protogrid

Search / io.github.Guruprasath-Annadurai/whitepact

WhitePact

R2· OAuth, once

AI governance MCP server: trust scoring, guardrails, bias/hallucination detection, compliance.

v1.2.3 · active · repository · website · descriptor JSON · versions

An agent can connect after a one-time OAuth consent by a human.Remote endpoint behind OAuth 2. Tokens stay with the agent; the registry only exposes the authorization metadata.
Quality92strong
Trust93of 100
Uptime, 30 days93%
Latency p50362 ms

Connect

8 clients · secrets stay placeholders
{
  "mcpServers": {
    "whitepact": {
      "type": "http",
      "url": "https://whitepact-mcp-http.onrender.com/mcp",
      "headers": {
        "Authorization": "Bearer ${WHITEPACT_TOKEN}"
      }
    }
  }
}
claude mcp add --transport http whitepact https://whitepact-mcp-http.onrender.com/mcp --header "Authorization: Bearer ${WHITEPACT_TOKEN}"
[mcp_servers.whitepact]
url = "https://whitepact-mcp-http.onrender.com/mcp"
bearer_token_env_var = "WHITEPACT_TOKEN"
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "whitepact": {
      "type": "remote",
      "url": "https://whitepact-mcp-http.onrender.com/mcp",
      "enabled": true,
      "headers": {
        "Authorization": "Bearer {env:WHITEPACT_TOKEN}"
      }
    }
  }
}
{
  "mcpServers": {
    "whitepact": {
      "type": "http",
      "url": "https://whitepact-mcp-http.onrender.com/mcp",
      "headers": {
        "Authorization": "Bearer ${WHITEPACT_TOKEN}"
      }
    }
  },
  "deeplink": "cursor://anysphere.cursor-deeplink/mcp/install?name=whitepact&config=eyJ0eXBlIjoiaHR0cCIsInVybCI6Imh0dHBzOi8vd2hpdGVwYWN0LW1jcC1odHRwLm9ucmVuZGVyLmNvbS9tY3AiLCJoZWFkZXJzIjp7IkF1dGhvcml6YXRpb24iOiJCZWFyZXIgJHtXSElURVBBQ1RfVE9LRU59In19"
}
{
  "servers": {
    "whitepact": {
      "type": "http",
      "url": "https://whitepact-mcp-http.onrender.com/mcp",
      "headers": {
        "Authorization": "Bearer ${WHITEPACT_TOKEN}"
      }
    }
  }
}
{
  "mcpServers": {
    "whitepact": {
      "httpUrl": "https://whitepact-mcp-http.onrender.com/mcp",
      "headers": {
        "Authorization": "Bearer ${WHITEPACT_TOKEN}"
      }
    }
  }
}
extensions:
  "whitepact":
    enabled: true
    name: "whitepact"
    type: streamable_http
    uri: "https://whitepact-mcp-http.onrender.com/mcp"
    headers:
      "Authorization": "Bearer ${WHITEPACT_TOKEN}"
    timeout: 300

Placeholders to fill from your own secret store: ${WHITEPACT_TOKEN}. The registry never accepts secret values.

Quality 92 / 100strong

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)
authorization83 · weight 15
  • pass
    auth.prmProtected Resource Metadata (RFC 9728) published
  • pass
    auth.as_metadataauthorization server metadata reachable
  • warn
    auth.cimdonly Dynamic Client Registration, deprecated in 2026-07-28 in favour of CIMD
  • 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
dependencies100 · weight 15
  • pass
    deps.known_vulnsno known advisory in 41 resolved packages
  • pass
    deps.mcp_sdk_versionmcp 1.30.0, no known advisory
  • pass
    deps.resolvable[email protected] resolved: 41 packages

Tool list unknown · checked 2026-10-20 18:06 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 93 / 100

provenance90
liveness97
freshness85
hygiene100

+repository +namespace-matches-repo +website +reachable +uptime-93% ~updated-69d-ago

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

Dependencies

[email protected] PyPI40 dependencies, resolved · MCP SDK mcp 1.30.0 · advisories checked 2026-10-19

No known advisory affects this dependency graph.

Dependency graphs from deps.dev; advisories from OSV.dev, including the GitHub Advisory Database and the PyPI Advisory Database; all CC BY 4.0. The graph is what a clean install of this version resolves today; nothing was installed or run. How it is checked.

Endpoints

remoteauthreachableuptime 30dp50protocollast ok
https://whitepact-mcp-http.onrender.com/mcp streamable-httpoauth2 AS: https://whitepact-mcp-http.onrender.comyes93%362 ms–2026-10-20
https://whitepact-mcp-http.onrender.com/sse sseoauth2 AS: https://whitepact-mcp-http.onrender.comyes93%346 ms–2026-10-20
packageregistryversionruntimesecrets
rai-governance-platformpypi1.2.2uvx

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": "io.github.Guruprasath-Annadurai/whitepact",
  "_meta": {
    "io.modelcontextprotocol.registry/publisher-provided": {
      "license": "MIT",
      "tool_count": 27,
      "resource_note": "Canonical resources are served under both whitepact:// and rai:// URI schemes (dual-scheme, see MIGRATION_WHITEPACT_V2.md Section 6) — 20 is the advertised count over the wire, 10 is the count of distinct underlying resources.",
      "resource_count_canonical": 10,
      "governance_decision_model": [
        "ALLOW",
        "ALLOW_WITH_REDACTION",
        "REQUIRE_APPROVAL",
        "DENY",
        "QUARANTINE"
      ],
      "resource_count_advertised": 20
    }
  },
  "title": "WhitePact",
  "$schema": "https://static.modelcontextprotocol.io/schemas/2025-12-11/server.schema.json",
  "remotes": [
    {
      "url": "https://whitepact-mcp-http.onrender.com/mcp",
      "type": "streamable-http",
      "headers": [
        {
          "name": "Authorization",
          "isSecret": true,
          "isRequired": true,
          "description": "Bearer API key for the hosted WhitePact MCP server. Obtain one from the WhitePact dashboard (Settings → API Keys) after creating a free org.",
          "placeholder": "Bearer <your-api-key>"
        }
      ]
    },
    {
      "url": "https://whitepact-mcp-http.onrender.com/sse",
      "type": "sse",
      "headers": [
        {
          "name": "Authorization",
          "isSecret": true,
          "isRequired": true,
          "description": "Bearer API key for the hosted WhitePact MCP server. Obtain one from the WhitePact dashboard (Settings → API Keys) after creating a free org.",
          "placeholder": "Bearer <your-api-key>"
        }
      ]
    }
  ],
  "version": "1.2.3",
  "packages": [
    {
      "version": "1.2.2",
      "transport": {
        "type": "stdio"
      },
      "identifier": "rai-governance-platform",
      "runtimeHint": "uvx",
      "registryType": "pypi",
      "registryBaseUrl": "https://pypi.org",
      "packageArguments": [
        {
          "type": "positional",
          "value": "whitepact-mcp",
          "description": "Console script to run (stdio transport, self-hosted, free, unrestricted). The legacy name `responsibleai-mcp` launches the identical process; see MIGRATION_WHITEPACT_V2.md Section 4."
        }
      ],
      "runtimeArguments": [
        {
          "name": "--from",
          "type": "named",
          "value": "rai-governance-platform",
          "description": "PyPI project name (distinct from the console script invoked below — see packageArguments)."
        }
      ],
      "environmentVariables": [
        {
          "name": "RAI_MCP_LOG_LEVEL",
          "default": "WARNING",
          "description": "Logging level: DEBUG | INFO | WARNING."
        }
      ]
    }
  ],
  "repository": {
    "url": "https://github.com/Guruprasath-Annadurai/Whitepact",
    "source": "github"
  },
  "websiteUrl": "https://github.com/Guruprasath-Annadurai/Whitepact",
  "description": "AI governance MCP server: trust scoring, guardrails, bias/hallucination detection, compliance."
}