github re-analysis due unconfirmed MCP

Wilkes-Liberty/mcp_sentinel

github

Enterprise governance for AI-agent access to Drupal — policy profiles, field redaction, DLP, tamper-evident audit logging, and HMAC webhooks over MCP / JSON:API / GraphQL.

maintainer
Wilkes-Liberty
license
first seen
2026-06-08
last seen
2026-06-15
releases · 30d
0
short id

Drift inferred · capture-to-capture

No drift recorded — single capability capture; advisories appear once its surface changes.

capabilities 3 tools
transport counts 3 tools · 0 res · 0 prompts permission surface via code analysis

tools

  • mcp_sentinel_approval

    Optional human-approval gate: queues governed destructive operations (bulk delete) as approval requests instead of executing them, for an authorized human to approve or deny. Depends only on mcp_senti

  • mcp_sentinel_graphql

    Extends governance to the GraphQL endpoint: gates mutations/reads, redacts fields, and audits operations for governed agents. Depends on graphql_compose.

  • mcp_sentinel_server

    Registers the Tool plugins with mcp_server (mcp_tool_config entities) and wires OAuth scopes. Provides drush mcp-sentinel:setup / :teardown. Depends on mcp_server_tool_bridge.

code evidence vHEAD · github-tarball
evidence-backed findings quoted directly from the published source artifact — not inferred

network 1

  • net Wilkes-Liberty-mcp_sentinel-f1b6a7b/js/dashboard.js :27 fetch(url, {