CesSpace ARC
Provides tools for interacting with Git repositories, including branch protection, diff inspection, and commit operations, with policy enforcement and audit logging.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@CesSpace ARCshow me the git diff and recent commits"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
CesSpace ARC — Secure Agent-to-Machine Control Plane
CesSpace ARC (Agent Remote Control) is a secure, vendor-neutral control plane providing policy-enforced, audited access to development machines, virtual machines, repositories, terminals, and processes for authorized AI coding agents. Lead Developer & Architect: P Thakur
1. Mission & Vision
Modern AI coding agents (Claude Code, Antigravity, OpenAI Codex, OpenCode, DeepSeek agents) require rich interactions with host environments—reading files, inspecting diffs, running tests, and executing builds. However, giving autonomous agents unrestricted ambient access (such as open SSH keys, raw /bin/sh evaluation, or unfettered root access) creates severe security risks:
Accidental or malicious filesystem destruction.
Credential harvesting (
~/.ssh,~/.aws,.env).Indirect prompt injection leading to remote code execution.
Silent repository or supply chain tampering.
CesSpace ARC mediates every single agent action through an authoritative policy engine, an OS-level filesystem jail, and an append-only audit trail.
Related MCP server: MCP SSH Orchestrator
2. High-Level Target Architecture
AI Client / Coding Agent (Claude Code / Antigravity / Codex / DeepSeek)
│
▼
MCP Interface (JSON-RPC 2.0)
│
═════════════════════╪═══════════════════════ Trust Boundary 1 (Ingress)
▼
ARC Remote Gateway
& Authentication Engine
│
═════════════════════╪═══════════════════════ Trust Boundary 2 (Policy)
▼
Policy Engine
(RC-01: Minimal Security Kernel;
RC-04: Declarative Rules & Approvals;
Precedence: DENY > REQUIRE APPROVAL > ALLOW)
│
▼
Audit Layer
(RC-01: In-Memory / Stream Sink;
RC-06: Anchored Persistent Log)
│
═════════════════════╪═══════════════════════ Trust Boundary 3 (Host Execution)
▼
ARC VM Agent
│
┌────────────────┼────────────────┬────────────────┐
▼ ▼ ▼ ▼
Filesystem Git Terminal Processes
(Jailed Roots) (Branch Guard) (Bounded execve) (Tree Superv.)Mandatory Invariant: No Filesystem, Git, Terminal, or Process operation may ever execute without traversing the full Authentication $\to$ Policy Engine $\to$ Audit Layer pipeline. In RC-01, this invariant is satisfied via the Minimal Security Kernel, which enforces default-deny admission, canonical workspace root binding, and audit logging before any tool runs.
3. The 20 Permanent Security Principles
Zero implicit trust
Default deny
Least privilege
Fail closed
Separation of authentication and authorization
Mandatory policy mediation for every privileged operation
No policy bypass
Authorized filesystem roots only (strict canonical jailing & descriptor containment)
Secrets and credential stores permanently inaccessible by default
Policy-controlled subprocess execution without shell interpolation
Destructive operations denied by default
Zero cloud-root or production access in public defaults
Universal auditability for every privileged action
Protected Git branches (
main,release/*) immutable to agentsExplicit human approval for sensitive mutations
Prohibition of private CES secrets, infrastructure details, and tokens
Permanence of committed secrets (Git history treated as public and forever)
Vendor neutrality across AI model providers and platforms
Code-enforced security invariants (never documentation alone)
Mandatory negative controls proving blocked operations fail
4. Documentation Index
The complete architecture and security foundation of CesSpace ARC is documented below:
Document | Description |
High-level system architecture, component breakdown, MCP standard, and architectural invariants. | |
The 4 security zones and 3 trust boundaries isolating untrusted agents. | |
STRIDE analysis, AI threat vectors (prompt injection, symlink escapes, DoS). | |
The 20 inviolable security invariants and their verification criteria. | |
Formal schemas and permission tiers for all read-only, mutating, and composite tools. | |
| |
Workspace jailing, canonical realpath checks, symlink containment, Linux | |
Append-only event schemas, data minimization first, redaction, and tiered anchoring. | |
Fail-closed error taxonomy and anti-leakage information sanitization. | |
Monorepo package layout, component boundaries, and dependency DAG. | |
Formal ADRs capturing key design and security decisions. | |
Detailed scope, Minimal Security Kernel, tool list, and negative control criteria for RC-01. | |
Detailed scope, controlled terminal and process execution, and negative control criteria for RC-02. | |
Detailed scope, safe file modification and patch engine, and negative control criteria for RC-03. | |
Detailed scope, declarative policy engine, approval state machine, and the 38 frozen negative controls. | |
RC-04 acceptance evidence: architecture summary, control coverage table, and final quality gates. | |
Detailed scope, secure remote gateway, Streamable HTTP over TLS 1.3, mTLS, and 79 negative controls. | |
RC-05 acceptance evidence: architecture summary, control coverage table, and final quality gates. | |
Mandatory project engineering, stage-gate, and security governance rules. | |
Vulnerability disclosure, responsible reporting, and safety invariants. | |
Guidelines for contributing code, tests, and security negative controls. |
5. Toolchain & Monorepo Configuration
CesSpace ARC is standardized on:
Node.js:
^24.0.0Package Manager:
pnpm@12.4.2(pnpm-workspace.yaml)Internal Dependency Protocol:
workspace:*Access: All internal packages are marked
private: trueduring development stages.
6. Development Roadmap & Stages
Stage | Name | Target Capabilities | Status |
RC-00 | Architecture & Security Foundation | Trust boundaries, threat models, invariants, tool taxonomy, ADRs. | Implemented |
RC-01 | Read-Only MCP Core | Minimal Security Kernel, 9 read-only tools, canonical jailing, negative controls. | Implemented |
RC-02 | Controlled Terminal & Processes | Bounded process execution, output limits, timeout enforcement. | Implemented |
RC-03 | Safe File Modification | Jailed file writing, atomic patches, size limits, approval gating. | Implemented |
RC-04 | Policy Engine & Approvals | Declarative YAML policy engine, authenticated admin channel, approval tokens, approval audit lifecycle. | Implemented |
RC-05 | Secure Remote Gateway | Streamable HTTP over TLS 1.3 with SSE response framing, mutual TLS, device enrollment, volatile sessions. | Implemented |
RC-06 | Audit & Evidence | Append-only JSONL logging, tiered anchoring, automated redaction. | Planned |
RC-07 | Engineering-Aware Tools | Composite verification commands ( | Planned |
RC-08 | Integrations & Security Review | Cross-client validation, penetration testing, fuzzing. | Planned |
7. License
CesSpace ARC is licensed under the Apache License, Version 2.0.
This server cannot be deployed
Maintenance
Related MCP Connectors
Security gateway for AI agents: policy, approval, and audited execution, no secrets shared.
Fail-closed policy guardrails for AI agents running kubectl, terraform, helm, and argocd.
Governance layer for AI coding agents: knowledge-graph grounding, session audit, policy controls.
- FullmaktOAuthai.fullmakt
Credential broker for AI agents: scoped, revocable API access with policy enforcement and audit.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceEnables secure remote access operations through SSH, SFTP, rsync, VPN, and tunneling with enterprise-grade policy enforcement and audit logging. Provides AI assistants with secure, policy-driven access to remote systems while maintaining comprehensive audit trails and zero-trust security.1Apache 2.0
- AlicenseBqualityAmaintenanceProvides policy-driven, auditable SSH access to server fleets for AI assistants with zero-trust security controls, command whitelisting, and comprehensive audit logging to safely manage infrastructure.1327Apache 2.0
- AlicenseNot gradedqualityAmaintenanceEnables AI assistants to securely execute SSH commands on remote servers with connection pooling, session isolation, and a web audit panel.3MIT
- FlicenseNot gradedqualityAmaintenanceGive AI agents Zero-Trust access to production infrastructure without the risks of granting them shell access. Actions are bounded by policy and an on-host runner.335-