Skip to main content

Documentation Index

Fetch the complete documentation index at: https://docs.langsight.dev/llms.txt

Use this file to discover all available pages before exploring further.

Usage

langsight init [OPTIONS]

Options

OptionDefaultDescription
--output, -o.langsight.yamlOutput path for config file
--slack-webhookSlack webhook URL for alerts
--yes, -yfalseSkip confirmation prompts
--skip-checkfalseWrite config without running the first health check

What it does

langsight init scans every well-known MCP config file location on your machine, merges all discovered servers into a single .langsight.yaml, and immediately runs a first health check so you see results before you exit. Auto-discovery sources — global user configs:
ClientConfig path (macOS)Config path (Linux)Key used
Claude Desktop~/Library/Application Support/Claude/claude_desktop_config.json~/.config/claude/claude_desktop_config.jsonmcpServers
Cursor~/.cursor/mcp.json~/.cursor/mcp.jsonmcpServers
VS Code~/.vscode/mcp.json~/.vscode/mcp.jsonservers
Windsurf~/.windsurf/mcp.json~/.windsurf/mcp.jsonmcpServers
Claude Code~/.claude/mcp.json~/.claude/mcp.jsonmcpServers
Gemini CLI~/.gemini/mcp.json~/.gemini/mcp.jsonmcpServers
Kiro~/.kiro/mcp.json~/.kiro/mcp.jsonmcpServers
Zed~/.config/zed/settings.json~/.config/zed/settings.jsoncontext_servers
Cline~/.cline/mcp.json~/.cline/mcp.jsonmcpServers
Project-local configs (current directory):
FileUsed by
.cursor/mcp.jsonCursor workspace
.mcp.jsonGeneric / team-shared config
.vscode/mcp.jsonVS Code workspace
Project-local configs take precedence over global ones when the same server name appears in both.

Example

$ langsight init

LangSight Init scanning for MCP servers...

  Claude Desktop  (~/Library/Application Support/Claude/claude_desktop_config.json)  4 servers
  Cursor          (~/.cursor/mcp.json)                                                2 servers
  VS Code         (~/.vscode/mcp.json)                                                1 server

Discovered 7 MCP servers:
  1. snowflake-mcp    (stdio)
  2. github-mcp       (stdio)
  3. slack-mcp        (sse)
  4. jira-mcp         (stdio)
  5. postgres-mcp     (stdio)
  6. filesystem-mcp   (stdio)
  7. search-mcp       (stdio)

Include all 7 servers? [Y/n]: Y

Slack webhook URL for alerts (leave blank to skip):

Running first health check...

  snowflake-mcp UP       89ms
  github-mcp UP       54ms
  slack-mcp UP      142ms
  jira-mcp DOWN       timeout after 5s
  postgres-mcp UP       31ms
  filesystem-mcp UP       12ms
  search-mcp UP       67ms

6/7 servers healthy
  jira-mcp is DOWN check the process is running

Config written to .langsight.yaml
  7 MCP servers configured

Next steps:
  langsight mcp-health      Full health table with latency and schema status
  langsight scorecard       A-F grade per server
  langsight security-scan   OWASP + CVE audit
  langsight monitor         Start continuous monitoring

Generated config

servers:
  - name: snowflake-mcp
    transport: stdio
    command: python
    args: [/path/to/snowflake_mcp/server.py]

  - name: slack-mcp
    transport: sse
    url: http://localhost:8080/sse

alerts:
  slack_webhook: https://hooks.slack.com/services/...

Non-interactive mode

langsight init --yes --slack-webhook https://hooks.slack.com/... --output /etc/langsight.yaml

Skip the first health check

Useful in CI pipelines or during infrastructure setup where the servers are not yet running:
langsight init --skip-check

See also