# Fiskmas

> Hosting for AI agents: your AI client deploys Docker apps to live HTTPS URLs over MCP.

- name: dev.fiskmas/fiskmas
- version: 1.0.0
- connection class: R1 (autonomous)
- trust: 77/100 flags: no-repository
- quality: 69/100 (needs work)
- owner: not claimed
- descriptor: https://api.protogrid.dev/v1/servers/dev.fiskmas%2Ffiskmas
- tools: https://api.protogrid.dev/v1/servers/dev.fiskmas%2Ffiskmas/tools

**An agent can connect on its own if it already holds `FISKMAS_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": {
    "fiskmas": {
      "type": "http",
      "url": "https://mcp.fiskmas.dev/mcp",
      "headers": {
        "Authorization": "Bearer ${FISKMAS_TOKEN}"
      }
    }
  }
}
```

Placeholders to fill: `${FISKMAS_TOKEN}`.

## Trust

- hygiene: 80
- liveness: 100
- freshness: 85
- provenance: 45
- drivers: +dns-namespace +reachable +uptime-100% ~updated-35d-ago -no-repository
- Derived from observable signals (official registry feed and our own credential-free probes); no code audit performed.

## Quality 69/100 (needs work)

### 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: 86 (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
- pass `tools.annotations`: 21 of 21 tools declare readOnlyHint or destructiveHint
- fail `tools.directory_hints`: no tool declares all four of readOnlyHint, destructiveHint, idempotentHint and openWorldHint; missing: list_projects (destructiveHint, idempotentHint, openWorldHint); create_account (destructiveHint, idempotentHint, openWorldHint); deploy_project (destructiveHint, idempotentHint, openWorldHint); …
- pass `tools.token_cost`: about 2,034 tokens to load every tool
- pass `tools.api_dump`: tools are not a one-to-one API dump

### stability: 25 (weight 15)

- warn `stability.changes`: 8 tool changes in 30 days
- fail `stability.rug_pull`: 3 tools kept their name but changed most of their description in 30 days; review before trusting them

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

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

- tools: 21, about 2,034 tokens to load them all
- tool set hash: cb6b6bfc6cf551b2e019958723e05996
- tools last changed: 2026-10-11T09:45:08.432Z
- badge: [![protogrid quality](https://protogrid.dev/badge/dev.fiskmas/fiskmas.svg)](https://protogrid.dev/servers/dev.fiskmas/fiskmas)
- Checks run on what our credential-free, read-only probes observe; tools are never called and no code audit is performed.

### Tool changes

- 2026-10-11 `restart_project` changed (description) **meaning changed**
  - before: Restart a running project's container.
  - after: Restart a running project's container. Recreates the pod, re-running the injected-DB resolver gate and the app's storage probes, and waits for readiness: a failed start returns a named error (e.g. an unresolvable DB host) and a plain retry usually clears a transient DNS drop. Not rate-limited. Env changes are NOT picked up by a restart - redeploy instead.
- 2026-10-11 `start_project` changed (description) **meaning changed**
  - before: Start a stopped project's container.
  - after: Start a stopped project's container. Waits until it is ready; a pod that fails to become ready returns a named error.
- 2026-10-11 `set_env` changed (description)
  - before: Set environment variables on a project. Requires a restart before they take effect.
  - after: Set environment variables on a project. They take effect on the next deploy_project: a restart does NOT re-apply env.
- 2026-10-08 `delete_project` changed (description) **meaning changed**
  - before: Stop and delete a project (free the slug after quarantine).
  - after: Stop and delete a project. Its slug goes into quarantine for 7 days: you may re-use it immediately, other accounts get a 409 until it is freed.
- 2026-10-08 `reissue_token` changed (description)
  - before: Re-issue the API token for an existing account. Provide the email the account was registered with; Fiskmås emails a fresh one-time verify link to that address. The human clicks it; the verify page shows the new token once (old tokens are revoked immediately). This is the self-service recovery path when a token was lost, rotated, or is being rejected as "invalid or expired". It does not create a new account — for a brand-new account use create_account. Rate-limited: a few requests per hour per email. If you already have a valid token and just want to rotate it, use rotate_token (follows in a later release).
  - after: Re-issue the API token for an existing account. Provide the email the account was registered with; Fiskmås emails a fresh one-time verify link to that address. The human clicks it; the verify page shows the new token once (old tokens are revoked immediately). This is the self-service recovery path when a token was lost, rotated, or is being rejected as "invalid or expired". It does not create a new account — for a brand-new account use create_account. Rate-limited: a few requests per hour per email.
- 2026-10-05 `get_stats` changed (description)
  - before: Account-wide or per-project stats for debugging: live CPU/mem vs the plan caps (Free: 128 MB / 0.2 CPU, Plus: 256 MB / 0.5 CPU) and deploy history. Omit `project` for all of the caller's projects; pass a project id or slug NaNalso returns `resources.history` — per-project CPU/mem time series over the window (sampled every ~30 s on the k3s platform; absent on stacks without the metrics collector).
  - after: Account-wide or per-project stats for debugging: live CPU/mem vs the plan caps (Free: 256 MB / 0.2 CPU, Plus: 512 MB / 1 CPU) and deploy history. Omit `project` for all of the caller's projects; pass a project id or slug NaNalso returns `resources.history` — per-project CPU/mem time series over the window (sampled every ~30 s on the k3s platform; absent on stacks without the metrics collector).
- 2026-10-05 `deploy_project` changed (description)
  - before: Pull an image by digest and run one container with the plan's cpu/memory caps (Free: 128 MB / 0.2 CPU, Plus: 256 MB / 0.5 CPU). Only registry.fiskmas.dev images are accepted. Rate-limited to 1 deploy per 5 minutes per account (429 with a retry-seconds hint); use restart_project for a transient crash - it does not count against the limit. Re-deploying a running project is always allowed; starting a second one on Free is blocked until one stops.
  - after: Pull an image by digest and run one container with the plan's cpu/memory caps (Free: 256 MB / 0.2 CPU, Plus: 512 MB / 1 CPU). Only registry.fiskmas.dev images are accepted. Rate-limited to 1 deploy per 5 minutes per account (429 with a retry-seconds hint); use restart_project for a transient crash - it does not count against the limit. Re-deploying a running project is always allowed; starting a second one on Free is blocked until one stops.
- 2026-10-05 `whoami` changed (description)
  - before: Return the identity of the current token holder (account + provider) plus its subscription plan (free | plus) and the plan's limits: max running projects, per-project memory/CPU caps, log windows, and the project-database fair-use guide. Free plans include an upgrade_url for Plus ($9.99/mo: 5 projects, 256 MB / 0.5 CPU per project, always-on).
  - after: Return the identity of the current token holder (account + provider) plus its subscription plan (free | plus) and the plan's limits: max running projects, per-project memory/CPU caps, log windows, and the project-database fair-use guide. Free plans include an upgrade_url for Plus ($9.99/mo: 5 projects, 512 MB / 1 CPU per project, always-on).

Full history: https://api.protogrid.dev/v1/servers/dev.fiskmas%2Ffiskmas/changes

## Remotes

- https://mcp.fiskmas.dev/mcp (streamable-http, auth api_key ${FISKMAS_TOKEN}, reachable true, uptime30d 1)

## Packages

_none_

## Tools (21)

- `account_status`: Poll onboarding state for an email (pending | active | unknown). Use after create_account while waiting for the human to verify.
- `create_account`: Start onboarding: require an email, create a pending account, and email a human verify link. Does NOT return an API token. The human must click the link; the verify page shows the token once. Then configure Authorization: Bearer <token> on this MCP client (also docker login -u <token> registry.fiskmas.dev). If you already have a token, call whoami instead.
- `create_project`: Create a project and reserve <slug>-app.fiskmas.dev. Slug must match ^[a-z0-9][a-z0-9-]{1,48}$ and is not reserved. Subject to the plan's running-project quota (Free: 1, Plus: 5) — on quota the error tells the human how to upgrade or free a slot.
- `delete_account`: Delete the caller's account. Stops and removes all projects (containers, routes, MariaDB) first, then deletes the account. Refuses to leave orphaned runtimes.
- `delete_project`: Stop and delete a project. Its slug goes into quarantine for 7 days: you may re-use it immediately, other accounts get a 409 until it is freed.
- `deploy_project`: Pull an image by digest and run one container with the plan's cpu/memory caps (Free: 256 MB / 0.2 CPU, Plus: 512 MB / 1 CPU). Only registry.fiskmas.dev images are accepted. Rate-limited to 1 deploy per 5 minutes per account (429 with a retry-seconds hint); use restart_project for a transient crash - it does not count against the limit. Re-deploying a running project is always allowed; starting a second one on Free is blocked until one stops.
- `get_logs`: Return recent container log lines. `tail` = line count (plan default 200; plan max 2000), `since` = time window in seconds (plan window: free 24 h, plus 7 d — logs are live-pod streams, not stored history). When both are given, `since` wins.
- `get_project`: Fetch a single project by id or slug.
- `get_skill`: Return the bytes of a platform skill by name.
- `get_stats`: Account-wide or per-project stats for debugging: live CPU/mem vs the plan caps (Free: 256 MB / 0.2 CPU, Plus: 512 MB / 1 CPU) and deploy history. Omit `project` for all of the caller's projects; pass a project id or slug NaNalso returns `resources.history` — per-project CPU/mem time series over the window (sampled every ~30 s on the k3s platform; absent on stacks without the metrics collector).
- `get_status`: Return project status, url, image digest, and last deploy error.
- `list_env`: List a project's env keys with masked values (never returns full secrets).
- `list_projects`: List the caller's projects with status and URL.
- `list_skills`: List the platform skills available to the caller.
- `reissue_token`: Re-issue the API token for an existing account. Provide the email the account was registered with; Fiskmås emails a fresh one-time verify link to that address. The human clicks it; the verify page shows the new token once (old tokens are revoked immediately). This is the self-service recovery path when a token was lost, rotated, or is being rejected as "invalid or expired". It does not create a new account — for a brand-new account use create_account. Rate-limited: a few requests per hour per email.
- `restart_project`: Restart a running project's container. Recreates the pod, re-running the injected-DB resolver gate and the app's storage probes, and waits for readiness: a failed start returns a named error (e.g. an unresolvable DB host) and a plain retry usually clears a transient DNS drop. Not rate-limited. Env changes are NOT picked up by a restart - redeploy instead.
- `send_feedback`: Report a problem with the Fiskmås toolset so it can be fixed. Use it when a tool errored or misbehaved, you got stuck and can't proceed, or the instructions/skill were unclear. Do NOT use it for praise. kind=bug means it broke, kind=suggestion means it was unclear or could be better, kind=other is anything else that didn't work. Name the `tool` and, if relevant, the `project`. At most one call per session.
- `set_env`: Set environment variables on a project. They take effect on the next deploy_project: a restart does NOT re-apply env.
- `start_project`: Start a stopped project's container. Waits until it is ready; a pod that fails to become ready returns a named error.
- `stop_project`: Stop a running project's container (keep the image).
- `whoami`: Return the identity of the current token holder (account + provider) plus its subscription plan (free | plus) and the plan's limits: max running projects, per-project memory/CPU caps, log windows, and the project-database fair-use guide. Free plans include an upgrade_url for Plus ($9.99/mo: 5 projects, 512 MB / 1 CPU per project, always-on).