check_approval

10 registry entries were observed exposing a tool named check_approval — none of them flagged as a privileged capability.

Every row is point-in-time scan output, dated below. Forge has an observed tool surface for 12,342 of 40,590 scannable entries (30%) — an entry that has not been scanned cannot appear here, so absence from this list is not evidence that an entry does not expose this tool.

  1. midplaneMCPattestedtrust 85/100 · A
    v0.20.0
    ↓ 223/wk

    Safe-by-default SQL guardrails for AI agents. MCP server for Postgres over stdio + Streamable HTTP: parses every statement with a real SQL AST, enforces a per-table access policy, and audits before the query runs.

    ClaudeCursorCopilotGemini
    UnknownMIT1mo agonpmGitHubobserved · static extraction
    mcpmodelcontextprotocolpostgressqlai-agentsguardrails
  2. @sendinel/mcp-serverMCPcommunitylivetrust 60/100 · B
    v1.0.26
    ↓ 2k/wk

    AI-controlled email operations control plane for campaigns, contacts, segments, analytics, and multi-provider sending via MCP.

    ClaudeCursorCopilotChatGPTGemini
    UnknownUNLICENSED16d agonpmGitHubobserved · static extraction
    mcpmodel-context-protocolsendinelemailclaudecursor
  3. @vibeads/mcpMCPcommunitytrust 60/100 · B
    v0.2.26
    ↓ 2k/wk
    ★ 1

    Manage Google Ads from Claude: read metrics, draft campaigns, publish with human approval.

    ClaudeCursorCopilotGemini
    io.github.vibeadsMIT2d agonpmGitHubobserved · static extraction
    mcp
  4. shrike-mcpMCPcommunitytrust 60/100 · B
    v4.1.0
    ↓ 160/wk
    ★ 2

    MCP server for action governance on AI agents — 14 tools that govern tool calls, SQL queries, file writes, shell commands, and agent-to-agent messages server-side, before execution. Allow / approve / block. Session correlation. Works with Claude Desktop,

    ClaudeCursorCopilotGemini
    Shrike SecurityApache-2.010d agonpmGitHubobserved · static extraction
    action-governanceai-agentsagent-governanceagent-securitymcpmcp-server
  5. io.github.Shrike-Security/shrike-mcpMCPcommunitytrust 60/100 · B
    v1.1.1
    ★ 2

    AI agent security scanner — prompt injection detection, SQL injection, PII isolation, threat intel.

    ClaudeCursorCopilotGemini
    io.github.Shrike-SecurityUnknown8mo agonpmGitHubobserved · static extraction
    mcp
  6. @looppause/mcpMCPcommunitytrust 60/100 · B
    v0.2.1

    LoopPause MCP server — pause agent execution and route human approval requests

    ClaudeCursorCopilotGemini
    io.github.soteeabamUnknown2mo agonpmGitHubobserved · static extraction
    mcp
  7. com.scrubmytext/toolsMCPcommunitylivetrust 60/100 · B
    v7.5.0

    49 deterministic tools for text integrity, agent control, and contextual quality evidence.

    ClaudeCursorCopilotChatGPTGemini
    com.scrubmytextUnknown1mo agoobserved · live tools/list
    mcp
  8. dev.gvnr/gvnrMCPcommunitylivetrust 60/100 · B
    v1.8.1

    Budget & cost control for AI agents — per-agent spend caps + rate limits before each call.

    ClaudeCursorCopilotChatGPTGemini
    dev.gvnrUnknown4mo agoGitHubobserved · static extraction
    mcp
  9. eu.zenvault/zenvaultMCPcommunitylivetrust 60/100 · B
    v1.0.2

    Wake-ups, webhook inboxes, TTL memory, watches and human approval for agents. Paid per call.

    ClaudeCursorCopilotChatGPTGemini
    eu.zenvaultUnknown2mo agoobserved · live tools/list
    mcp
  10. net.glyt/glytMCPcommunitylivetrust 60/100 · B
    v0.1.0

    Human-in-the-loop approval for agent actions, with verifiable action-bound receipts.

    ClaudeCursorCopilotChatGPTGemini
    net.glytUnknown3mo agoobserved · live tools/list
    mcp

All indexed toolsSearch the registry for check_approval