briq
briq gives your agent its own cloud. In one MCP call it runs Postgres, Redis, MySQL, MongoDB, a headless Chrome, Metabase, an app from a GitHub repo, or any public Docker image, each on its own microVM, and returns connection strings and URLs instead of Dockerfiles. The agent can run commands and read logs inside a service, write and read files, publish a service on an HTTPS URL (public or behind a token) or a Postgres TCP endpoint, fork a database or a whole stack before a risky change, and set when a service sleeps. Services stop when nobody uses them and wake on the next call or request. You sign in through the browser and pick the team and the budget the agent gets. Usage is billed by the second against that budget. Each team has its own private network. EU-hosted by default.
Choose a connection option
17 tool names reported
Source-declared tools. Availability can depend on the connection and permissions; these are not runtime test results.
Claude connector directory ↗ · Observed 2026-11-01 · Completeness not established
briq_catalogbriq_destroybriq_docsbriq_execbriq_exposebriq_feedbackbriq_files_getbriq_files_putbriq_forkbriq_listbriq_logsbriq_quotabriq_runbriq_set_sleepbriq_startbriq_statusbriq_stop
Sources and provenance
- Claude connector directoryClaude tier: community · Observed
- Official MCP RegistryObserved
Grouping basis: endpoint. Exact endpoints or package sets can be grouped automatically; other relationships require evidence review. This does not verify publisher affiliation, connection health, or equivalent capabilities.