skvil-mcp
Enables security scanning and verification of AI agent skills hosted on GitHub repositories.
Enables security scanning and verification of AI agent skills hosted on GitLab repositories.
Supports verification of tamper-proof, on-chain security certifications for AI agent skills anchored on the Solana blockchain.
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., "@skvil-mcp Check if sha256:4a2f...c81e is safe to install"
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.
skvil-mcp
MCP server for the Skvil security scanner
Verify, scan, and check on-chain certifications for AI agent skills — directly from your AI assistant.
Why skvil-mcp?
AI agents install skills from the internet — but how do you know a skill is safe?
Skvil is a community-powered security scanner that analyzes AI agent skills for malicious patterns, builds reputation scores through crowdsourced scans, and issues on-chain certifications that are tamper-proof and publicly verifiable.
This MCP server gives your AI agent native tools to interact with the Skvil network. No HTTP knowledge required — just ask your agent to verify a skill.
On-chain certification
Skvil's certification pipeline is what sets it apart — the entire process is fully automated with zero human intervention:
Community scanning — multiple independent agents scan the same skill
Reputation building — scores aggregate via exponential moving average (EMA)
Crucible analysis — automated static analysis scans 32+ pattern categories, then an AI triage phase (embeddings + LLM) validates findings and filters false positives
On-chain registration — skills scoring ≥ 80 are automatically anchored on Solana via SPL Memo transactions, creating a tamper-proof trust anchor that no single party can forge or revoke silently
Certification is algorithmic: score ≥ 50 passes, score < 50 fails and revokes any existing certificate. A periodic re-certification scheduler re-analyzes certified skills and revokes those that no longer pass.
When you run skvil_verify, you're not just checking a database — you're verifying against an immutable on-chain record.
Related MCP server: vigile-mcp
Quick start
Tip: Works with both
npx(Node) andbunx(Bun). We recommend Bun for faster installs and startup.
Claude Desktop
Add to your claude_desktop_config.json:
{
"mcpServers": {
"skvil": {
"command": "bunx",
"args": ["@skvil/mcp-server"]
}
}
}{
"mcpServers": {
"skvil": {
"command": "npx",
"args": ["-y", "@skvil/mcp-server"]
}
}
}Claude Code
Add to your project's .mcp.json:
{
"mcpServers": {
"skvil": {
"command": "bunx",
"args": ["@skvil/mcp-server"]
}
}
}{
"mcpServers": {
"skvil": {
"command": "npx",
"args": ["-y", "@skvil/mcp-server"]
}
}
}VS Code / Cursor
Add to your settings (JSON):
{
"mcp.servers": {
"skvil": {
"command": "bunx",
"args": ["@skvil/mcp-server"]
}
}
}{
"mcp.servers": {
"skvil": {
"command": "npx",
"args": ["-y", "@skvil/mcp-server"]
}
}
}That's it. The server auto-registers a free API key on first use. Zero config.
Tools
Tool | Auth | Description |
| No | Check if a skill is safe by its SHA-256 hash. Returns reputation score, risk level, on-chain certification status, and Crucible behavioral analysis. |
| No | Community statistics: total skills scanned, trusted, critical, and on-chain certified counts. |
| No | List skills with active on-chain certifications (V1/V2/V3/Gold). Up to 10 most recent. |
| No | Browse the full catalog of certified skills with metadata, install URLs, and provider info. Up to 100 skills. |
| No | Get a free API key (500 scans/day). Auto-cached locally for future use. |
| Key | Submit security scan results to the community reputation network. Requires full skill identification (see below). |
| Key | Report a suspicious skill. Confirmed reports trigger automatic on-chain revocation. |
skvil_scan — required fields
Every scan submission requires full identification so the Crucible behavioral analysis pipeline can fire:
Field | Type | Description |
| string | Skill name (max 256 chars) |
| string |
|
| number | Number of files in the skill |
| object | Map of |
| number | Computed security score 0-100 (server recomputes from findings) |
| string |
|
| string | Required. Source URL — must be |
| string | Required. |
| string | Required. Agent platform submitting the scan (e.g. |
| array | Security findings (severity, category, description, file, line) |
| object | Optional SKILL.md metadata |
Without skill_url, the backend skips Crucible forwarding and the skill can never be certified.
Certification levels
Level | Meaning |
V1 | Basic verification — scanned by community, passed automated static analysis (32+ pattern categories + AI triage) |
V2 | Enhanced verification — V1 + passed Crucible behavioral analysis in sandboxed environment |
V3 | Full verification — V2 + passed periodic re-certification cycles |
Gold | Highest trust — V3 + continuous monitoring, reserved for critical infrastructure skills |
All levels are registered on-chain. The entire certification process is automated — no human review is involved at any level. Higher levels require progressively more rigorous automated verification.
Configuration
API key
The server automatically registers a free API key on first use and caches it in ~/.skvil/mcp-config.json.
To use an existing key:
{
"mcpServers": {
"skvil": {
"command": "npx",
"args": ["-y", "@skvil/mcp-server"],
"env": {
"SKVIL_API_KEY": "sk_your_key_here"
}
}
}
}Custom API URL
For self-hosted or development instances:
{
"env": {
"SKVIL_API_URL": "http://localhost:8000"
}
}Key resolution order
SKVIL_API_KEYenvironment variableCached key in
~/.skvil/mcp-config.jsonLegacy Python client key in
~/.skvil/config
Examples
"Is this skill safe to install?"
User: Check if sha256:4a2f...c81e is safe
Agent calls skvil_verify → gets reputation, certification, findings
Agent: This skill has a reputation score of 91.2 (safe) and is
on-chain certified at V2 level. 15 community scans with
no critical findings. Safe to install."What skills are certified?"
User: Show me certified skills
Agent calls skvil_certified → gets list of on-chain certified skills
Agent: There are 7 on-chain certified skills:
1. web-scraper — V2, score 91.2, certified Feb 18
2. data-pipeline — V1, score 85.0, certified Feb 15
..."Report this suspicious skill"
User: Report sha256:dead...beef — it's sending data to an unknown server
Agent calls skvil_report → submits report
Agent: Report #42 submitted. The skill will be re-analyzed
automatically. If the report is confirmed, the skill
will be flagged and any on-chain certification will
be revoked.How it works
┌─────────────┐ stdio ┌────────────┐ HTTPS ┌──────────────────┐
│ AI Agent │ ◄────────────► │ skvil-mcp │ ────────────► │ api.skvil.com │
│ (Claude, │ MCP tools │ (local) │ REST API │ (reputation DB │
│ GPT, etc) │ │ │ │ + on-chain) │
└─────────────┘ └────────────┘ └──────────────────┘The MCP server runs locally as a subprocess of your AI client. It translates MCP tool calls into HTTPS requests to the Skvil API. No data is stored remotely except scan results and reports — and certifications are anchored on-chain for public verification.
Development
git clone https://github.com/Skvil-IA/skvil-mcp.git
cd skvil-mcp
bun install # or: npm install
bun run build # or: npm run buildRun locally
# Point to local API for development
SKVIL_API_URL=http://localhost:8000 bun dist/index.jsTest with MCP Inspector
npx @modelcontextprotocol/inspector node dist/index.jsLint & format
npm run lint
npm run format
npm run typecheckLicense
MIT — Skvil 2026
Available Tools
7 toolsskvil_catalogA
Browse the full catalog of Skvil-certified AI agent skills with detailed metadata: author, version, description, provider, agent platform, file count, and install URL. Returns up to 100 skills. Use this to discover safe skills available for installation.
Inputs: no named parameters.
skvil_certifiedA
List skills that have been verified and certified by Skvil admins. Certified skills have been manually reviewed and registered for tamper-proof verification. Returns up to 10 most recently certified skills with their level (V1/V2/V3/Gold), reputation score, and certification date.
Inputs: no named parameters.
skvil_registerA
Register for a free Skvil API key. The key is automatically cached locally for future use. No sign-up or account required. Other tools (skvil_scan, skvil_report) will use the cached key automatically.
Inputs: no named parameters.
skvil_reportA
Report a suspicious or malicious AI agent skill to Skvil admins for review. Requires an API key (use skvil_register first). Reports are reviewed by admins and confirmed findings lead to certification revocation.
Inputs: hash (required), reason (required), details.
skvil_scanA
Submit security scan results for an AI agent skill to the Skvil reputation network. Contributes to the community reputation score (EMA). Requires an API key (use skvil_register first). The server recomputes the score from findings — always provide accurate findings.
Inputs: name (required), composite_hash (required), file_count (required), file_hashes (required), +7 more.
skvil_statsB
Get aggregate statistics from the Skvil community network: total skills scanned, trusted count, critical findings, and certified skills.
Inputs: no named parameters.
skvil_verifyA
Check if an AI agent skill is safe before installing it. Returns reputation score, risk level, certification status, and community scan data. Use this to verify any skill by its SHA-256 composite hash.
Inputs: hash (required).
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 7 tools
Each tool has a clearly distinct purpose with no overlap: catalog browsing, certified listing, registration, reporting, scanning, statistics, and verification. The descriptions specify unique functions, making misselection unlikely.
All tools follow a consistent 'skvil_verb' pattern (e.g., skvil_catalog, skvil_register), using snake_case throughout. This predictability aids agent selection and readability.
With 7 tools, the set is well-scoped for the domain of AI skill security and reputation management. Each tool serves a specific role, covering discovery, verification, reporting, and community interaction without bloat.
The toolset covers core workflows: discovery (catalog, certified), verification (verify, scan), reporting (report), and community stats. A minor gap is the lack of a tool for managing or revoking API keys, but agents can work around this.
Maintenance
Related MCP Connectors
Token rug-risk scans, Know Your Agent wallet checks and deployer reputation for AI agents.
Human-reviewed security certificates and ops audits for AI agent skills, paid per job.
Trust layer for AI agents. Privi Guard checks web pages, emails and tool results for prompt injection and outgoing text for leaked API keys and card numbers, with signed on-chain receipts (1,000 free checks a month). Privi Scan grades any MCP server for tool poisoning and rug pulls. Plus tamper-evident audit logs, agent passports, spending mandates and a live kill switch.
Pay-per-call safety checks for AI agents: screen a crypto address or URL before you transact.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceProvides agent certification and trust verification tools for AI agents, enabling certification checks, trust score calculations, audit ticket issuance, and emergency kill switch activation through the A-SOC trust network.1 npm1-
- AlicenseAqualityFmaintenanceEnables AI agents to query trust scores for MCP servers and agent skills while scanning content for potential security issues. It provides direct access to the Vigile trust registry to help users evaluate the safety of third-party tools and integrations.925 npmMIT
- FlicenseNot gradedqualityDmaintenanceOn-chain trust verification for AI agent tools. Agents query skill attestations, audit levels, and risk scores before running third-party MCP servers, so you know what's safe before you execute.-
- AlicenseAqualityDmaintenanceEnables AI coding agents to scan smart contracts and code for vulnerabilities, check against 12 famous-hack patterns, and return public security receipts directly in the IDE.418 npmMIT