Connect

8 clients · secrets stay placeholders

JSON (mcpServers)Claude CodeCodexOpenCodeCursorVS CodeGemini CLIGoose

{
  "mcpServers": {
    "penholder": {
      "type": "http",
      "url": "https://api.penholder.ai/mcp"
    }
  }
}

claude mcp add --transport http penholder https://api.penholder.ai/mcp

[mcp_servers.penholder]
url = "https://api.penholder.ai/mcp"

{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "penholder": {
      "type": "remote",
      "url": "https://api.penholder.ai/mcp",
      "enabled": true
    }
  }
}

{
  "mcpServers": {
    "penholder": {
      "type": "http",
      "url": "https://api.penholder.ai/mcp"
    }
  },
  "deeplink": "cursor://anysphere.cursor-deeplink/mcp/install?name=penholder&config=eyJ0eXBlIjoiaHR0cCIsInVybCI6Imh0dHBzOi8vYXBpLnBlbmhvbGRlci5haS9tY3AifQ%3D%3D"
}

{
  "servers": {
    "penholder": {
      "type": "http",
      "url": "https://api.penholder.ai/mcp"
    }
  }
}

{
  "mcpServers": {
    "penholder": {
      "httpUrl": "https://api.penholder.ai/mcp"
    }
  }
}

extensions:
  "penholder":
    enabled: true
    name: "penholder"
    type: streamable_http
    uri: "https://api.penholder.ai/mcp"
    timeout: 300

Quality – / 100not scored

Not scored: fewer than three checks apply, usually because no remote answered a credential-free probe or the server is a local package.

protocoln/a · weight 25

n/a
protocol.modern, protocol.stateless, protocol.transport, protocol.list_ttlno remote answered a protocol handshake (not probed yet, unreachable, or local-only)

authorizationn/a · weight 15

n/a
auth.prm, auth.as_metadata, auth.cimdno remote uses OAuth
n/a
auth.secret_in_urlno templated URL

tool hygienen/a · weight 30

n/a
tools.descriptions, tools.description_length, tools.schemas, tools.annotations, tools.directory_hints, tools.token_cost, tools.api_dumptool list unknown (behind auth, not probed, or empty)

stabilityn/a · weight 15

n/a
stability.changes, stability.rug_pulltool list unknown

dependenciesn/a · weight 15

n/a
deps.known_vulns, deps.mcp_sdk_version, deps.resolvableno npm or PyPI package

Tool list unknown · checked 2026-10-19 10:52 UTC

Tool changes

No tool definition changes recorded. A server's first observation is its baseline; later probes record what changes.

Checks run on what our credential-free, read-only probes observe; tools are never called and no code audit is performed. How it is computed.

Trust 50 / 100

no-repositoryunreachable

provenance55

liveness0

freshness85

hygiene80

+dns-namespace +website -unreachable(13 failures) ~updated-63d-ago -no-repository

Derived from observable signals (official registry feed and our own credential-free probes); no code audit performed. How it is computed.

Endpoints

remote	auth	reachable	uptime 30d	p50	protocol	last ok
`https://api.penholder.ai/mcp` streamable-http	unknown	no (13 failures)	0%	–	–	–

Tools (0)

No tools observed. Tools appear once a credential-free probe can list them.

Schemas: list_tools.

Similar MCP servers

Official server.json

{
  "name": "ai.penholder/penholder",
  "_meta": {
    "io.modelcontextprotocol.registry/publisher-provided": {
      "tagline": "Preventive human-approval write-gate for AI agents: intercepts an agent write to a system of record as a durable PENDING proposal that commits only after a human approves; fail-closed on conflict, with tamper-evident (hash-chained) provenance.",
      "referenceArticle": "https://penholder.ai/preventive-vs-reactive-ai-agent-governance.html"
    }
  },
  "$schema": "https://static.modelcontextprotocol.io/schemas/2025-12-11/server.schema.json",
  "remotes": [
    {
      "url": "https://api.penholder.ai/mcp",
      "type": "streamable-http"
    }
  ],
  "version": "1.0.0",
  "websiteUrl": "https://penholder.ai",
  "description": "Preventive human-approval write-gate for AI agents: writes commit only after a human approves."
}