harness-code-security-mcp

Documentation

Documentation link · transport stdio

Tools

• sl_whoami — Verify Qwiet auth / identity of the configured access token.
• sl_ensure_cli — Install or update the Qwiet CLI (sl) under ~/.shiftleft.
• sl_analyze — Run `sl analyze --wait` in the workspace; returns JSON with scan_id.
• sl_list_applications — List applications in the org.
• sl_list_branch_scans — List scans for an application branch; latest.id is the scan id.
• sl_list_findings — List findings for a scan (counts, top_actionable).
• sl_get_findings — Fetch several findings by id (max 10).
• sl_get_finding — Fetch a single finding by id.
• sl_get_finding_dataflow — Fetch the source -> steps -> sink data flow for one finding.
• sl_get_finding_dataflows — Fetch data flows for several findings (max 5).
• sl_lookup_package_cves — Intelligent SCA — look up CVEs for a list of package PURLs.
• sl_request_finding_fix — Request a Qwiet AutoFix for a finding (async write).
• sl_get_recommended_fix — Fetch the recommended AutoFix for one finding.
• sl_get_recommended_fixes — Poll recommended AutoFixes for up to 5 findings; returns edits[] when ready.
• sl_list_branch_autofixes — List branch-level AutoFixes for an application branch.

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.