@launchlint/mcp
Click on "Deploy 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., "@@launchlint/mcp scan my project for security issues"
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.
@launchlint/mcp
Secure local MCP connector for LaunchLint. It reads only supported files from the explicitly approved workspace, respects .gitignore and .launchlintignore, never executes project code, and sends a controlled snapshot directly to LaunchLint over HTTPS.
On Windows, the connector combines Node.js' bundled certificates with the trusted Windows certificate store. TLS verification always remains enabled.
Codex
codex mcp add launchlint -- npx -y @launchlint/mcp@0.1.5Related MCP server: ChampCity GPT MCP Launcher
Claude Code
claude mcp add launchlint -- npx -y @launchlint/mcp@0.1.5Cursor or JSON configuration
{
"mcpServers": {
"launchlint": {
"command": "npx",
"args": ["-y", "@launchlint/mcp@0.1.5"],
"env": {
"LAUNCHLINT_WORKSPACE": "/absolute/path/to/app"
}
}
}
}LAUNCHLINT_WORKSPACE is optional when the MCP client provides exactly one filesystem root.
The first tool call opens a browser for OAuth sign-in and consent. prepare_workspace_scan only reports the selected file count, size, exclusions, and a one-time confirmation token. A paid app check is consumed only after an explicit start_workspace_scan confirmation.
The connector excludes local credential files, dependencies, caches, build outputs, binary files, and symlinks. It does not install dependencies, invoke a shell, run package scripts, or send source files through the model context. Unsaved editor changes cannot be checked.
Security
The connector is public so its local file handling and network boundary can be audited. LaunchLint's scanner, authorization, billing, database, and infrastructure remain in the private service. Installing this package does not grant a LaunchLint plan or access to another user's projects.
Please report vulnerabilities privately as described in SECURITY.md.
Available Tools
6 toolsget_fix_taskDRead-onlyIdempotent
Use the authenticated LaunchLint cloud tool get_fix_task.
Inputs: scanId (required), findingId (required), locale.
get_project_statusDRead-onlyIdempotent
Use the authenticated LaunchLint cloud tool get_project_status.
Inputs: projectKey (required).
list_findingsDRead-onlyIdempotent
Use the authenticated LaunchLint cloud tool list_findings.
Inputs: scanId (required), domain, severity.
list_projectsCRead-onlyIdempotent
Use the authenticated LaunchLint cloud tool list_projects.
Inputs: no named parameters.
prepare_workspace_scanPrepare local app checkARead-onlyIdempotent
Inspect the approved workspace without uploading it. Returns counts, exclusions, size, and a one-time confirmation token.
Inputs: platforms.
start_workspace_scanStart local app checkA
Upload the previously prepared workspace snapshot directly to LaunchLint. Requires explicit confirmation and consumes one app check.
Inputs: confirm (required), confirmationToken (required), appName, platforms, +1 more.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 6 tools
Each tool targets a distinct action: project listing/status, scan preparation/execution, finding listing, and fix task retrieval. No overlap or ambiguity.
All tools follow a consistent verb_noun pattern with snake_case (list_projects, get_project_status, etc.), making predictions easy.
Six tools cover the scanning workflow efficiently: 2 for projects, 2 for scan lifecycle, and 2 for results. Not excessive or sparse.
Covers the core scanning workflow well, but lacks project creation/deletion tools. Minor gap, but agents can still execute scans on existing projects.
Maintenance
Related MCP Connectors
Scan any public GitHub MCP-server repo for security issues. 37 MCP-specific L1 rules, 8 languages.
Scan any MCP server for tool-poisoning, security, auth & license. Trust score before install.
Scan AI agent skills, MCP server packages and MCP configs before you install them. Static analysis.
Security scanner for MCP servers. Detect vulnerabilities, prompt injection, and tool poisoning.
Related MCP Servers
- AlicenseNot gradedqualityAmaintenanceA desktop launcher and local MCP workspace server that enables ChatGPT and other MCP clients to securely read, edit, search, run commands, and show changes in selected local project folders.1MIT
- FlicenseBqualityCmaintenanceChatGPT-compatible MCP server and Electron launcher for controlled local project-file access, providing read-only and approval-gated write tools over STDIO or HTTP with optional OAuth and HTTPS tunneling.19-
- AlicenseBqualityDmaintenanceworkbench-mcp is a Python FastMCP server for controlled local workspace inspection, bounded file reads/searches, guarded text patching, allowlisted test execution, read-only Git status, approved artifact collection, and workspace diagnostics.10MIT
- AlicenseNot gradedqualityBmaintenanceA minimal, security-focused MCP server that provides structured read/write access to exactly one local workspace, with built-in local Git checkpoints and rollback.Apache 2.0