protogrid

Search / one.secureai/redaction

redaction

R2· OAuth, once

Takes the people out of text before a model sees it, and puts them back in the reply.

v1.0.0 · 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.
Quality94strong
Trust93of 100
Uptime, 30 days99%
Latency p50581 ms

Connect

8 clients · secrets stay placeholders
{
  "mcpServers": {
    "redaction": {
      "type": "http",
      "url": "https://secureai.one/mcp",
      "headers": {
        "Authorization": "Bearer ${REDACTION_TOKEN}"
      }
    }
  }
}
claude mcp add --transport http redaction https://secureai.one/mcp --header "Authorization: Bearer ${REDACTION_TOKEN}"
[mcp_servers.redaction]
url = "https://secureai.one/mcp"
bearer_token_env_var = "REDACTION_TOKEN"
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "redaction": {
      "type": "remote",
      "url": "https://secureai.one/mcp",
      "enabled": true,
      "headers": {
        "Authorization": "Bearer {env:REDACTION_TOKEN}"
      }
    }
  }
}
{
  "mcpServers": {
    "redaction": {
      "type": "http",
      "url": "https://secureai.one/mcp",
      "headers": {
        "Authorization": "Bearer ${REDACTION_TOKEN}"
      }
    }
  },
  "deeplink": "cursor://anysphere.cursor-deeplink/mcp/install?name=redaction&config=eyJ0eXBlIjoiaHR0cCIsInVybCI6Imh0dHBzOi8vc2VjdXJlYWkub25lL21jcCIsImhlYWRlcnMiOnsiQXV0aG9yaXphdGlvbiI6IkJlYXJlciAke1JFREFDVElPTl9UT0tFTn0ifX0%3D"
}
{
  "servers": {
    "redaction": {
      "type": "http",
      "url": "https://secureai.one/mcp",
      "headers": {
        "Authorization": "Bearer ${REDACTION_TOKEN}"
      }
    }
  }
}
{
  "mcpServers": {
    "redaction": {
      "httpUrl": "https://secureai.one/mcp",
      "headers": {
        "Authorization": "Bearer ${REDACTION_TOKEN}"
      }
    }
  }
}
extensions:
  "redaction":
    enabled: true
    name: "redaction"
    type: streamable_http
    uri: "https://secureai.one/mcp"
    headers:
      "Authorization": "Bearer ${REDACTION_TOKEN}"
    timeout: 300

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

Quality 94 / 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 hygiene100 · weight 30
  • pass
    tools.descriptionsevery tool has a description
  • pass
    tools.description_lengthdescriptions are concise
  • pass
    tools.schemasevery tool has an object input schema
  • pass
    tools.annotations2 of 2 tools declare readOnlyHint or destructiveHint
  • pass
    tools.directory_hintsevery tool declares readOnlyHint, destructiveHint, idempotentHint and openWorldHint
  • pass
    tools.token_costabout 352 tokens to load every tool
  • pass
    tools.api_dumptools are not a one-to-one API dump
stabilityn/a · weight 15
  • n/a
    stability.changes, stability.rug_pulltool history not recorded yet
dependenciesn/a · weight 15
  • n/a
    deps.known_vulns, deps.mcp_sdk_version, deps.resolvableno npm or PyPI package

2 tools, about 352 tokens to load them all · checked 2026-10-20 08:26 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

provenance85
liveness100
freshness85
hygiene100

+repository +dns-namespace +website +reachable +uptime-99% ~updated-32d-ago

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

Endpoints

remoteauthreachableuptime 30dp50protocollast ok
https://secureai.one/mcp streamable-httpoauth2 AS: https://secureai.oneyes99%581 ms–2026-10-20

Tools (2)

redactread-onlyReplace the people in a piece of text — names, emails, phone numbers, addresses, card and account numbers — with plausible stand-ins, before the text is sent to a model or a third party. Returns the redacted text and a map. Keep the map: it is the only way to put the real values back, and it is not stored anywhere.
restoreread-onlyReverse a redaction using the map it returned. Use this on a model's reply so the reader sees what they actually wrote rather than the stand-ins.

Schemas: list_tools.

Similar MCP servers

Official server.json
{
  "name": "one.secureai/redaction",
  "$schema": "https://static.modelcontextprotocol.io/schemas/2025-09-29/server.schema.json",
  "remotes": [
    {
      "url": "https://secureai.one/mcp",
      "type": "streamable-http",
      "headers": [
        {
          "name": "Authorization",
          "isSecret": true,
          "isRequired": true,
          "description": "Bearer sai_... — a key from Settings → Developer at secureai.one"
        }
      ]
    }
  ],
  "version": "1.0.0",
  "repository": {
    "url": "https://github.com/secureaione-jpg/secure-ai-web",
    "source": "github"
  },
  "websiteUrl": "https://secureai.one/developers",
  "description": "Takes the people out of text before a model sees it, and puts them back in the reply."
}