f658f44d0eca948eb6282f2b76 #v2
+
+      - name: Install test MCP server dependencies
+        run: |
+          cd base-action/test/mcp-test
+          bun install
+
+      - name: Test outer action with inline MCP config
+        uses: ./
+        id: claude-inline-test
+        with:
+          prompt: "Use the mcp__test-server__test_tool to test the MCP integration"
+          anthropic_api_key: ${{ secrets.ANTHROPIC_API_KEY }}
+          github_token: ${{ secrets.GITHUB_TOKEN }}
+          claude_args: |
+            --mcp-config '{"mcpServers":{"test-server":{"type":"stdio","command":"bun","args":["base-action/test/mcp-test/simple-mcp-server.ts"],"env":{}}}}'
+            --allowedTools mcp__test-server__test_tool
+
+      - name: Check execution output
+        run: |
+          echo "Checking if MCP test tool was used..."
+          OUTPUT_FILE="${{ steps.claude-inline-test.outputs.execution_file }}"
+
+          if [ ! -f "$OUTPUT_FILE" ]; then
+            echo "Error: Output file not found!"
+            exit 1
+          fi
+
+          cat $OUTPUT_FILE
+
+          # Check if the tool was actually called - looking in assistant messages
+          if jq -e '.[] | select(.type == "assistant" and .message.content) | .message.content[] | select(.type == "tool_use" and .name == "mcp__test-server__test_tool")' "$OUTPUT_FILE" > /dev/null; then
+            echo "✓ MCP test tool was called"
+            
+            # Check the tool result - looking for the user message with tool_result
+            if jq -e '.[] | select(.type == "user" and .message.content[0].type == "tool_result") | .message.content[0].content[0].text | contains("Test tool response")' "$OUTPUT_FILE" > /dev/null; then
+              echo "✓ MCP test tool returned expected result"
+            else
+              echo "✗ MCP test tool result not as expected"
+              echo "Tool results in output:"
+              jq '.[] | select(.type == "user") | .message.content[]? | select(.type == "tool_result")' "$OUTPUT_FILE"
+              exit 1
+            fi
+          else
+            echo "✗ MCP test tool was not called"
+            echo "Tools used:"
+            jq '.[] | select(.type == "assistant" and .message.content) | .message.content[] | select(.type == "tool_use") | .name' "$OUTPUT_FILE"
+            exit 1
+          fi
+
+  # Test the outer action with file-based MCP config
+  test-outer-action-file-mcp:
+    runs-on: ubuntu-latest
+    steps:
+      - name: Checkout repository
+        uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 #v4
+
+      - name: Setup Bun
+        uses: oven-sh/setup-bun@735343b667d3e6f658f44d0eca948eb6282f2b76 #v2
+
+      - name: Install test MCP server dependencies
+        run: |
+          cd base-action/test/mcp-test
+          bun install
+
+      - name: Create MCP config file
+        run: |
+          cat > /tmp/test-mcp-config.json << 'EOF'
+          {
+            "mcpServers": {
+              "test-server": {
+                "type": "stdio",
+                "command": "bun",
+                "args": ["base-action/test/mcp-test/simple-mcp-server.ts"],
+                "env": {}
+              }
+            }
+          }
+          EOF
+
+      - name: Test outer action with file-based MCP config
+        uses: ./
+        id: claude-file-test
+        with:
+          prompt: "Use the mcp__test-server__test_tool to test the MCP integration"
+          anthropic_api_key: ${{ secrets.ANTHROPIC_API_KEY }}
+          github_token: ${{ secrets.GITHUB_TOKEN }}
+          claude_args: |
+            --mcp-config /tmp/test-mcp-config.json
+            --allowedTools mcp__test-server__test_tool
+
+      - name: Check tool usage
+        run: |
+          echo "Checking if MCP test tool was used..."
+          OUTPUT_FILE="${{ steps.claude-file-test.outputs.execution_file }}"
+
+          if [ ! -f "$OUTPUT_FILE" ]; then
+            echo "Error: Output file not found!"
+            exit 1
+          fi
+
+          cat $OUTPUT_FILE
+
+          # Check if the tool was actually called - looking in assistant messages
+          if jq -e '.[] | select(.type == "assistant" and .message.content) | .message.content[] | select(.type == "tool_use" and .name == "mcp__test-server__test_tool")' "$OUTPUT_FILE" > /dev/null; then
+            echo "✓ MCP test tool was called"
+            
+            # Check the tool result - looking for the user message with tool_result
+            if jq -e '.[] | select(.type == "user" and .message.content[0].type == "tool_result") | .message.content[0].content[0].text | contains("Test tool response")' "$OUTPUT_FILE" > /dev/null; then
+              echo "✓ MCP test tool returned expected result"
+            else
+              echo "✗ MCP test tool result not as expected"
+              echo "Tool results in output:"
+              jq '.[] | select(.type == "user") | .message.content[]? | select(.type == "tool_result")' "$OUTPUT_FILE"
+              exit 1
+            fi
+          else
+            echo "✗ MCP test tool was not called"
+            echo "Tools used:"
+            jq '.[] | select(.type == "tool") | .name' "$OUTPUT_FILE"
+            exit 1
+          fi

action.yml

@@ -61,10 +61,6 @@ inputs:
     description: "Additional arguments to pass directly to Claude CLI"
     required: false
     default: ""
-  mcp_config:
-    description: "Additional MCP configuration (JSON string) that merges with built-in GitHub MCP servers"
-    required: false
-    default: ""
   additional_permissions:
     description: "Additional GitHub permissions to request (e.g., 'actions: read')"
     required: false
@@ -146,7 +142,6 @@ runs:
         USE_COMMIT_SIGNING: ${{ inputs.use_commit_signing }}
         ADDITIONAL_PERMISSIONS: ${{ inputs.additional_permissions }}
         CLAUDE_ARGS: ${{ inputs.claude_args }}
-        MCP_CONFIG: ${{ inputs.mcp_config }}
         ALL_INPUTS: ${{ toJson(inputs) }}
 
     - name: Install Base Action Dependencies

base-action/examples/issue-triage.yml

@@ -103,5 +103,6 @@ jobs:
         with:
           prompt_file: /tmp/claude-prompts/triage-prompt.txt
           allowed_tools: "Bash(gh label list),mcp__github__get_issue,mcp__github__get_issue_comments,mcp__github__update_issue,mcp__github__search_issues,mcp__github__list_issues"
-          mcp_config: /tmp/mcp-config/mcp-servers.json
+          claude_args: |
+            --mcp-config /tmp/mcp-config/mcp-servers.json
           anthropic_api_key: ${{ secrets.ANTHROPIC_API_KEY }}

docs/configuration.md

@@ -2,39 +2,28 @@
 
 ## Using Custom MCP Configuration
 
-The `mcp_config` input allows you to add custom MCP (Model Context Protocol) servers to extend Claude's capabilities. These servers merge with the built-in GitHub MCP servers.
+You can add custom MCP (Model Context Protocol) servers to extend Claude's capabilities using the `--mcp-config` flag in `claude_args`. These servers merge with the built-in GitHub MCP servers.
 
 ### Basic Example: Adding a Sequential Thinking Server
 
 ```yaml
-- uses: anthropics/claude-code-action@beta
+- uses: anthropics/claude-code-action@v1
   with:
     anthropic_api_key: ${{ secrets.ANTHROPIC_API_KEY }}
-    mcp_config: |
+    claude_args: |
-      {
+      --mcp-config '{"mcpServers": {"sequential-thinking": {"command": "npx", "args": ["-y", "@modelcontextprotocol/server-sequential-thinking"]}}}'
-        "mcpServers": {
+      --allowedTools mcp__sequential-thinking__sequentialthinking
-          "sequential-thinking": {
-            "command": "npx",
-            "args": [
-              "-y",
-              "@modelcontextprotocol/server-sequential-thinking"
-            ]
-          }
-        }
-      }
-    allowed_tools: "mcp__sequential-thinking__sequentialthinking" # Important: Each MCP tool from your server must be listed here, comma-separated
     # ... other inputs
 ```
 
 ### Passing Secrets to MCP Servers
 
-For MCP servers that require sensitive information like API keys or tokens, use GitHub Secrets in the environment variables:
+For MCP servers that require sensitive information like API keys or tokens, you can create a configuration file with GitHub Secrets:
 
 ```yaml
-- uses: anthropics/claude-code-action@beta
+- name: Create MCP Config
-  with:
+  run: |
-    anthropic_api_key: ${{ secrets.ANTHROPIC_API_KEY }}
+    cat > /tmp/mcp-config.json << 'EOF'
-    mcp_config: |
     {
       "mcpServers": {
         "custom-api-server": {
@@ -47,6 +36,13 @@ For MCP servers that require sensitive information like API keys or tokens, use
         }
       }
     }
+    EOF
+
+- uses: anthropics/claude-code-action@v1
+  with:
+    anthropic_api_key: ${{ secrets.ANTHROPIC_API_KEY }}
+    claude_args: |
+      --mcp-config /tmp/mcp-config.json
     # ... other inputs
 ```
 
@@ -55,10 +51,9 @@ For MCP servers that require sensitive information like API keys or tokens, use
 For Python-based MCP servers managed with `uv`, you need to specify the directory containing your server:
 
 ```yaml
-- uses: anthropics/claude-code-action@beta
+- name: Create MCP Config for Python Server
-  with:
+  run: |
-    anthropic_api_key: ${{ secrets.ANTHROPIC_API_KEY }}
+    cat > /tmp/mcp-config.json << 'EOF'
-    mcp_config: |
     {
       "mcpServers": {
         "my-python-server": {
@@ -73,7 +68,14 @@ For Python-based MCP servers managed with `uv`, you need to specify the director
         }
       }
     }
-    allowed_tools: "my-python-server__<tool_name>" # Replace <tool_name> with your server's tool names
+    EOF
+
+- uses: anthropics/claude-code-action@v1
+  with:
+    anthropic_api_key: ${{ secrets.ANTHROPIC_API_KEY }}
+    claude_args: |
+      --mcp-config /tmp/mcp-config.json
+      --allowedTools my-python-server__<tool_name>  # Replace <tool_name> with your server's tool names
     # ... other inputs
 ```
 
@@ -84,10 +86,26 @@ For example, if your Python MCP server is at `mcp_servers/weather.py`, you would
   ["--directory", "${{ github.workspace }}/mcp_servers/", "run", "weather.py"]
 ```
 
+### Multiple MCP Servers
+
+You can add multiple MCP servers by using multiple `--mcp-config` flags:
+
+```yaml
+- uses: anthropics/claude-code-action@v1
+  with:
+    anthropic_api_key: ${{ secrets.ANTHROPIC_API_KEY }}
+    claude_args: |
+      --mcp-config /tmp/config1.json
+      --mcp-config /tmp/config2.json
+      --mcp-config '{"mcpServers": {"inline-server": {"command": "npx", "args": ["@example/server"]}}}'
+    # ... other inputs
+```
+
 **Important**:
 
 - Always use GitHub Secrets (`${{ secrets.SECRET_NAME }}`) for sensitive values like API keys, tokens, or passwords. Never hardcode secrets directly in the workflow file.
 - Your custom servers will override any built-in servers with the same name.
+- The `claude_args` supports multiple `--mcp-config` flags that will be merged together.
 
 ## Additional Permissions for CI/CD Integration
 
@@ -322,5 +340,6 @@ Many individual input parameters have been consolidated into `claude_args` or `s
 | `model`               | Use `claude_args: "--model claude-4-0-sonnet-20250805"`  |
 | `claude_env`          | Use `settings` with `"env"` object                       |
 | `custom_instructions` | Use `claude_args: "--system-prompt 'Your instructions'"` |
+| `mcp_config`          | Use `claude_args: "--mcp-config '{...}'"`                |
 | `direct_prompt`       | Use `prompt` input instead                               |
 | `override_prompt`     | Use `prompt` with GitHub context variables               |

docs/migration-guide.md

@@ -25,6 +25,7 @@ The following inputs have been deprecated and replaced:
 | `allowed_tools`       | `claude_args: --allowedTools`    | Use CLI format                                |
 | `disallowed_tools`    | `claude_args: --disallowedTools` | Use CLI format                                |
 | `claude_env`          | `settings` with env object       | Use settings JSON                             |
+| `mcp_config`          | `claude_args: --mcp-config`      | Pass MCP config via CLI arguments             |
 
 ## Migration Examples
 
@@ -156,17 +157,19 @@ claude_args: |
   --allowedTools Edit,Read,Write,Bash
   --disallowedTools WebSearch
   --system-prompt "You are a senior engineer focused on code quality"
+  --mcp-config '{"mcpServers": {"custom": {"command": "npx", "args": ["-y", "@example/server"]}}}'
 ```
 
 ### Common claude_args Options
 
 | Option              | Description              | Example                                |
-| ------------------- | ------------------------ | ------------------------------------- |
+| ------------------- | ------------------------ | -------------------------------------- |
 | `--max-turns`       | Limit conversation turns | `--max-turns 10`                       |
 | `--model`           | Specify Claude model     | `--model claude-4-0-sonnet-20250805`   |
 | `--allowedTools`    | Enable specific tools    | `--allowedTools Edit,Read,Write`       |
 | `--disallowedTools` | Disable specific tools   | `--disallowedTools WebSearch`          |
 | `--system-prompt`   | Add system instructions  | `--system-prompt "Focus on security"`  |
+| `--mcp-config`      | Add MCP server config    | `--mcp-config '{"mcpServers": {...}}'` |
 
 ## Provider-Specific Updates
 
@@ -190,6 +193,44 @@ claude_args: |
       --model claude-4-0-sonnet@20250805
 ```
 
+## MCP Configuration Migration
+
+### Adding Custom MCP Servers
+
+**Before (v0.x):**
+
+```yaml
+- uses: anthropics/claude-code-action@beta
+  with:
+    mcp_config: |
+      {
+        "mcpServers": {
+          "custom-server": {
+            "command": "npx",
+            "args": ["-y", "@example/server"]
+          }
+        }
+      }
+```
+
+**After (v1.0):**
+
+```yaml
+- uses: anthropics/claude-code-action@v1
+  with:
+    claude_args: |
+      --mcp-config '{"mcpServers": {"custom-server": {"command": "npx", "args": ["-y", "@example/server"]}}}'
+```
+
+You can also pass MCP configuration from a file:
+
+```yaml
+- uses: anthropics/claude-code-action@v1
+  with:
+    claude_args: |
+      --mcp-config /path/to/mcp-config.json
+```
+
 ## Step-by-Step Migration Checklist
 
 - [ ] Update action version from `@beta` to `@v1`
@@ -202,6 +243,7 @@ claude_args: |
 - [ ] Convert `allowed_tools` to `claude_args` with `--allowedTools`
 - [ ] Convert `disallowed_tools` to `claude_args` with `--disallowedTools`
 - [ ] Move `claude_env` to `settings` JSON format
+- [ ] Move `mcp_config` to `claude_args` with `--mcp-config`
 - [ ] Test workflow in a non-production environment
 
 ## Getting Help

src/entrypoints/collect-inputs.ts

@@ -17,7 +17,6 @@ export function collectActionInputsPresence(): void {
     custom_instructions: "",
     direct_prompt: "",
     override_prompt: "",
-    mcp_config: "",
     additional_permissions: "",
     claude_env: "",
     settings: "",

src/modes/agent/index.ts

@@ -119,13 +119,6 @@ export const agentMode: Mode = {
       claudeArgs = `--mcp-config '${escapedOurConfig}'`;
     }
 
-    // Add user's MCP_CONFIG env var as separate --mcp-config
-    const userMcpConfig = process.env.MCP_CONFIG;
-    if (userMcpConfig?.trim()) {
-      const escapedUserConfig = userMcpConfig.replace(/'/g, "'\\''");
-      claudeArgs = `${claudeArgs} --mcp-config '${escapedUserConfig}'`.trim();
-    }
-
     // Append user's claude_args (which may have more --mcp-config flags)
     claudeArgs = `${claudeArgs} ${userClaudeArgs}`.trim();
 

src/modes/tag/index.ts

@@ -155,13 +155,6 @@ export const tagMode: Mode = {
     const escapedOurConfig = ourMcpConfig.replace(/'/g, "'\\''");
     claudeArgs = `--mcp-config '${escapedOurConfig}'`;
 
-    // Add user's MCP_CONFIG env var as separate --mcp-config
-    const userMcpConfig = process.env.MCP_CONFIG;
-    if (userMcpConfig?.trim()) {
-      const escapedUserConfig = userMcpConfig.replace(/'/g, "'\\''");
-      claudeArgs = `${claudeArgs} --mcp-config '${escapedUserConfig}'`;
-    }
-
     // Add required tools for tag mode
     claudeArgs += ` --allowedTools "${tagModeTools.join(",")}"`;