Loading the directory
Goose lists extensions in config.yaml. Enable the extension and restart the session.
config.yaml at the path for your OS.~/.config/goose/config.yaml~/.config/goose/config.yaml%USERPROFILE%\.config\goose\config.yamlEvery server page builds a ready-to-paste YAML config for Goose.
Servers that can be installed in this client.
Ecuador's open government data for AI assistants: CKAN, SRI, BCE, INEC, Supercias, SERCOP and more.
Local-first Sui DeFi evidence and review for AI clients before wallet signing.
Offline SAP ABAP/RAP tools for AI agents: lint, Cloud readiness, released APIs, knowledge.
Monitor services, manage incidents and status pages in Statuser.cloud from your AI assistant.
Zero-code proxy: policy, human gate, read-back and a hash-chained ledger for any MCP server.
Auto-resolves Git merge conflicts so agents only touch the complex hunks.
Zenrows MCP server: Fetch, Extract, Batch, and Browser Sessions for AI agents
Free Remotion video templates and creative guides; optional hosted Studio rendering and publishing.
Search 1,673 source-linked exam blueprints with reviewed guidance. Read-only; no API key.
The design system your coding agents check before they ship: tokens plus exact UI fixes.
Observe any running process from your agent. strace, py-spy, perf, lsof, tcpdump as evidence.
Free renovation calculators, contract templates, room planners and contractor directories (EN/PL)
Ask a local SQLite mirror of your Jira and Confluence: SQL, full-text search, issue detail.
LLM serving capacity planner: VRAM, KV cache, GPU topology, latency, and cost.
Read-only MCP access to a BAOS workspace: product graphs, requirements, evidence, research.
Wetter und Pegel je Gemeinde in Österreich. Privates Projekt, kein offizielles Behördenangebot.
Verify companies, domains and counterparties before transacting. Sanctions, UBO, fraud scoring.
PR blast radius and 0-1 risk score from git history, so low-risk PRs can be auto-approved.
File-first, local-first MCP memory for AI coding assistants: Markdown + YAML, no vector DB.
Signed messages between AI agents. Dangerous actions wait for a human-signed approval.
Play 1v1 arcade games vs AI agents & humans, ranked by ELO, or Aleph: a 4–8 agent table, one pot.
Unknown author
Read-only Playwright CI results for agents: new vs known failures, flaky tests, test history.
Set up and audit site measurement: GA4, Search Console and PageSpeed. Read-only unless enabled.
Measure the matches your exact join is silently dropping, and get the rule that fixes each.