sentinelSAFE
Autonomous multi-agent engineering copilot that investigates software issues, plans fixes, uses MCP tools, verifies changes, and learns from past incidents.
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
Autonomous Multi-Agent Engineering Ops Copilot
Sentinel is a production-oriented AI engineering system that autonomously investigates software engineering incidents, plans fixes, uses controlled tools to inspect and modify repositories, verifies changes through automated testing, learns from previous incidents, and reports execution outcomes.
Vision
Sentinel aims to demonstrate modern AI engineering patterns including:
- Multi-agent orchestration
- Planning and autonomous workflows
- Tool calling
- Model Context Protocol (MCP)
- Agent memory
- Automated verification
- Evaluation
- Observability
- Human-in-the-loop controls
- Production-oriented architecture
Current Status
🚧 Project initialization — Sprint 0
Technology
- Python
- LangGraph
- LangChain
- Ollama
- MCP
- FastAPI
- ChromaDB
- SQLite
- Pytest
- Docker
Architecture
The project follows Clean Architecture principles with explicit separation between domain logic, application services, infrastructure, agent orchestration, and external interfaces.
Development
Install dependencies
uv sync
123013807dccOBSERVED · 2026-10-11Connect
Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control.
claude mcp add sentinel -- uvx sentinel
{
"mcpServers": {
"sentinel": {
"command": "uvx",
"args": [
"sentinel"
]
}
}
}Exposed tools (3)
2 read · 1 write · 0 destructive.
| Tool | Risk | Description |
|---|---|---|
read_file | read | Read a UTF-8 text file from the repository. |
run_tests | write | Run a focused pytest target. |
search_code | read | Search repository source code for a text pattern. |
Trust audit
SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | PASS |
| L1 | Static analysis of the code | PASS |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | PASS |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- none-observed
- Network
- none-observed
- Shell
- none-observed
- Dependencies
- pinned
- Secrets in source
- none-found
Findings (3)
"path": "../../outside.txt",
policy.validate_path("src/../../outside.txt")Gates applied: no_behavioural_pass, no_license.
123013807dccfull audit observations/trust-audit/mcp-server/juyelhushen__sentinel.json · Report an issue / request a re-scanAudit history
Every audit this server has had. A grade with a past is a grade somebody is still checking.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-11 | 123013807dcc | SAFE | B | 89 | first audit |
Questions
What is the sentinel MCP server?
Autonomous multi-agent engineering copilot that investigates software issues, plans fixes, uses MCP tools, verifies changes, and learns from past incidents.
What tools does sentinel expose?
3 in total: 2 read-only, 1 that write, and 0 that can delete or overwrite. Every one is listed on this page with its risk.
Is sentinel safe to connect to an agent?
The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean server reads B.
What credentials does sentinel need?
No credential environment variables were found in its source, so it appears to need none.
How does sentinel run?
It speaks stdio, so it runs as a local process your client starts. It is published on PyPI as sentinel.
How current is this page?
The grade is for one exact copy of the source (123013807dcc), read on 2026-10-11. The repository is watched and re-audited when it changes.