
Compact structural IR of JS/TS/Python files for AI agents: risk and signals instead of raw source.
Public tool metadata for what this MCP can expose to an agent.
analyze_codecompact IR of the given sourcecompact IR of the given source
No parameter schema in public metadata yet.
analyze_filecompact IR of one file inside the allowed folderscompact IR of one file inside the allowed folders
No parameter schema in public metadata yet.
analyze_directoryone short entry per file (path, risk, status, language, lines, operations, up to 3 risk signals; "full": all facts), sorted from highest to lowest risk, plus riskCounts, statusCounts and incomplete (paths whose analysis did not finish; check them separately, their low risk is...one short entry per file (path, risk, status, language, lines, operations, up to 3 risk signals; "full": all facts), sorted from highest to lowest risk, plus riskCounts, statusCounts and incomplete (paths whose analysis did not finish; check them separately, their low risk is...
No parameter schema in public metadata yet.
Sponsors
MCP server for sentinel-ir:
it lets AI agents in Claude Desktop, Cursor, Windsurf or any other
Model Context Protocol client read a
compact structural IR of JavaScript, TypeScript, Python and Rust files instead of the raw source.
sentinel-irThe IR tells the agent what a file does (risk level, dangerous
capabilities such as eval or child_process, routes, exports, imports,
environment reads, network / filesystem / process / crypto calls) in a few
hundred characters. The agent can triage a folder first and then read the raw
source only of the files that matter.
sentinel-ir-mcp