{
  "listings": [
    {
      "slug": "composio-rube",
      "name": "Composio (API + MCP)",
      "company": "Sampark Inc (d/b/a Composio)",
      "grade": "A",
      "fit": "caveat",
      "why": "Session config enables or disables toolkits and tools and sets require_approval by tool or by destructiveHint tag, and sessions are served over MCP. Description scanning wasn't found in the pages read, and acc-02 built its own gateway for finer permissions.",
      "source": "https://docs.composio.dev/docs/configuring-sessions.md",
      "confidence": "high",
      "url": "https://www.anchorterminal.com/tools/composio-rube"
    },
    {
      "slug": "mcp-gateway-parkkola",
      "name": "MCP Gateway",
      "company": "No legal entity found. COMMERCIAL.md, CLA.md and AUTHORSHIP.md name Mikko Parkkola, Finland, as licensor and author",
      "grade": "BB",
      "fit": "caveat",
      "why": "One endpoint with per-key tool allowlists, a tool-poisoning validator on every description, an injection and credential-redaction firewall, rug-pull pinning and budgets. No approval step before writes and no per-call log export were found.",
      "source": "https://github.com/MikkoParkkola/mcp-gateway/blob/main/README.md",
      "confidence": "medium",
      "url": "https://www.anchorterminal.com/tools/mcp-gateway-parkkola"
    },
    {
      "slug": "merge-agent-handler",
      "name": "Merge Agent Handler",
      "company": "Merge API, Inc.",
      "grade": "BB",
      "fit": "caveat",
      "why": "Tool access resolves per default, group and user, the Security Gateway scans every call's arguments to allow, redact or block, and logs export by API. No approval step before writes, and no scan of tool descriptions, was found.",
      "source": "https://docs.merge.dev/merge-agent-handler/administer/managing-tool-access.md",
      "confidence": "medium",
      "url": "https://www.anchorterminal.com/tools/merge-agent-handler"
    },
    {
      "slug": "one",
      "name": "One",
      "company": "One Systems, Inc.",
      "grade": "B",
      "fit": "caveat",
      "why": "Per-connection levels (read only, read and write, custom actions) are enforced on every call, execute_one_action is annotated destructive, and writes can ask first by MCP elicitation. No scan of tool descriptions or arguments was found.",
      "source": "https://www.withone.ai/docs/mcp/md",
      "confidence": "high",
      "url": "https://www.anchorterminal.com/tools/one"
    },
    {
      "slug": "stackone",
      "name": "StackOne",
      "company": "StackOne Technologies Limited",
      "grade": "B",
      "fit": "caveat",
      "why": "One MCP endpoint with Tool Policies that allow, mask fields or deny writes before the provider is called, Defender scanning responses for injection, PII redaction and request logs. Tool Policies are plan-gated and Defender scans responses, not descriptions.",
      "source": "https://docs.stackone.com/secure/policies.md",
      "confidence": "high",
      "url": "https://www.anchorterminal.com/tools/stackone"
    },
    {
      "slug": "zapier-mcp",
      "name": "Zapier MCP (agent actions)",
      "company": "Zapier Inc.",
      "grade": "C",
      "fit": "caveat",
      "why": "Separate read and write execute tools, account-level app and action restrictions, workspace task quotas and audit logs. Restrictions can't be set for MCP alone, and no description or argument scanning is documented.",
      "source": "https://docs.zapier.com/mcp/manage/security.md",
      "confidence": "high",
      "url": "https://www.anchorterminal.com/tools/zapier-mcp"
    },
    {
      "slug": "agentweb",
      "name": "AgentWeb",
      "company": "Agent Web Labs, Inc.",
      "grade": "D",
      "fit": "no",
      "why": "AgentWeb runs its own site maps; it isn't a gateway in front of a team's own MCP servers or tools.",
      "source": "https://docs.agentweb.us/mcp-apps.md",
      "confidence": "medium",
      "url": "https://www.anchorterminal.com/tools/agentweb"
    },
    {
      "slug": "letme",
      "name": "letme",
      "company": "Long Lunch Labs Limited (company number 17523112, registered in England and Wales, incorporated 15 October 2026), trading as Anchor Terminal and letme",
      "grade": "BB",
      "fit": "no",
      "why": "letme is not a gateway in front of a team's tools; it lists no tools per person and logs no tool calls.",
      "source": "https://letme.dev/llms.txt",
      "confidence": "medium",
      "selfAssessed": true,
      "url": "https://www.anchorterminal.com/tools/letme"
    },
    {
      "slug": "monid",
      "name": "Monid",
      "company": "Monid, Inc.",
      "grade": "C",
      "fit": "no",
      "why": "Monid brokers third-party data endpoints; it doesn't front a team's own tools or list tools per person.",
      "source": "https://monid.ai/llms.txt",
      "confidence": "medium",
      "url": "https://www.anchorterminal.com/tools/monid"
    },
    {
      "slug": "smithery",
      "name": "Smithery",
      "company": "Clavia, Inc. (doing business as Smithery)",
      "grade": "F",
      "fit": "no",
      "why": "The proxy is gone, and acc-11 found 22 of 100 registry servers with unsafe tool descriptions when it ran.",
      "source": "https://smithery.ai/",
      "confidence": "high",
      "url": "https://www.anchorterminal.com/tools/smithery"
    },
    {
      "slug": "unified-to-mcp",
      "name": "Unified.to MCP Server",
      "company": "Unified API Inc.",
      "grade": "B",
      "fit": "no",
      "why": "One MCP URL per customer connection with tool filters and hide_sensitive for PII; it is not a single governed entry for staff agents, and no write approval or description scanning is documented.",
      "source": "https://docs.unified.to/mcp/server-options.md",
      "confidence": "high",
      "url": "https://www.anchorterminal.com/tools/unified-to-mcp"
    }
  ],
  "marks": "yes: the docs show it does the job as the success test says. caveat: it does the job with a limit an agent should know. no: it doesn't do this job. unchecked: we couldn't read it.",
  "meta": {
    "attribution": "Anchor Terminal (https://www.anchorterminal.com)",
    "attributionRequired": true,
    "credit": "CC BY 4.0, credit Anchor Terminal and link the page or API address you took it from (https://www.anchorterminal.com/terms/#data)",
    "docs": "https://www.anchorterminal.com/docs/",
    "generatedAt": "2026-11-16",
    "license": "CC-BY-4.0",
    "method": "https://www.anchorterminal.com/benchmark/",
    "methodology": "0.8",
    "openapi": "https://www.anchorterminal.com/openapi.json",
    "preview": false,
    "run": "2026-10-01",
    "runLabel": "October 2026 research run",
    "terms": "https://www.anchorterminal.com/terms/#data"
  },
  "useCase": {
    "accounts": 4,
    "after": [
      "agent-observability.trace"
    ],
    "area": "business",
    "asks": [
      "give the team's agents GitHub and Datadog",
      "only allow read tools",
      "block secrets leaving in tool calls"
    ],
    "before": [],
    "blockers": [
      "no per-call outbound authorisation from a sandbox",
      "registry servers with unsafe descriptions"
    ],
    "capabilities": [
      "agent.tools",
      "auth.audit",
      "agent.mcp-client"
    ],
    "category": "aggregator",
    "categoryName": "Agent tool access",
    "checked": "2026-11-15",
    "companies": {
      "fit": 0,
      "fitWithLimit": 6,
      "tagged": 127
    },
    "competition": "none",
    "fits": null,
    "fitsWithLimit": [
      "composio-rube",
      "mcp-gateway-parkkola",
      "merge-agent-handler",
      "one",
      "stackone",
      "zapier-mcp"
    ],
    "id": "aggregator.governed-gateway",
    "listings": {
      "caveat": 6,
      "no": 5,
      "notRead": 1,
      "tagged": 141,
      "unchecked": 0,
      "yes": 0
    },
    "name": "Give staff agents one governed entry to many tools",
    "status": "draft",
    "success": "One MCP endpoint that lists only allowed tools per agent or person, blocks or asks before writes, scans tool descriptions and arguments, and logs each call.",
    "url": "https://www.anchorterminal.com/api/v1/use-cases/aggregator.governed-gateway.json",
    "weight": 11,
    "weightBasis": "4 of 32 accounts (HN gateway users and a registry scan)"
  }
}
