MCP.Market

Arcstone Sidecar MCP server

by trencinodin-stack·io.github.trencinodin-stack/arcstone-mcp-sidecar·v0.1.0

Deterministic execution boundary and reference MCP sidecar for Arcstone Security Stack

C65/100grade C
What users say
No reviews yet
Be the first
Safety scan
C65/100

full report

Adoption
New

0 stars

Reviews

Write one

Nobody has reviewed Arcstone Sidecar yet.

If you have run it, two minutes of your experience saves the next person an afternoon.

Arcstone Sidecar 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 · 2026-10-02 · same rubric, same numbers if you re-run it

no findings
  • –Code scanremote-only server, no package to scann/a
  • –Live reliabilityno gateway calls yet and no remote to proben/a
  • –Tool poisoningtools not inspected (local package is not executed); not countedn/a
  • Auth qualityno auth information5/15
  • Maintenancelast push 2 days ago15/15
  • Maintainer identityregistry namespace matches repository owner6/10
Overall 65/100. Components that don't apply are left out of the denominator. Any critical finding is an F.RubricAppeal a findingJSON

How Arcstone Sidecar compares

Against every graded Security MCP server, from our own scans and uptime checks. Updated after each scan run.

Safety score
65/100
higher than 20% of 915 Security servers

Install Arcstone Sidecar in Claude Code, Cursor or VS Code

The registry entry has no remote endpoint or installable package.

What the publisher says

From the Arcstone Sidecar repository's README, as published. We do not edit it. Read it on GitHub

Arcstone Execution Boundary

Repository identity: arcstone-mcp-sidecar Implementation package: arcstone-execution-boundary Status: Experimental / Downstream / Non-Canonical / Bounded Evidence Version: 0.1.0 implementation starter

This repository is the initial native implementation of the frozen Arcstone Execution Boundary v0.1 experimental specification.

It tests one bounded question:

Can a deterministic downstream execution boundary prevent an untrusted or nondeterministic producer from causing a protected side effect unless an explicit, boundary-controlled authorization condition has been satisfied?

Frozen upstream relationship

Arcstone Continuity Core
                        FROZEN
                       /      \
                      /        \
                     ▼          ▼
       Path A Ingress Lab    Execution Boundary
          COMPLETE/FROZEN       THIS REPO

The Path A Ingress Lab and Execution Boundary are sibling downstream investigations.

This repository does not modify or reinterpret either frozen upstream repository.

v0.1 invariants

I1 — NO VALID AUTHORIZATION
     ⇒ ZERO PROTECTED ACTUATION

I2 — ONE VALID SINGLE-USE AUTHORIZATION
     ⇒ AT MOST ONE PROTECTED ACTUATION

I3 — UNTRUSTED PRODUCER
     ⇏ PROTECTED RESOURCE

The implementation explicitly keeps separate:

authorization lifecycle
≠ gate decision
≠ actuation result
≠ observed protected effect

What is intentionally not here

v0.1 does not require or claim:

  • MCP
  • WASM
  • HMAC / signatures / PKI / KMS
  • network APIs
  • generalized policy engines
  • agent frameworks
  • package-manager publication
  • public production distribution guarantees
  • exactly-once real-world execution
  • production authorization security
  • AI alignment or general agent safety

Local data model

The experimental root has this shape:

runtime/
├── auth/
│   ├── issued/
│   └── consumed/
├── protected/
│   └── effect.bin
└── evidence/
    └── <run-id>/

An authorization record is trusted because the untrusted producer is not permitted to create or modify the auth tree under the tested authority configuration. The authorization identifier itself carries no authority.

The consumed/.claim file is created with create_new(true). That atomic local reservation is the v0.1 single-use claim primitive.

Build

Windows CMD:

cargo build
cargo test

or:

scripts\windows\verify.cmd

Example

Create the runtime directories:

arcstone-exec init --root runtime

Issue one authorization:

arcstone-exec issue --root runtime --auth-id AUTH-001 --action WRITE_PROTECTED_FILE --resource-id EFFECT_LOG --payload-hex 48454c4c4f

Create request.json:

{
  "authorization_id": "AUTH-001",
  "action": "WRITE_PROTECTED_FILE",
  "resource_id": "EFFECT_LOG",
  "payload_hex": "48454c4c4f"
}

Execute it:

arcstone-exec execute --root runtime --request request.json --run-id manual-001

Inspect authorization state:

arcstone-exec inspect --root runtime --auth-id AUTH-001

A replay of the same request should return a denied result because the claim already exists.

Windows authority-boundary evidence

The Rust tests verify deterministic authorization, binding, consumption, replay, failure separation, and concurrent claiming.

They cannot by themselves prove producer-to-resource authority separation when producer and boundary run under the same Windows principal.

A separate bounded Windows authority experiment was therefore completed using distinct non-administrator producer and authority principals and a dedicated disposable runtime with explicit ACL separation.

Observed results:

Shortened. The full README is on GitHub.

Nothing above is checked by us. What we check is on the safety report.

Arcstone Sidecar: common questions

Is Arcstone Sidecar MCP server safe?
With care: it is graded C, so read the findings first (65/100). Read the Arcstone Sidecar safety report
Does Arcstone Sidecar need an API key?
Not as far as the registry entry and our scan can tell: no credentials are declared or required.
Is Arcstone Sidecar maintained?
The last commit was 35 days ago (2026-09-30). The latest release is v0.1.0.
What can I use instead of Arcstone Sidecar?
Servers from other publishers that do the same job: Guardvibe MCP server, MCP Safety Warden MCP server and SPARDA MCP server.

Alternatives to Arcstone Sidecar

Same job from other publishers: the closest match first, then the best rated.

  • Guardvibe
    Deterministic security layer your AI can't be. 644 rules, 39 tools, CLI + doctor + host audit.
    C
  • MCP Safety Warden
    MCP proxy adding security scanning, behavioral profiling, risk gating, and safe tool call execution.
    A
  • SPARDA
    AI writes. SPARDA proves. Deterministic, offline security gate for AI edits.
    A
  • ZeroDOM
    The deterministic attack-surface perception layer for AI security agents
    A
  • SPARDA
    AI writes. SPARDA proves. Deterministic, offline security gate for AI edits.
    A