Sentinel-IR
Compact structural IR of JS/TS/Python files for AI agents: risk and signals instead of raw source.
- GitHub stars
- 1
- tools
- 3
- transport
- STDIO
- last updated
- Nov 10, 2026
Tools
3 toolsPublic tool metadata for what this MCP can expose to an agent.
analyze_codecompact IR of the given source
compact IR of the given source
No parameter schema in public metadata yet.
analyze_filecompact IR of one file inside the allowed folders
compact 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
Agent CaffeineSponsoredClose your lid, come back to finished work
SnugSponsoredThe clipboard manager for the AI eraPromote your product hereReach 125k+ visitors monthly
WaxSponsoredBlock anything with supervision, without erasing your iPhonePromote your product hereReach 125k+ visitors monthly
knobsSponsoredSee your site on any phone, any day, in any languageReadme
Sentinel-IR-MCP
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.
- npm: https://www.npmjs.com/package/sentinel-ir-mcp
- GitLab (main repository): https://gitlab.com/jakubrojicek11/sentinel-ir-mcp
- GitHub (mirror): https://github.com/jakcmencz/sentinel-ir-mcp
- Library behind it:
sentinel-ir - See what the agent sees, in your browser: https://sentinel-ir-playground-dc30c8.gitlab.io/
The 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.
Details
- Repository
- github.com/jakcmencz/sentinel-ir-mcp
- Website
- gitlab.com/jakubrojicek11/sentinel-ir-mcp
- Package
sentinel-ir-mcp- Transport
- STDIO
- Registry
- MCP registry, active