ApprovalLens
Provides an optional hosted 'second opinion' review of agent file operations using NVIDIA Nemotron through Nebius Token Factory, returning validated advisory findings that inform the human approval decision but can never override policy or authorize execution.
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.
ApprovalLens — proof before permission
A Cursor extension that checks supported agent file operations against developer-owned rules, gathers evidence, and holds sensitive operations for human approval. NVIDIA Nemotron through Nebius Token Factory provides an optional hosted second opinion. A model cannot override policy or authorize execution.
Install from Open VSX · Website · Setup guide · Judge walkthrough · Release downloads
Start in Cursor
Install ApprovalLens 0.7.1 or newer. If the registry still shows an older version, install the 0.7.1 VSIX from GitHub Releases. Open one trusted local project on macOS or Linux.
Run ApprovalLens: Enable for this workspace and confirm. The extension bundles the companion and installs project hooks, an editable rules file, and the public MCP configuration. No separate Node installation, clone, or terminal service is required.
Edit
.approvallens/rules.json, then run ApprovalLens: Apply rules. The starter permits only readingpackage.json. Exact path grants are intentional; unsupported operations are denied.Use a supported native Read, whole-file Write, or Delete. Ordinary permitted reads pass locally; eligible mutations wait for your decision. Activity is grouped by chat.
For Nemotron findings, run ApprovalLens: Connect hosted review with a privately supplied pilot credential. The token goes into editor SecretStorage. Anonymous installs work in rules-only mode; the owner configures capped or uncapped authenticated testing.
Cursor may ask you to enable the configured MCP or start a new chat. Disable the workspace integration before uninstalling the extension so owned hooks are removed.
Related MCP server: @palveron/mcp-server
How it works
Cursor preToolUse → bundled local companion → applied policy + observed file evidence
↓ eligible LIVE review
hosted MCP → Nebius Nemotron
↓ validated findings
human decision ← extension dialog
↓ recheck file state
allow or deny the waiting native callHard policy violations and incomplete evidence stop locally. Rules-only reviews explicitly say no model ran. The hosted server returns advisory findings, never an execution grant. The independent public MCP sample uses synthetic files and cannot inspect your workspace.
Boundaries
This is a restrictive development beta, not a universal agent firewall. Supported adapters cover Read/whole-file Write/Delete. Selected literal read-only shell commands are available through opt-in shell inspection. Patches and other unsupported hook-delivered calls are denied. Built-in search may not deliver compatible hooks and therefore cannot be promised interception or logging. No separate small-model classifier exists: routing is deterministic. Single local folder only; Windows, remote workspaces and multi-root are not supported by bundled onboarding.
The applied rules snapshot lives outside the repository. Changes to the editable file require explicit application. Supported agent writes to ApprovalLens and Cursor security configuration are blocked. This is not an OS sandbox or protection against another process running as your user.
Repository map
Location | Responsibility |
| Shared analysis, evidence and review validation |
| Policy, reviewer, MCP transports and hosted-review client |
| Native hook controller, local decisions and persistence |
| Cursor commands, bundled setup, chat activity and approval UI |
| Product site, guide and Vercel MCP route |
| Policy, transport, lifecycle and integration regressions |
| Build, package, development services and demonstrations |
| Synthetic policies and reproducible scenarios |
Develop
Node 24+ is required for repository development, not for installed extension users.
npm ci
npm run typecheck
npm test
npm run build
npm run extension:packageThe package command bundles the companion, policy parser and hook. Install the generated VSIX in a disposable project to verify actual editor behavior. See contributor guide for ownership and validation, architecture for trust boundaries, deployment for secrets and publishing, and plan for outstanding work.
Evidence and license
Automated functional tests do not establish benchmark accuracy. Verification status and remaining external dependencies are recorded in release status. Original research provenance is in provenance. MIT licensed; see LICENSE.
Shell and data checks
Version 0.7.1 adds opt-in read-only shell pipelines, command lists and argument checks, plus sensitive-data inspection before supported reads and remote review transmission. See shell and egress for exact coverage. Follow the setup guide for practical verification cases; the judge walkthrough is separate.
This server cannot be deployed
Maintenance
Related MCP Connectors
Human-in-the-loop review and approval for AI agents. Audit trail, approval policies, native MCP.
Pre-execution governance for AI agents. Deterministic PASS/FAIL/REVIEW verdicts, replayable proof.
Zero-secret MCP gateway for AI agents: risk-scored, audited calls with human-in-the-loop approval.
Human-in-the-loop for AI agents over MCP: durable approvals with a hosted review page & audit trail
Related MCP Servers
- FlicenseNot gradedqualityDmaintenanceWraps your existing MCP servers and checks each tool call against policy and live state before it runs. Allow, block, or require a refresh, with a reason the agent can act on.5-
- AlicenseAqualityCmaintenanceProvides advisory AI-governance checks for MCP hosts and coding agents, enabling policy verdicts, PII masking, and audit traces before executing tool calls.395 npmMIT
- AlicenseNot gradedqualityCmaintenanceProvides a human-in-the-loop approval gateway for AI agents, enforcing policies and audit logging for MCP-compatible tool calls.Apache 2.0

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.12 npmMIT