Ephemora Cell MCP — WASM Sandbox MCP server
io.github.MichaelS1011/ephemora-cell-mcp·v1.0.3·48 starsWASM sandbox for MCP tools. WASI-isolated, fuel/memory/I/O capped, attested.
48 stars229 downloads/wk
Reviews
Write oneNobody has reviewed Ephemora Cell MCP — WASM Sandbox yet.
If you have run it, two minutes of your experience saves the next person an afternoon.
Ephemora Cell MCP — WASM Sandbox tools
No tool declarations could be read from the package source. They show once the server is installed.
Public scan report
scanner v0.1.10 · 2026-10-15 · same rubric, same numbers if you re-run it
- Code scan25 source files scanned25/25
- –Live reliabilityno gateway calls yet and no remote to proben/a
- –Tool poisoningtools not inspected (local package is not executed); not countedn/a
- Auth qualitylocal package, no credentials required12/15
- Maintenancelast push 1 days ago15/15
- Maintainer identityregistry namespace matches repository owner6/10
How Ephemora Cell MCP — WASM Sandbox compares
Against every graded MCP server, from our own scans and uptime checks. Updated after each scan run.
- Safety score
- 89/100
- higher than 80% of 48,255 servers
- GitHub stars
- 48
- more than 94% of 28,688 servers
- Downloads a week
- 229
- more than 77% of 12,191 servers with a package
Install Ephemora Cell MCP — WASM Sandbox in Claude Code, Cursor or VS Code
claude mcp add ephemora-cell-mcp -- uvx ephemora-cell
What the publisher says
From the Ephemora Cell MCP — WASM Sandbox repository's README, as published. We do not edit it. Read it on GitHub
Ephemora Cell
Deterministic execution for untrusted AI-generated code.
Run AI-generated code, MCP tools and plugins with exact, predictable cost — every execution bounded, measured, and reproducible.
~0.5 ms warm · ~3M executions/hour per core (one-liner) up to ~5.5M pooled · deterministic, not "isolated and hoped for"
Built for AI agents, MCP tools, plugins, code interpreters, and other untrusted workloads.
Fast, capability-based WASM execution: CPU, memory, time, I/O and filesystem budgets enforced per execution, with sign-ready execution records (RFC 8785 JCS canonicalization + ES256 sign()/verify() primitives).
The problem
AI agents increasingly need to write and execute code, call tools, and run plugins. The question that decides whether that is safe:
How do you let an agent execute untrusted code without giving that code access to your host, your credentials, your network, or unlimited compute — with nothing pre-opened by default?
AI Agent ──▶ Tool / MCP ──▶ Ephemora Cell ──▶ WASM ──▶ bounded resultEphemora Cell is a small, capability-based WASM execution runtime for exactly that job: an execution primitive — not an agent framework — that sits underneath your existing agent stack, MCP server, plugin system, or application.
Every execution leaves evidence
Every tool call answers three questions at once — attached to the result as _meta.execution, canonicalized (RFC 8785 JCS) and signable:
"Verifying. Not claimed." is data, not a slogan: any record can be re-checked — rewrite one field and verify() fails. Runnable demo: python examples/signedrecorddemo.py.
Quick Start
Three commands: install Cell, run something untrusted, read its audited receipt.
1 — Install (use a virtualenv; on Ubuntu ≥ 23.04 / Fedora a bare pip install is refused by PEP 668. Windows: use Git Bash or WSL, and python instead of python3):
python3 -m venv .venv && source .venv/bin/activate
python -m pip install ephemora-cell2 — Run something untrusted (the repo ships examples, or bring any .wasm):
git clone https://github.com/MichaelS1011/ephemora-cell.git && cd ephemora-cell
ephemora-cell run examples/hello.wasm --isolated(adds OS-level process isolation around the run, a few ms — recommended for code you didn't build)
Hello from Ephemora Cell!3 — Read the audited receipt — same run, machine-readable. Here a hostile module (examples/fuel_bomb.wasm) is given a 100-unit fuel budget and stopped, exactly as budgeted:
ephemora-cell run examples/fuel_bomb.wasm --fuel 100 --isolated --jsonShortened. The full README is on GitHub.
Nothing above is checked by us. What we check is on the safety report.
Grade history
- 2026-09-19restoreB → Ascore 89
- 2026-09-19restoreC → Bscore 71: Whole environment serialized (possible credential exfil)
Ephemora Cell MCP — WASM Sandbox: common questions
- Is Ephemora Cell MCP — WASM Sandbox MCP server safe?
- Yes, by our scan: it is graded A (89/100). Read the Ephemora Cell MCP — WASM Sandbox safety report
- How do I install Ephemora Cell MCP — WASM Sandbox?
- It runs on your machine. Copy the Claude Code, Cursor, VS Code or Claude Desktop config from the install section.
- Does Ephemora Cell MCP — WASM Sandbox need an API key?
- Not as far as the registry entry and our scan can tell: no credentials are declared or required.
- Is Ephemora Cell MCP — WASM Sandbox maintained?
- The last commit was 21 days ago (2026-10-14). The latest release is v1.0.3.
- How does Ephemora Cell MCP — WASM Sandbox compare with other MCP servers?
- safety score 89/100 (higher than 80% of 48,255 servers); github stars 48 (more than 94% of 28,688 servers); downloads a week 229 (more than 77% of 12,191 servers with a package). Full comparison.