Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@Respan MCP Server list recent error logs"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Model Context Protocol (MCP) server for Respan - access logs, prompts, traces, and customer data directly from your AI assistant.
Logs - Query, filter, and create LLM request logs
Traces - View complete execution traces with span trees
Customers - Access customer data and budget information
Prompts - Manage prompt templates and versions
Related MCP server: MCP Datadog Server
No installation required.
Get your API key from platform.respan.ai
Add to your MCP config file:
Cursor (~/.cursor/mcp.json):
{
"mcpServers": {
"respan": {
"url": "https://mcp.respan.ai/api/mcp",
"headers": {
"Authorization": "Bearer YOUR_RESPAN_API_KEY"
}
}
}
}Claude Desktop (macOS: ~/Library/Application Support/Claude/claude_desktop_config.json):
{
"mcpServers": {
"respan": {
"url": "https://mcp.respan.ai/api/mcp",
"headers": {
"Authorization": "Bearer YOUR_RESPAN_API_KEY"
}
}
}
}Restart Cursor/Claude Desktop
Run the MCP server locally for personal development or offline use.
Prerequisites: Node.js v18+
git clone https://github.com/Keywords-AI/keywordsai-mcp.git
cd keywordsai-mcp
npm install
npm run build{
"mcpServers": {
"respan": {
"command": "node",
"args": ["/absolute/path/to/respan-mcp/dist/lib/index.js"],
"env": {
"RESPAN_API_KEY": "YOUR_RESPAN_API_KEY"
}
}
}
}Deploy your own instance to Vercel for teams sharing a single deployment.
Set RESPAN_API_KEY in Vercel Dashboard > Settings > Environment Variables.
Share this config with your team:
{
"mcpServers": {
"respan": {
"url": "https://your-project.vercel.app/mcp"
}
}
}Tool | Description |
| List and filter LLM request logs with powerful query capabilities |
| Retrieve complete details of a single log by unique ID |
| Create a new log entry for any type of LLM request |
Tool | Description |
| List and filter traces with sorting and pagination |
| Retrieve complete hierarchical span tree of a trace |
Tool | Description |
| List customers with pagination and sorting |
| Get customer details including budget usage |
Tool | Description |
| List all prompts in your organization |
| Get detailed prompt information |
| List all versions of a prompt |
| Get specific version details |
Tools that support filtering accept a filters object:
{
"cost": {"operator": "gt", "value": [0.01]},
"model": {"operator": "", "value": ["gpt-4"]},
"customer_identifier": {"operator": "contains", "value": ["user"]},
"metadata__session_id": {"operator": "", "value": ["abc123"]}
}Operators: "" (equal), not, lt, lte, gt, gte, contains, icontains, startswith, endswith, in, isnull
respan-mcp/
├── api/
│ └── mcp.ts # HTTP entry point (Vercel serverless function)
├── lib/
│ ├── index.ts # Stdio entry point (local mode)
│ ├── shared/
│ │ └── client.ts # API client, auth config, path validation
│ ├── observe/
│ │ ├── logs.ts # list_logs, get_log_detail, create_log
│ │ ├── traces.ts # list_traces, get_trace_tree
│ │ └── users.ts # list_customers, get_customer_detail
│ └── develop/
│ └── prompts.ts # list_prompts, get_prompt_detail, versions
├── vercel.json # Vercel config (rewrites, function timeout)
├── tsconfig.json # TypeScript config
└── package.jsonTwo entry points: api/mcp.ts (HTTP via Vercel) and lib/index.ts (stdio for local use)
Shared core: Both entry points create an AuthConfig and pass it to the same tool registration functions via closures - no global mutable state
Tool modules: Organized by domain (observe/ for runtime data, develop/ for prompt management)
API client: lib/shared/client.ts handles all upstream API calls with 30s timeout, path validation, and auth
For custom API endpoints, set the RESPAN_API_BASE_URL environment variable:
Stdio mode:
{
"mcpServers": {
"respan": {
"command": "node",
"args": ["/path/to/respan-mcp/dist/lib/index.js"],
"env": {
"RESPAN_API_KEY": "YOUR_API_KEY",
"RESPAN_API_BASE_URL": "https://your-endpoint.example.com/api"
}
}
}
}Private deployment: Set RESPAN_API_BASE_URL in Vercel environment variables.
npm run build # Compile TypeScript
npm run watch # Watch mode
npm run stdio # Build and run in stdio modeFull documentation at docs.respan.ai/documentation/resources/mcp
MIT
This server cannot be installed
Unclaimed servers have limited discoverability.
If you are the server author, to access and configure the admin panel.
Read-only access to Auralogs production logs: search logs, inspect errors, review AI analyses.
AI agent run monitoring with incident replay and SLA receipts.
Enterprise AI Control Plane: governance, guardrails, spend tracking, compliance & smart routing.
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/respanai/respan-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server