MCP Server

The Whawit MCP (Model Context Protocol) server enables AI assistants to access your observability data, search project knowledge, and analyze incidents programmatically.

This page is about WHAWIT as an MCP server for your AI assistants. For the other direction — connecting your organization’s MCP server so WHAWIT can resolve incidents by acting on your internal systems — see MCP Actions.

Overview

MCP is an open protocol that allows AI assistants to interact with external tools and data sources. The Whawit MCP server exposes eight tools that give AI assistants full access to:

Project knowledge base search
DevOps analysis and log querying
Incident details and correlated analyses
AI-optimized prompts for fixing issues

Hosted Server

Whawit provides a hosted MCP server that requires no local installation:

Endpoint
`https://mcp.whawit.ai/sse`

The hosted server is recommended for most users. It stays up-to-date automatically and requires no maintenance.

Quick Setup

Cursor
Claude Desktop
Windsurf

Add to ~/.cursor/mcp.json:

{
  "mcpServers": {
    "WHAWIT": {
      "url": "https://mcp.whawit.ai/sse"
    }
  }
}

Add to ~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or %APPDATA%\Claude\claude_desktop_config.json (Windows):

{
  "mcpServers": {
    "WHAWIT": {
      "url": "https://mcp.whawit.ai/sse"
    }
  }
}

Add to your Windsurf MCP configuration:

{
  "mcpServers": {
    "WHAWIT": {
      "url": "https://mcp.whawit.ai/sse"
    }
  }
}

Signing In

There is nothing to copy into your configuration. The URL is the whole setup. When your client first calls the server, Whawit answers 401 with a WWW-Authenticate challenge pointing at its OAuth metadata. Your client reads that, opens your browser, and you sign in to Whawit the way you normally would. The client stores the resulting token and refreshes it on its own.

You are connected when your client lists the Whawit tools — try asking it to “list my Whawit projects”.

You see the same projects your Whawit account sees. Nothing to scope, and no key to rotate or leak.

Available Tools

The MCP server exposes eight tools for AI assistants:

whawit_context_search

Search the project knowledge base for relevant context about architecture, business logic, and implementation details.

string

required

The search query to find relevant context.

string

required

The project URN to search in (e.g., urn:project:abc123).

array

Types of contexts to search: repo, project, user, other. Defaults to all.

number

default:"3"

Maximum number of results to return. Range: 1-5.

Example prompt:

Search for how authentication works in project urn:project:abc123

whawit_devops_analysis

Analyze logs, metrics, and system health from connected observability providers.

string

required

What to analyze (e.g., “redis errors”, “API failures”, “high latency”).

string

required

The project URN to analyze.

string

default:"1h"

Time range start (e.g., 15m, 1h, 24h).

string

default:"now"

Time range end.

string

default:"concise"

Output verbosity: concise or detailed.

Example prompt:

Check for errors in the last 15 minutes in project urn:project:abc123

whawit_project_info

Get information about a project including its integrations, contexts, and configuration.

string

required

The project URN to get info for.

whawit_list_projects

List all available projects for the authenticated user. This tool takes no parameters.

whawit_get_analysis_full

Get complete analysis data with full JSON payload and formatted markdown.

string

required

The URN of the analysis to fetch (e.g., urn:history:abc123).

string

default:"both"

Output format: markdown, json, or both.

boolean

default:"false"

Include raw log events in output.

number

default:"15000"

Maximum output length in characters.

whawit_get_incident_full

Get full incident details with optional correlated analysis.

string

required

The project URN to fetch incidents from.

string

Specific incident URN to fetch.

string

Filter by severity: critical, high, medium, low. Gets first matching open incident.

boolean

default:"true"

Include the correlated analysis if available.

whawit_generate_fix_prompt

Generate an AI-ready prompt for fixing issues identified in an analysis.

string

required

The URN of the analysis to generate a fix prompt for.

string

default:"all"

Focus area: code, infrastructure, or all.

whawit_codebase_analysis_prompt

Generate a prompt for analyzing a codebase based on project context.

string

required

The project URN to analyze.

string

Optional specific query to focus the analysis on.

boolean

default:"true"

Include architecture/overview contexts.

MCP Resources

The server also exposes projects as MCP resources:

whawit://project/{urn}

Reading a project resource returns:

Project details (name, description, URN)
Connected providers
Available contexts with titles and types

Authentication

The server authenticates you with OAuth 2.1, discovered automatically. You add a URL; your client does the rest. An unauthenticated request is answered with an RFC 9728 challenge:

HTTP/2 401
WWW-Authenticate: Bearer resource_metadata="https://mcp.whawit.ai/.well-known/oauth-protected-resource"

The client follows that to the metadata documents, registers itself, sends you to your browser to sign in, and then calls the server with a Bearer token. Every MCP client that implements the authorization spec — Claude, Cursor, VS Code, Windsurf — does this without being told.

Headless environments

A CI job or a script has no browser to open. For those, the server also accepts an X-API-Key header, which you can generate in the Whawit web app under Settings > User Settings. Prefer OAuth anywhere a person is present: a key is something to store, rotate and eventually leak.

Transport Protocols

The Whawit MCP server supports two transport protocols:

Protocol	Endpoint	Use Case
SSE (Server-Sent Events)	`/sse`	Traditional MCP clients
StreamableHTTP	`/mcp`	Modern clients like Cursor

Both endpoints support the full MCP protocol including tools and resources.

Example Workflows

Whawit MCP tools in action — Using Whawit MCP tools in Cursor to analyze incidents

Investigating an Incident

Ask Claude to list your projects:
“List my Whawit projects”
Get incident details:
“Get the latest critical incident from project urn:project:abc123”
Generate a fix prompt:
“Generate a fix prompt for the incident analysis”
Let Claude implement the fix based on the context

Searching Documentation

“Search the project knowledge base for how the payment processing flow works in urn:project:payments”

Running DevOps Analysis

“Analyze Redis connection errors in the last 30 minutes for urn:project:backend”

Troubleshooting

Tools not appearing in Claude/Cursor

Verify your MCP configuration file syntax is valid JSON
Restart Claude Desktop or Cursor after configuration changes
Check that the access token is valid and not expired
Ensure the MCP server URL is reachable from your network

Authentication errors

Check that your configuration has no headers block — an old X-API-Key entry left in place takes precedence over OAuth and will fail once that key is revoked.
Sign out and reconnect so the client runs the browser flow again; tokens expire.
Confirm the account you signed in with has access to the project you are asking about — try “list my Whawit projects” to see what it can reach.

Project not found errors

Verify the project URN format is correct (urn:project:...)
Ensure you have access to the project in Whawit
Run whawit_list_projects to see available projects

Next Steps

VS Code Extension

Install the Whawit extension for integrated observability in your editor.

GitHub Copilot

Use @whawit in GitHub Copilot Chat for AI-assisted analysis.

Getting started

On-call

MCP Actions

Policies

Concepts

Delivery reliability

Developer Tools

Demos & resources

Company

Overview

Hosted Server

Quick Setup

Signing In

Available Tools

whawit_context_search

whawit_devops_analysis

whawit_project_info

whawit_list_projects

whawit_get_analysis_full

whawit_get_incident_full

whawit_generate_fix_prompt

whawit_codebase_analysis_prompt

MCP Resources

Authentication

Transport Protocols

Example Workflows

Investigating an Incident

Searching Documentation

Running DevOps Analysis

Troubleshooting

Next Steps

VS Code Extension

GitHub Copilot

​Overview

​Hosted Server

​Quick Setup

​Signing In

​Available Tools

​whawit_context_search

​whawit_devops_analysis

​whawit_project_info

​whawit_list_projects

​whawit_get_analysis_full

​whawit_get_incident_full

​whawit_generate_fix_prompt

​whawit_codebase_analysis_prompt

​MCP Resources

​Authentication

​Transport Protocols

​Example Workflows

​Investigating an Incident

​Searching Documentation

​Running DevOps Analysis

​Troubleshooting

​Next Steps

VS Code Extension

GitHub Copilot

Overview

Hosted Server

Quick Setup

Signing In

Available Tools

whawit_context_search

whawit_devops_analysis

whawit_project_info

whawit_list_projects

whawit_get_analysis_full

whawit_get_incident_full

whawit_generate_fix_prompt

whawit_codebase_analysis_prompt

MCP Resources

Authentication

Transport Protocols

Example Workflows

Investigating an Incident

Searching Documentation

Running DevOps Analysis

Troubleshooting

Next Steps