
Palveron MCP Server
io.github.palveronPublished by GitHub account palveronv1.0.1Updated Nov 10, 2026
Early access - AI governance gateway for MCP tool calls (policies, PII masking, audit).
Overview
Palveron's advisory governance server lets an MCP host ask, before running a tool call, whether policy allows, masks or blocks it, and get an audit trace ID.
- What you can do
- Check a planned tool call against governance policies and get a verdict (passed, blocked, modified/redacted/anonymized with sanitized input, pending approval), findings and an audit trace ID
- Inspect governance status and diagnostics, including gateway connectivity, circuit-breaker state and configured local lists
- List the project's active policies so the host can explain its decisions
- Apply local always-block and always-allow tool lists without calling the gateway
- When to use it
- Use it when you want policy verdicts, PII masking results and audit traces inside any MCP-capable host or coding agent, or when you plan to wrap tool calls programmatically. It is advisory only, so it suits setups where the agent or your own code honors the verdict rather than needing non-bypassable enforcement.
- Requirements
- Node.js 18 or newer and an MCP-capable client. A Palveron API key in PALVERON_API_KEY, which currently requires an Early Access invite. Optional environment variables set the gateway base URL, fail-open behavior, log level, and always-block or always-allow tool lists. Network access to the Palveron gateway.
Installation
In SourceWeft
- Open Palveron MCP Server in the dashboard and add it to a workspace.
- Enable the server for the chats that should use its tools.
Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.
Other MCP clients
Follow the launch instructions in the repository.
README
@palveron/mcp-server
Official Palveron MCP server — advisory AI-governance checks for MCP hosts and coding agents
[npm version] [npm downloads] [License: MIT] [Documentation] [Early Access]
⚡ 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
Advisory check vs. enforced governance — which one do you need?
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.
See the MCP setup guide for the enforced path.
Installation
Quick Start
The
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.
Claude Code
Add to your claude_desktop_config.json:
Other MCP hosts
Any MCP-capable host can launch the server via the palveron-mcp binary:
Tools exposed via MCP
Configuration
The server reads its configuration from environment variables. The MCP host sets them; you never put secrets in code.
Requirements
- Node.js 18 or newer
- An MCP-capable client (Claude Code 0.4+, Cursor, etc.)
Links
- Early Access / Waitlist — palveron.com/early-access
- Documentation — docs.palveron.com/integrations/mcp
- Dashboard — palveron.com
- Support — [email protected]
- GitHub — palveron/mcp-server
- Changelog — CHANGELOG.md
License
MIT — Copyright © 2026 Palveron.
Source: README.md at commit 536ec7d
Tools
0Version history
1- v1.0.1LatestSep 16, 2026
Score
50% of the applicable checks met
How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.
- Reached in the last 30 days25 pts
Keep the endpoint answering the MCP handshake; SourceWeft probes it every 30 days.
- Auth declared10 pts
Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.
- Tools listed15 pts
Answer tools/list without a credential, or ship a package that starts in a sandbox without one.
- DescriptionRequired15 pts
- Logo10 pts
- Documentation15 pts
- License10 pts
