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., "@@palveron/mcp-server Check this tool call against governance policy before I execute it."
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.
⚡ Early access. Palveron is launching soon and access is currently invite-gated. This server is fully functional — you just need a
pv_live_key, which comes with an Early Access invite. Join the waitlist → palveron.com/early-access
Give your MCP-capable client — Claude Code, Cursor, any other MCP host — governance tools it can call before executing an action: policy verdicts, PII-masking results, and an audit trace for every check, all from the Palveron AI Governance Gateway.
Drop-in MCP server — one binary, configure your MCP host, you're done
Advisory governance verdicts — the gateway decides allow / mask / deny / hold; the agent (or your wrapping code) acts on the verdict
Audit trail per check — trace IDs flow back to the Palveron dashboard
Built on @palveron/sdk — retry, circuit breaker, typed errors out of the box
This package is the advisory path. It cannot physically stop a tool call: it answers the question "is this allowed?", and the calling agent (or your code via check()/wrap()) is expected to honor the answer. That is by design — it works with any MCP host, needs no network topology change, and gives you verdicts plus audit traces immediately.
Enforced, non-bypassable governance for MCP tool calls is a different product surface: the Palveron remote MCP proxy. There you register the target MCP server in the Palveron dashboard and point your IDE at POST {gateway}/api/v1/mcp/proxy/{server_id} instead of the target — every tools/call then structurally passes through policy checks, approval holds, and drift detection before it can reach the target server. No cooperation from the agent required.
This package ( | Remote MCP proxy | |
Model | Voluntary pre-flight check | In-path enforcement |
Can a call bypass it? | Yes — enforcement depends on the caller honoring the verdict | No — the proxy sits between client and target server |
Setup |
| Register the target server in the dashboard, point the IDE at the proxy URL |
Use it when | You want verdicts + audit traces inside any MCP host, or wrap tool calls programmatically | You need governance that agents cannot skip |
See the MCP setup guide for the enforced path.
Related MCP server: AgentGuard MCP Server
npm install -g @palveron/mcp-server
# or use directly via npx
npx @palveron/mcp-serverThe
pv_live_…key in the examples below requires an Early Access invite — request one here. Once you have a key, everything works out of the box.
Add to your claude_desktop_config.json:
{
"mcpServers": {
"palveron": {
"command": "npx",
"args": ["@palveron/mcp-server"],
"env": {
"PALVERON_API_KEY": "pv_live_xxx",
"PALVERON_BASE_URL": "https://gateway.palveron.com"
}
}
}
}Any MCP-capable host can launch the server via the palveron-mcp binary:
PALVERON_API_KEY=pv_live_xxx palveron-mcpTool | Purpose |
| Check a tool call against governance policies before execution. Returns the decision ( |
| Governance status and diagnostics — gateway connectivity, circuit-breaker state, configured local lists. |
| List the project's active policies so the host can explain its decisions. |
The server reads its configuration from environment variables. The MCP host sets them; you never put secrets in code.
Variable | Required | Description |
| yes | API key ( |
| no | Override the gateway endpoint (default: |
| no |
|
| no |
|
| no | Comma-separated tool names that are always denied locally, without a gateway call |
| no | Comma-separated tool names that always pass locally, without a gateway call |
Node.js 18 or newer
An MCP-capable client (Claude Code 0.4+, Cursor, etc.)
Early Access / Waitlist — palveron.com/early-access
Documentation — docs.palveron.com/integrations/mcp
Dashboard — palveron.com
Support — hello@palveron.com
GitHub — palveron/mcp-server
Changelog — CHANGELOG.md
MIT — Copyright © 2026 Palveron.
Verify a tool call against PALVERON governance policies before execution. Returns whether the action is allowed, blocked, or modified (with PII redacted). Every check creates an immutable audit trace.
Inputs: tool (required), input (required), agent_id, session_id.
List active governance policies for the current project. Shows policy names, enforcement actions, and content type scopes.
Inputs: environment.
Get PALVERON governance status and diagnostics. Shows connection state, circuit breaker status, configured policies, and gateway health.
Inputs: no named parameters.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Scored across 3 tools
Each tool has a distinct purpose: palveron_check verifies a single action, palveron_status provides system diagnostics, and palveron_policy_list lists policies. There is no ambiguity or overlap between them.
All tools share the consistent palveron_ prefix and snake_case format, but the second word is a mix of verb (check) and nouns (status, policy_list). Minor deviation from a strict verb_noun pattern.
Three tools is well-scoped for a governance checker: one to perform checks, one for status, and one for policy listing. No tools feel redundant or missing.
The domain is governance policy enforcement, and the set covers the core operations: enforcing a policy (check), understanding system state (status), and discovering applicable policies (list). No obvious gaps for the stated purpose.
MCP enforcement layer that intercepts AI agent actions and blocks rule violations before execution.
Security & DLP proxy for MCP: tool-poisoning scans, PII redaction on tool args/results. Beta.
Runtime permission, approval, and audit layer for AI agent tool execution.
Pre-execution governance for AI agents. Deterministic PASS/FAIL/REVIEW verdicts, replayable proof.
