# Joinlayer MCP server

Source: https://glimind.com/server/mcp-registry%2Fapp.joinlayer%2Fmcp
Registry id: `mcp-registry/app.joinlayer/mcp`
Status: auth-required (checked 2026-10-26T18:30:19.429Z)

## Measurements (30 days)

- Uptime: 100%
- Checks: 211
- Outages (90 days): 0

## Install

```json
{
  "mcpServers": {
    "joinlayer-mcp-server": {
      "type": "http",
      "url": "https://mcp.joinlayer.app/mcp"
    }
  }
}
```

Claude Code:

```sh
claude mcp add --transport http joinlayer-mcp-server https://mcp.joinlayer.app/mcp
```

## Tools (29)

- `cancel_agent_approval`: Cancel one pending approval request owned by this agent identity.
- `cancel_connection_setup`: Cancel an unused secure connection setup link.
- `create_connection_setup`: Create a browser setup from non-secret config_schema fields. Omit every secret-marked field, credential, and secret placeholder.
- `create_pipeline_draft`: Create a pipeline draft. Inspect connections first; validate and preview before any run.
- `diagnose_run_failure`: Return run state, structured errors, events, and dead-letter summaries for diagnosis.
- `discover_connection_schema`: Discover relational schemas, ClickHouse databases, BigQuery datasets and tables, or sample Kafka fields with topic as table and no schema.
- `get_connection`: Get one connection's safe metadata and current configuration capabilities.
- `get_connection_setup_status`: Poll a secure connection setup session; completed responses expose only the durable connection ID.
- `get_pipeline`: Get the complete safe pipeline definition, mappings, transforms, checks, setup state, and runtime summary.
- `get_run`: Get run progress, counters, worker lease, recovery state, and curated failure details.
- `get_usage_report`: Return workspace and per-pipeline usage attribution for an ISO-8601 date range.
- `get_workspace_capacity`: Return current workspace plan capacity, usage, remaining limits, and run blockers.
- `get_workspace_context`: Return identity, workspace, role, scopes, and whether workspace policy requires approvals for agent run starts/stops.
- `get_workspace_overview`: Inspect identity, role-visible capacity, connections, and pipelines in one read-only first-session operation.
- `list_activity`: List workspace run activity using explicit status, mode, period, and pipeline filters.
- `list_agent_approvals`: List this agent identity's pending and historical approval requests.
- `list_connection_setups`: List this identity's recent setup sessions to recover safely after an uncertain create response.
- `list_connections`: List workspace connections in a paginated object without stored credentials or encrypted configuration.
- `list_connector_types`: List providers, roles, capabilities, and exact config_schema fields/defaults/options/secret flags. Call before setup.
- `list_pipeline_runs`: List recent runs and recovery state for a pipeline.
- `list_pipelines`: List pipelines with one authoritative inventory_state, plus setup, runtime, validation, and matching state summaries.
- `preview_pipeline`: Preview transformed and enriched target rows without starting the pipeline.
- `request_run_start_approval`: Request exact human approval when workspace policy requires it. If approval_required=false, start without approval_id; otherwise present approval_url and poll.
- `request_run_stop_approval`: Request human approval to stop one exact run when workspace policy requires it. Honor approval_required and return approval_url/next_action when required.
- `start_pipeline`: Start or resume a validated pipeline using an approved request or matching automation policy.
- `stop_run`: Stop an active run using an approved request or matching automation policy.
- `test_connection`: Test one stored connection using server-side secrets. Kafka verifies broker/topic/Registry; ClickHouse verifies transport, credentials, and database access.
- `update_pipeline_draft`: Replace a pipeline draft contract with an explicitly supplied full configuration.
- `validate_pipeline`: Run non-destructive pipeline checks and return stable issues, sections, and remediation actions.

Measured by Glimind (https://glimind.com): MCP handshake + tool list only, no tool is ever called. CC BY 4.0.