Fiskmas
Server Details
Hosting for AI agents: your AI client deploys Docker apps to live HTTPS URLs over MCP.
- Status
- Healthy
- Uptime
- 100.0% over the last 24 hours
- Last Tested
- Transport
- Streamable HTTP · MCP 2025-11-25
- URL
- ChatGPT
- –
- Claude
- –
TDQS
Scored across 23 tools
Most tools are cleanly separated by resource and action, and descriptions actively steer between lookalikes (create_account vs reissue_token, restart_project vs deploy_project, stop vs start). The only soft overlaps are get_project, get_status, and list_projects, all of which surface project state/URL, though their scopes (single fetch vs runtime status vs list) are still distinguishable.
The dominant pattern is verb_noun (create_project, deploy_project, restart_project, list_env, get_logs, delete_account), which holds across most of the surface. Deviations are limited to a few noun-first names (account_status, database_dump, dump_status) plus the special-case whoami, which are readable but break the pattern.
23 tools is on the heavy side of the 3-15 sweet spot, but the domain genuinely spans account onboarding, project CRUD, container lifecycle, env, logs, metrics, database dumps, and skills. Nearly every tool maps to a distinct operator action, so the count is justified rather than padded.
Coverage is strong across the lifecycle: account create/status/delete/reissue/whoami, project create/get/list/delete, deploy/start/stop/restart, env list/set, logs, stats, status, DB dump + dump polling, and skills. Gaps are minor but real: there is no unset/delete env operation (set_env only merges), no project metadata update, and no way to list or cancel dumps.
Available Tools
23 toolsaccount_statusaccount_statusARead-onlyInspect
Poll onboarding state for an email (pending | active | unknown). Use after create_account while waiting for the human to verify.
Inputs: email (required).
create_accountcreate_accountAInspect
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 on this MCP client (also docker login -u registry.fiskmas.dev). If you already have a token, call whoami instead.
Inputs: email (required), display_name.
create_projectcreate_projectAInspect
Create a project and reserve -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.
Inputs: name, slug.
database_dumpdatabase_dumpAInspect
Export the project's platform-provisioned database: starts a cluster-side dump Job in your own tenant namespace (mariadb-dump --single-transaction, zstd-compressed; gzip fallback) writing a compressed artifact to your tenant artifact store. Small dumps finish inline and return metadata + a presigned download URL (expires in ~24 h; the artifact itself is purged after 7 days). Large dumps return a dump_id with status=running — poll dump_status. The dump bytes NEVER pass through this tool response. Rate limit: 2 per hour per account.
Inputs: project (required).
delete_accountdelete_accountAInspect
Delete the caller's account. Stops and removes all projects (containers, routes, MariaDB) first, then deletes the account. Refuses to leave orphaned runtimes.
Inputs: no named parameters.
delete_projectdelete_projectAInspect
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.
Inputs: project.
deploy_projectdeploy_projectAInspect
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.
Inputs: image, project.
dump_statusdump_statusARead-onlyInspect
Report one database_dump job: status pending|running|done|failed. When done, includes the artifact size/compression and the presigned download URL (expires ~24 h after the dump started; null once expired — request a new dump). When failed, includes the error reason. Poll this after database_dump returns status=running (large dumps).
Inputs: dump (required).
get_logsget_logsARead-onlyInspect
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.
Inputs: tail, since, project.
get_projectget_projectBInspect
Fetch a single project by id or slug.
Inputs: project.
get_statsget_statsBRead-onlyInspect
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).
Inputs: since, project.
get_statusget_statusBRead-onlyInspect
Return project status, url, image digest, and last deploy error.
Inputs: project.
list_envlist_envARead-onlyInspect
List a project's env keys with masked values (never returns full secrets).
Inputs: project.
list_projectslist_projectsARead-onlyInspect
List the caller's projects with status and URL.
Inputs: no named parameters.
list_skillslist_skillsARead-onlyInspect
List the platform skills available to the caller.
Inputs: no named parameters.
reissue_tokenreissue_tokenAInspect
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.
Inputs: email (required).
restart_projectrestart_projectAInspect
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.
Inputs: project.
send_feedbacksend_feedbackAInspect
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.
Inputs: kind (required), message (required), tool, project.
set_envset_envAInspect
Merge environment variables into a project (existing keys are kept). They take effect on the next deploy_project: a restart does NOT re-apply env. The platform-injected DATABASE_URL/MYSQL_* are protected: set_env rejects overriding them and never drops them.
Inputs: env, project.
start_projectstart_projectAInspect
Start a stopped project's container. Waits until it is ready; a pod that fails to become ready returns a named error.
Inputs: project.
stop_projectstop_projectAInspect
Stop a running project's container (keep the image).
Inputs: project.
whoamiwhoamiARead-onlyInspect
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).
Inputs: no named parameters.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Related MCP Connectors
Deploy AI-generated HTML/CSS/JS to instant public HTTPS URLs from any MCP-compatible agent.
MCP hosting for AI agents: Claude or Codex writes the code, runs it and sends a live link.
1Hosting for AI agents: publish a live website in one tool call, ephemeral or forever.
MCP server that lets your AI assistant build and deploy apps, hosting each one at a live URL.
Related MCP Servers
- AlicenseAqualityDmaintenanceAgent-native hosting: your agent deploys any folder to a live URL in one command — no account, no dashboard, no CAPTCHA — and hands the human a link plus a plain-language summary. Full deploy lifecycle as MCP tools (deploy, verify, logs, inspect, rollback), production approval human-only; static sites and full Node.js apps, open source (Apache-2.0).13Apache 2.0
- AlicenseAqualityDmaintenanceEnables AI agents to deploy and manage Docker containers on your own machine via MCP tools, providing public HTTPS URLs through free Cloudflare quick tunnels.12MIT
- AlicenseAqualityCmaintenanceInstant web hosting for AI agents. Publish a live site in one call, no account needed.5MIT
- AlicenseNot gradedqualityCmaintenanceHost apps built with AI: deploy to a live HTTPS URL, custom domains, managed sign-in, secrets and backups. Hosted remote MCP server at https://softkiln.com/mcp/ — this repository is its plugins and skills.MIT
Glama MCP Gateway
Add one secure layer between your agents and this server.