Enhancements với MCP servers — Extending Claude Code

Add MCP server

CLI command:

Example:

claude mcp add [server-name] [command-to-start-server]

Add MCP server (tiếp)

Claude Code on startup connect to registered servers. Tools available trong sessions.

claude mcp add sentry npx @sentry/mcp-server
claude mcp add docs uv run /path/to/docs_server.py
claude mcp add github docker run -i github-mcp-server

Custom MCP server example

Build server expose "convert doc → markdown":

Register:

# docs_mcp_server.py
from mcp.server.fastmcp import FastMCP
from pydantic import Field

mcp = FastMCP("DocsMCP")


@mcp.tool(
    name="document_path_to_markdown",
    description="Convert PDF, Word, or other doc to markdown format."
)
def convert_document(
    path: str = Field(description="Absolute path to document file")
) -> str:
    # Use python libs to convert
    import pypandoc
    return pypandoc.convert_file(path, "md")


if __name__ == "__main__":
    mcp.run(transport="stdio")

Custom MCP server example (tiếp)

Now in Claude Code:

claude mcp add docs uv run docs_mcp_server.py

Custom MCP server example (tiếp)

Claude uses your custom tool → returns markdown. Chain with Write to save.

> Convert /path/to/report.docx to markdown

Popular MCP integrations

Install từ respective repos. Each extends Claude Code.

Dev workflow example

Bug fix workflow

Claude Code orchestrate across multiple systems.

1. Claude Code in repo
2. MCP: sentry-mcp connected
3. MCP: jira-mcp connected

> Fix the top error in Sentry this week

Claude:
a. Uses sentry-mcp list_errors → top issue
b. Reads related code files (built-in)
c. Analyzes, proposes fix
d. Edits code (built-in)
e. Runs tests (built-in Bash)
f. Uses jira-mcp update_ticket → mark resolved
g. Git commit, open PR

Workflow: Team standup

claude mcp add github ...
claude mcp add slack ...
claude mcp add gcal ...

Workflow: Team standup (tiếp)

Automate mundane async work.

> Generate my standup for today

Claude:
a. github-mcp → my PRs since yesterday
b. gcal-mcp → today's meetings
c. slack-mcp → blockers mentioned in #me channel
d. Generate markdown summary
e. slack-mcp post_message → send to #standup

Custom team server

Your org có internal tools? Wrap in MCP:

Entire team use Claude Code với company tools.

# company_tools_mcp.py

@mcp.tool()
def lookup_customer(customer_id: str):
    """Query internal CRM."""
    return db.query(customer_id)


@mcp.tool()
def ship_to_staging(service_name: str):
    """Trigger internal deployment."""
    return ci.trigger_deploy(service_name, env="staging")


@mcp.tool()
def open_incident(severity: str, description: str):
    """Open PagerDuty incident."""
    return pagerduty.create(severity=severity, desc=description)

Popular sources

Check regularly — ecosystem growing fast.

• github.com/modelcontextprotocol/servers — official curated
• mcp.pulse.com — community registry
• Anthropic docs — integration guides

Security considerations

MCP servers = arbitrary code execution access.

Best practices

Production security: dedicated channel vs casual use.

• Only trusted servers — vet official/OSS before install
• Sandbox sensitive — don't give prod access
• Review server code — especially custom
• Permission scoping — read-only vs write
• Audit logs — track what agent does

When NOT to add MCP server

⚠️ Overkill for

✅ Worth building

• 1 simple task (inline tool suffices)
• Prototype / 1-time use
• No team benefit
• Team-wide tool
• Reusable across projects
• Expose to external (as product)

Claude Desktop MCP config

Thay vì CLI, Claude Desktop có config file:

Restart Claude Desktop → servers connected. Use qua chat.

// ~/Library/Application Support/Claude/claude_desktop_config.json
{
  "mcpServers": {
    "docs": {
      "command": "uv",
      "args": ["run", "/path/to/docs_mcp.py"]
    },
    "sentry": {
      "command": "npx",
      "args": ["@sentry/mcp-server"]
    }
  }
}

Example: Custom analytics MCP

On-call engineer uses Claude Desktop + this MCP:

@mcp.tool()
def get_metric(metric_name: str, time_range: str = "7d"):
    """Query Prometheus/DataDog metric."""
    return metrics_client.query(metric_name, time_range)


@mcp.tool()
def list_alerts(severity: str = "critical"):
    """List active alerts."""
    return alerts_api.list(severity=severity)


@mcp.tool()
def silence_alert(alert_id: str, duration_hours: int):
    """Silence alert temporarily."""
    return alerts_api.silence(alert_id, duration_hours)

Example: Custom analytics MCP (tiếp)

AI on-call buddy.

> What alerts active? Silence the db pool one for 1 hour while I fix.

Team adoption pattern

Phase 1 (Week 1)

Phase 2 (Week 3)

Phase 3 (Month 2)

Phase 4 (Month 6)

Gradual, measure ROI each phase.

• 1 dev tries Claude Code + few MCP servers
• Learn workflows
• Team tries selected MCP servers (GitHub, Slack)
• Build 1-2 custom team tools
• Team-wide adoption
• Custom MCP servers for team-specific tasks
• Shared config file trong repo
• Process automation: standups, retros, code reviews
• Org-level MCP for company systems

Anti-patterns

❌ Install every MCP server

20 servers → tool bloat, slow Claude.

Fix: Only install used servers.

❌ Custom MCP without docs

Team uses but can't fix or extend.

Fix: README, schema docs, tests.

❌ No version control for config

Dev's Claude Desktop config local → team inconsistent.

Fix: Commit to repo. Sync across team.

❌ Forget security

MCP server có DB write access exposed.

Fix: Principle of least privilege. Read-only default.

Áp dụng ngay

Bài tập 1: Install 1 MCP server (30 phút)

Visit modelcontextprotocol.io. Install filesystem or github MCP. Use via Claude Code.

Bài tập 2: Design team MCP (20 phút)

Cho your team, identify 3 tools worth building as MCP server. Sketch tool schemas.

Tóm tắt

🎯 MCP extends Claude Code — add domain-specific tools.

🎯 claude mcp add register servers.

🎯 Rich ecosystem: GitHub, Slack, Sentry, Jira, Postgres, ...

🎯 Custom MCP cho team tools — reusable, shareable.

🎯 Security + governance cho production use.