SAIR MCP Server
by compscidrio.github.compscidr/sairv0.1.33
Run Android tests on real phones, or lease one: install, shell, screenshot, logcat.
context tax
pending
security
97/100
cold start
pending
freshness
Active2d ago
Our reading of SAIR, from the data
SAIR is a code execution & sandboxes MCP server from compscidr, listed in the official MCP Registry.
We haven't measured its tool list yet, so its token cost is unknown.
Maintenance is active: the last public signal was 2 days ago (2026-10-17). For comparison, 68% of code execution & sandboxes servers are active or maintained.
With 1 GitHub stars it ranks #158 of 357 code execution & sandboxes servers we index.
It runs locally on your machine over stdio and needs one secret (SAIR_API_KEY); use a scoped, least-privilege key.
Install SAIR MCP server
No published package or hosted endpoint yet — see the repository README for build-from-source instructions.
Configuration
| Variable | Required | Secret | Description |
|---|---|---|---|
| SAIR_API_KEY | yes | yes | An API key from https://sair.run/dashboard |
| SAIR_API_URL | — | — | Agent API base URL (default: https://api.sair.run) |
Security signals
97/100 — no known issues found as of 2026-10-19, from the checks below. This is not a guarantee of safety; review what a server can do before connecting it.
Deductions
- No security policy (SECURITY.md)-3
Checks
- ✓Repository hygiene (archived, activity, license, security policy)
- ○Package metadata (install scripts, provenance) — pending
- ○Tool descriptions (prompt-injection and hidden-text heuristics) — pending
- ○Source scan (secrets, CVEs, risky code) by vectra-guard — pending
Scan it yourself before installing with vectra-guard, the open-source agent security CLI. Scoring rules
Freshness
Active — last maintenance signal 2d ago. The newest of the signals below sets the band.
Last commit (default branch)
2026-10-17 · 2d ago · GitHub
Latest release
2026-10-17 · 2d ago · GitHub · v0.1.33
Package published
no data · npm/PyPI
Registry entry updated
2026-10-17 · 2d ago · official registry · v0.1.33
How it compares in Code Execution & Sandboxes
Against the most-starred code execution & sandboxes servers we index. Token cost is per model turn, measured from each server's live tool list.
| Server | Stars | Tools | Tokens / turn | Freshness | Runs |
|---|---|---|---|---|---|
| SAIR (this) | 1 | — | not measured | Active | local |
| REA | 324,759 | — | not measured | Active | local |
| Node Repl | 28,567 | — | not measured | Active | local |
| Ask Jev | 5,224 | — | not measured | Active | hosted |
| Container Use | 4,072 | — | not measured | Maintained | — |
| MATLAB | 1,679 | — | not measured | Active | local |
FAQ
›Does SAIR require an API key?
Yes. It expects SAIR_API_KEY, of which 1 is a secret.
›Can I use SAIR as a remote (hosted) MCP server?
No hosted endpoint is published; it runs locally over stdio.
›Is SAIR in the official MCP registry?
Yes, as io.github.compscidr/sair.
Sources and method
- Official MCP Registry entry
- updated 2026-10-17
- GitHub repository
- fetched 2026-10-19
- Package registry (npm / PyPI)
- listed
- Security signals, computed by us
- 2026-10-19
- Last checked against all sources
- 2026-10-19
The description, packages and links come from the maintainer's own published metadata. Token cost, security signals, freshness and the reading above are MCPSkillHub's own measurements; see the methodology. Spot an error? Request a correction or claim the listing.
Alternatives to SAIR
Other code execution & sandboxes MCP servers.
REAActiveReverse engineer anything from your terminal or agent with one CLI and MCP server.
Node ReplActiveStandalone MCP server exposing a session-persistent Node.js REPL (node_repl) — independent of qwen-code core.
Ask JevActiveA private persistent computer: files and a bash shell that survive between runs.
Container UseMaintainedContainerized environments for coding agents: each agent works in its own fresh container and git branch, with execution history and terminal access.
MATLABActiveConnect AI coding agents to MATLAB. Run code, tests, and analysis via MCP.
LLM SandboxActiveSecurely run LLM-generated code in isolated containers across 7 languages and 3 container backends.