Skip to main content
Connect your AI coding tools to LogClaw incidents, logs, and anomalies via the Model Context Protocol. Works with Claude Code, Cursor, Windsurf, Claude.ai, and any MCP-compatible client.

Remote (Cloud)

Connect via URL — no installation needed

Local (npm)

Install locally via npx logclaw-mcp-server

​
Remote (Cloud)

Connect directly via URL — no installation required. LogClaw’s remote MCP server uses OAuth 2.1 and Streamable HTTP transport. 
https://mcp.logclaw.ai
When you connect, you’ll be prompted to enter your LogClaw API key. The key is encrypted and never exposed to the MCP client.

​
Claude Desktop / Claude.ai

Add LogClaw as a remote MCP server:
  1. Open Settings → MCP Servers → Add Server
  2. Enter the URL: https://mcp.logclaw.ai
  3. Complete the OAuth flow by entering your API key

​
Any MCP Client (URL-based)

For any MCP client that supports remote servers, use:
SettingValue
Server URLhttps://mcp.logclaw.ai
TransportStreamable HTTP
AuthOAuth 2.1 (automatic)

​
Local (npm)

Install and run the MCP server locally via stdio transport: 
npx logclaw-mcp-server
The server communicates over stdio using the Model Context Protocol. Your AI tool launches it automatically — you just need to add the config once.

​
Setup

{
  "mcpServers": {
    "logclaw": {
      "command": "npx",
      "args": ["-y", "logclaw-mcp-server"],
      "env": {
        "LOGCLAW_ENDPOINT": "https://ticket.logclaw.ai",
        "LOGCLAW_API_KEY": "lc_proj_..."
      }
    }
  }
}

​
Environment Variables

VariableRequiredDescription
LOGCLAW_API_KEYYesYour LogClaw project API key (starts with lc_proj_)
LOGCLAW_ENDPOINTNoAuth proxy endpoint (default: https://ticket.logclaw.ai)
Get your API key from the LogClaw Console under Settings → API Keys.

​
Available Tools

The MCP server exposes 8 tools that your AI assistant can call:
ToolDescription
logclaw_list_incidentsList and filter incidents by severity, state, service, or search query
logclaw_get_incidentFull incident details — root cause, causal chain, evidence logs, traces, timeline, blast radius
logclaw_update_incidentTransition incident state (acknowledge, investigate, mitigate, resolve) or add a note
logclaw_search_logsSearch raw logs by service, level, time range, and query
logclaw_get_anomaliesGet recent anomaly detections (Z-score analysis on error rates)
logclaw_service_healthCheck LogClaw pipeline health status and latency
logclaw_bulk_updateUpdate multiple incidents at once (acknowledge, investigate, mitigate, or resolve)
logclaw_export_incidentsExport incidents in CSV, markdown table, or JSON format

​
Example Prompts

Once connected, try asking your AI assistant:

Triage incidents

“What incidents are open right now?”

Root cause analysis

“Show me the root cause for TICK-0037”

Search logs

“Search for ERROR logs from auth-service in the last 30 minutes”

Query anomalies

“Are there any critical anomalies?”

Update incidents

“Acknowledge TICK-0042 and add a note that I’m looking into it”

Health check

“Is the LogClaw pipeline healthy?”

Bulk update

“Acknowledge TICK-0037, TICK-0038, and TICK-0039”

Export incidents

“Export all critical incidents as a markdown table”

​
Self-Hosted

Running LogClaw on your own infrastructure? Point LOGCLAW_ENDPOINT to your auth proxy: 
LOGCLAW_ENDPOINT=https://logclaw.internal.company.com \
  LOGCLAW_API_KEY=lc_proj_... \
  npx logclaw-mcp-server
Air-gapped? Install the package from a private registry or copy the dist/ folder directly. The MCP server has zero runtime network dependencies beyond reaching your auth proxy.

​
Source Code

GitHub

View source code and contribute

npm

logclaw-mcp-server on npm