MCP server · Lightrun

com.lightrun/mcp-server

Connect AI assistants to live runtime context for production debugging.

Open endpoint → Lightrun provider profile

One-click install for Cursor, VS Code, Claude, and 20+ other MCP clients, powered by API Commons MCP Install — visit install.apicommons.org for more information.

Provider: Lightrun Type: Hosted endpoint Transport: streamable-http Host: app.lightrun.com

Endpoint

https://app.lightrun.com/mcp

Hosted endpoint · transport streamable-http

Connect

This is a remote MCP server — point an MCP client at the endpoint URL. Clients with native remote support (Claude, Cursor, VS Code, …):

# mcp client config (e.g. .mcp.json / mcp settings) { "mcpServers": { "lightrun": { "url": "https://app.lightrun.com/mcp" } } }

For stdio-only clients (older Claude Desktop, etc.), bridge with mcp-remote:

# Add to claude_desktop_config.json { "mcpServers": { "lightrun": { "command": "npx", "args": ["-y", "mcp-remote", "https://app.lightrun.com/mcp"] } } }

If the server requires authentication, add the provider's token/header (e.g. an X-API-Key) per its docs. A quick reachability check:

curl -i -X POST https://app.lightrun.com/mcp \ -H "Content-Type: application/json" -H "Accept: application/json, text/event-stream" \ -d '{"jsonrpc":"2.0","id":1,"method":"tools/list"}'

Tools

get_runtime_sources — Discover available applications, services and runtime environments available for debugging.
get_runtime_expression_values — Inspect variable values and expressions at a code location (synchronous; v1.75-1.84).
get_runtime_callstack — Capture call stacks at a specific code location (synchronous; v1.75-1.84).
snapshot_create — Initialize an asynchronous runtime snapshot action (v1.85+).
snapshot_status — Poll the status of a snapshot action.
snapshot_cancel — Terminate a running snapshot action.
snapshot_get_values — Retrieve captured expression values from a snapshot.
snapshot_get_call_stack — Retrieve captured call stacks from a snapshot.
get_runtime_execution_duration — Measure how long a code section takes to execute (synchronous; v1.78-1.86).
get_runtime_execution_duration_samples — Retrieve detailed execution-duration measurement samples.
get_runtime_execution_count — Count how many times a code path executes (synchronous; v1.80-1.88).
execution_count_create — Initialize an asynchronous execution-count action (v1.89+).
execution_count_status — Poll the status of an execution-count action.
execution_count_samples — Retrieve execution-count samples.
execution_count_cancel — Stop execution-count collection.
get_runtime_numeric_metric — Capture integer expression values as a metric (synchronous; v1.79-1.88).
get_runtime_numeric_metric_samples — Retrieve numeric-metric sample details.
custom_metric_create — Initialize an asynchronous custom-metric action (v1.89+).
custom_metric_status — Poll the status of a custom-metric action.
custom_metric_samples — Retrieve custom-metric samples.
custom_metric_cancel — Stop custom-metric collection.
get_actions — List the Lightrun actions currently in place, for AI assistants (added v1.88, 30 June 2026).

About MCP

The Model Context Protocol (MCP) is an open protocol Anthropic introduced for connecting LLM-based agents to external tools and data sources. Providers publish MCP servers that expose their API surface as structured, discoverable tools — an MCP-compatible client (Claude Desktop, Cursor, Cline, Continue, etc.) can connect to the server and call its tools without any per-provider integration code.

Browse every MCP server on the APIs.io network or compare with the broader Agent Skill surfaces of the same providers.