Skip to main content
Model Context Protocol (MCP) lets you extend Siclaw with external tools and data sources. During investigation, the agent discovers and uses MCP tools automatically — querying Prometheus metrics, searching GitHub issues, reading files, or calling any custom API.

​
Supported Transports

TransportUse CaseConfig
stdioLocal processes (npx packages, Python scripts)command + args
SSERemote servers (Server-Sent Events)url
streamable-httpRemote servers (bidirectional HTTP)url

​
Configuration

In Gateway mode, go to Settings > MCP Servers:
  1. Click New Server
  2. Select transport type
  3. Enter a unique name and optional description
  4. Fill in transport-specific fields (command/args or URL)
  5. Add environment variables or HTTP headers as needed
  6. Save
Changes take effect immediately — all active sessions reload automatically.
Creating and managing MCP servers requires admin role. All users can use the tools they provide.

​
Via settings.json (CLI mode)

For TUI / single-user mode, add MCP servers to ~/.siclaw/config/settings.json: 
{
  "mcpServers": {
    "prometheus": {
      "transport": "stdio",
      "command": "npx",
      "args": ["-y", "@prom-mcp/server"],
      "env": {
        "PROMETHEUS_URL": "http://prometheus:9090"
      }
    }
  }
}

​
Environment Variable Substitution

Use ${VAR_NAME} in env values — Siclaw resolves them from the process environment at spawn time: 
{
  "mcpServers": {
    "github": {
      "transport": "streamable-http",
      "url": "http://localhost:8000/mcp",
      "headers": {
        "Authorization": "Bearer ${GITHUB_TOKEN}"
      }
    }
  }
}

​
Examples

​
Prometheus Metrics

{
  "prometheus": {
    "transport": "stdio",
    "command": "npx",
    "args": ["-y", "@prom-mcp/server"],
    "env": {
      "PROMETHEUS_URL": "http://prometheus.monitoring:9090"
    }
  }
}
The agent can then query metrics during investigation: 
Phase 1: Context Gathering
  [mcp:prometheus] rate(http_request_duration_seconds_sum{service="payment"}[5m])
  [kubectl] get pods -n payments

​
Filesystem Access

{
  "filesystem": {
    "transport": "stdio",
    "command": "npx",
    "args": ["-y", "@modelcontextprotocol/server-filesystem", "/workspace"]
  }
}

​
GitHub

{
  "github": {
    "transport": "stdio",
    "command": "npx",
    "args": ["-y", "@github/mcp-server"],
    "env": {
      "GITHUB_TOKEN": "${GITHUB_TOKEN}"
    }
  }
}

​
Custom HTTP Service

Any service implementing the MCP protocol can be connected: 
{
  "my-service": {
    "transport": "streamable-http",
    "url": "https://mcp.internal.example.com/v1",
    "headers": {
      "Authorization": "Bearer ${MY_SERVICE_TOKEN}"
    }
  }
}

​
How It Works

​
Tool Discovery

When a session starts, Siclaw connects to all enabled MCP servers and discovers their tools. MCP tools appear alongside built-in tools with a mcp__ prefix: 
mcp__prometheus__query        ← from Prometheus MCP server
mcp__github__search_issues    ← from GitHub MCP server
mcp__filesystem__read_file    ← from Filesystem MCP server
The agent decides which tools to use based on the investigation context — no manual tool selection needed.

​
Config Sync (Gateway Mode)

In multi-user deployments, MCP configuration syncs automatically: 
Admin creates/edits MCP server in Web UI
  → Saved to database
  → Gateway notifies all active AgentBoxes
  → Each AgentBox fetches merged config
  → Active sessions reload with new tools
The merge strategy: DB entries (managed via Web UI) override local seed entries with the same name. Disabling a DB entry removes it from the merged config.

​
Kubernetes Considerations

In Kubernetes mode, MCP server binaries must be available in the AgentBox container image. For stdio transport servers that use npx, ensure the package can be installed inside the pod (network access required) or pre-install it in the image.
For HTTP-based transports (sse, streamable-http), the MCP server runs externally — the AgentBox pod only needs network access to the URL.