protogrid

Search / ai.agentplaybooks/agentplaybooks

AgentPlaybooks

R2· OAuth, once

Vendor-neutral home for portable agents: skills, MCP tools, memory, canvas, and secret proxy.

v0.10.0 · 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.
Quality83good
Trust95of 100
Uptime, 30 days96%
Latency p50618 ms

Connect

8 clients · secrets stay placeholders
{
  "mcpServers": {
    "agentplaybooks": {
      "type": "http",
      "url": "https://agentplaybooks.ai/api/mcp/manage",
      "headers": {
        "Authorization": "Bearer ${AGENTPLAYBOOKS_TOKEN}"
      }
    }
  }
}
claude mcp add --transport http agentplaybooks https://agentplaybooks.ai/api/mcp/manage --header "Authorization: Bearer ${AGENTPLAYBOOKS_TOKEN}"
[mcp_servers.agentplaybooks]
url = "https://agentplaybooks.ai/api/mcp/manage"
bearer_token_env_var = "AGENTPLAYBOOKS_TOKEN"
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "agentplaybooks": {
      "type": "remote",
      "url": "https://agentplaybooks.ai/api/mcp/manage",
      "enabled": true,
      "headers": {
        "Authorization": "Bearer {env:AGENTPLAYBOOKS_TOKEN}"
      }
    }
  }
}
{
  "mcpServers": {
    "agentplaybooks": {
      "type": "http",
      "url": "https://agentplaybooks.ai/api/mcp/manage",
      "headers": {
        "Authorization": "Bearer ${AGENTPLAYBOOKS_TOKEN}"
      }
    }
  },
  "deeplink": "cursor://anysphere.cursor-deeplink/mcp/install?name=agentplaybooks&config=eyJ0eXBlIjoiaHR0cCIsInVybCI6Imh0dHBzOi8vYWdlbnRwbGF5Ym9va3MuYWkvYXBpL21jcC9tYW5hZ2UiLCJoZWFkZXJzIjp7IkF1dGhvcml6YXRpb24iOiJCZWFyZXIgJHtBR0VOVFBMQVlCT09LU19UT0tFTn0ifX0%3D"
}
{
  "servers": {
    "agentplaybooks": {
      "type": "http",
      "url": "https://agentplaybooks.ai/api/mcp/manage",
      "headers": {
        "Authorization": "Bearer ${AGENTPLAYBOOKS_TOKEN}"
      }
    }
  }
}
{
  "mcpServers": {
    "agentplaybooks": {
      "httpUrl": "https://agentplaybooks.ai/api/mcp/manage",
      "headers": {
        "Authorization": "Bearer ${AGENTPLAYBOOKS_TOKEN}"
      }
    }
  }
}
extensions:
  "agentplaybooks":
    enabled: true
    name: "agentplaybooks"
    type: streamable_http
    uri: "https://agentplaybooks.ai/api/mcp/manage"
    headers:
      "Authorization": "Bearer ${AGENTPLAYBOOKS_TOKEN}"
    timeout: 300

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

Quality 83 / 100good

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
dependenciesn/a · weight 15
  • n/a
    deps.known_vulns, deps.mcp_sdk_version, deps.resolvableno npm or PyPI package

Tool list unknown · checked 2026-11-07 17:28 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 95 / 100

provenance85
liveness98
freshness100
hygiene100

+repository +dns-namespace +website +reachable +uptime-96% +updated-7d-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://agentplaybooks.ai/api/mcp/manage streamable-httpoauth2 AS: https://zcphxfospbvqplonkvco.supabase.co/auth/v1yes96%618 ms–2026-11-07

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.agentplaybooks/agentplaybooks",
  "icons": [
    {
      "src": "https://agentplaybooks.ai/icon.svg",
      "sizes": [
        "any"
      ],
      "mimeType": "image/svg+xml"
    }
  ],
  "title": "AgentPlaybooks",
  "$schema": "https://static.modelcontextprotocol.io/schemas/2025-12-11/server.schema.json",
  "remotes": [
    {
      "url": "https://agentplaybooks.ai/api/mcp/manage",
      "type": "streamable-http",
      "headers": [
        {
          "name": "Authorization",
          "isSecret": true,
          "description": "Optional. OAuth 2.1 with PKCE is the default: an OAuth-capable client gets a 401 with a resource_metadata challenge and signs in through the browser. Set this only for headless use, as a Bearer AgentPlaybooks user API key (for example: Bearer apb_live_...)."
        }
      ]
    }
  ],
  "version": "0.10.0",
  "repository": {
    "url": "https://github.com/matebenyovszky/agentplaybooks",
    "source": "github"
  },
  "websiteUrl": "https://agentplaybooks.ai",
  "description": "Vendor-neutral home for portable agents: skills, MCP tools, memory, canvas, and secret proxy."
}