# ai.tigertiger/tigertiger

> Chief of Staff, strategy and writing tools that give your Claude subscription structure and memory.

- name: ai.tigertiger/tigertiger
- version: 1.0.0
- connection class: R1 (autonomous)
- trust: 83/100 flags: no-repository
- quality: 79/100 (good)
- owner: not claimed
- descriptor: https://api.protogrid.dev/v1/servers/ai.tigertiger%2Ftigertiger
- tools: https://api.protogrid.dev/v1/servers/ai.tigertiger%2Ftigertiger/tools

**An agent can connect on its own if it already holds `TIGERTIGER_TOKEN`.** Remote endpoint behind a static API key or header. The registry never sees the value; the agent fills the placeholder.

## Connection (mcpServers)

```json
{
  "mcpServers": {
    "tigertiger": {
      "type": "http",
      "url": "https://mcp.tigertiger.ai/mcp",
      "headers": {
        "Authorization": "Bearer ${TIGERTIGER_TOKEN}"
      }
    }
  }
}
```

Placeholders to fill: `${TIGERTIGER_TOKEN}`.

## Trust

- hygiene: 80
- liveness: 100
- freshness: 100
- provenance: 55
- drivers: +dns-namespace +website +reachable +uptime-100% +updated-16d-ago -no-repository
- Derived from observable signals (official registry feed and our own credential-free probes); no code audit performed.

## Quality 79/100 (good)

### protocol: 75 (weight 25)

- warn `protocol.modern`: newest supported version is 2025-11-25; 2026-07-28 not supported, older versions are deprecated until 2027-07-28
- n/a `protocol.stateless`: only applies to 2026-07-28 servers
- pass `protocol.transport`: streamable HTTP
- n/a `protocol.list_ttl`: only applies to 2026-07-28 servers

### authorization: n/a (weight 15)

- n/a `auth.prm`, `auth.as_metadata`, `auth.cimd`: no remote uses OAuth
- n/a `auth.secret_in_url`: no templated URL

### tool hygiene: 71 (weight 30)

- pass `tools.descriptions`: every tool has a description
- pass `tools.description_length`: descriptions are concise
- pass `tools.schemas`: every tool has an object input schema
- fail `tools.annotations`: no tool declares readOnlyHint or destructiveHint, so clients cannot tell safe calls from risky ones
- fail `tools.directory_hints`: no tool declares all four of readOnlyHint, destructiveHint, idempotentHint and openWorldHint; missing: forum_update (readOnlyHint, destructiveHint, idempotentHint, openWorldHint); help (readOnlyHint, destructiveHint, idempotentHint, openWorldHint); upgrade_link (readOnlyHint, destructiveHint, idempotentHint, openWorldHint); …
- pass `tools.token_cost`: about 673 tokens to load every tool
- pass `tools.api_dump`: tools are not a one-to-one API dump

### stability: 100 (weight 15)

- pass `stability.changes`: no tool changes in 30 days
- pass `stability.rug_pull`: no tool changed its meaning under the same name

### dependencies: n/a (weight 15)

- n/a `deps.known_vulns`, `deps.mcp_sdk_version`, `deps.resolvable`: no npm or PyPI package

- tools: 7, about 673 tokens to load them all
- tool set hash: 4eecf9754ce8a1eeae82ae42748adaff
- badge: [![protogrid quality](https://protogrid.dev/badge/ai.tigertiger/tigertiger.svg)](https://protogrid.dev/servers/ai.tigertiger/tigertiger)
- Checks run on what our credential-free, read-only probes observe; tools are never called and no code audit is performed.

### Tool changes

_No tool definition changes recorded._

## Remotes

- https://mcp.tigertiger.ai/mcp (streamable-http, auth api_key ${TIGERTIGER_TOKEN}, reachable true, uptime30d 1)

## Packages

_none_

## Tools (7)

- `capabilities`: Show everything on the user's TigerTiger plan — tools, trigger phrases, and how sessions work.
    Preferred over cos.help() for plan-wide questions.
    Triggers on: "what can you do", "what can TigerTiger do", "what's on my plan",
    "how do I use this", "help me get started", "what are my tools".
    This tool is ungated — it works for all users including Free (vault-only).
    
- `forum_update`: Prepare a monthly EO Forum 5% reflections update through a guided interview.
    Walks through Work, Family, and Personal categories to extract feelings, headlines, and significance.

    Args:
        context: Optional — notes on the forum type (Forum E or ABF) or month. Leave empty to have the agent ask.
    
- `help`: List the specific work modes available in the TigerTiger Chief of Staff MCP.
    Only call this when the user is explicitly asking what the Chief of Staff tool
    can do — e.g. 'what does tiger-cos do?', 'what Chief of Staff modes are there?',
    'what can the Chief of Staff help with?'. Do NOT call this for general Claude
    capability questions.
- `list_skills`: Show all TigerTiger skills available on the user's plan, grouped by pack.
    Each skill includes when to use it and an exact phrase to try.
    This tool is ungated — works for all users including Free (vault-only).
    Triggers on: "list skills", "what skills do I have", "show me what I can do",
    "skill list", "what can I use", "show my skills".
    
- `my_account`: Show account info: plan, seats, and users on the account.
    This tool is ungated — it works for all users including Free, matching
    capabilities()'s pattern (friendly response if the key isn't recognized).
    Triggers on: "what's my plan", "my account", "my subscription", "account info".
    
- `strategy_map_help`: List the modes available in the TigerTiger Strategy Map.
- `upgrade_link`: Get a Stripe Checkout link to upgrade to Pro. Returns a URL only —
    never charges directly. The customer must open the link and confirm the
    purchase themselves.

    Args:
        plan: Billing interval — "monthly" or "annual" (default "monthly").