K-Dense-AI/scientific-agent-skills / skills/latchbio-integration
latchbio-integration
VerifiedBuilds, registers, debugs, and operates bioinformatics workflows on Latch using the Python SDK, CLI, Latch Data and Registry, Nextflow, Snakemake, programmatic execution, and Latch MCP. Use when authoring or deploying Latch workflows, configuring resources or interfaces, moving data, integrating Registry, or launching and monitoring runs.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 9.8 KB |
| references/data-management.md | markdown | 7.8 KB |
| references/latch-mcp.md | markdown | 4.6 KB |
| references/nextflow-snakemake.md | markdown | 8.4 KB |
| references/operations-and-debugging.md | markdown | 10.2 KB |
| references/registry.md | markdown | 7.5 KB |
| references/resource-configuration.md | markdown | 7.7 KB |
| references/ui-and-automation.md | markdown | 9.7 KB |
| references/verified-workflows.md | markdown | 6.5 KB |
| references/workflow-creation.md | markdown | 9.0 KB |
| scripts/inspect_latch_sdk.py | script | 9.0 KB |
references/latch-mcp.md
View on GitHub# Latch MCP
Latch provides a remote Model Context Protocol server:
```text
https://mcp.latch.bio/mcp
```
It lets compatible AI clients discover workflows and interact with Latch Data
and executions through an OAuth-authorized tool surface.
## Authentication Boundary
- A Latch account is required.
- MCP uses OAuth in the connected AI client.
- MCP authorization does not authenticate the Latch SDK, CLI, or Console.
- SDK login credentials do not replace MCP authorization.
- Actions launched through MCP incur the same normal Latch charges as the
corresponding Console or SDK action.
Never copy OAuth tokens between these authentication domains.
## Setup
### Cursor
Add:
```json
{
"mcpServers": {
"LatchBio": {
"url": "https://mcp.latch.bio/mcp"
}
}
}
```
Then open **Cursor Settings → Tools & MCP(s)**, select LatchBio, click
**Connect**, and complete OAuth.
### Claude Code
```bash
claude mcp add --transport http latchbio https://mcp.latch.bio/mcp
```
Run `/mcp` and complete OAuth.
### Codex
```bash
codex mcp add latchbio --url https://mcp.latch.bio/mcp
codex mcp login latchbio
```
For another MCP client, configure the same remote HTTP URL and follow that
client's OAuth flow.
## Documented Tools
The current guide lists:
| Tool | Purpose |
|---|---|
| `list_files` | List immediate children of a Latch Data directory |
| `get_file` | Return a Console link or presigned download URL for a file |
| `list_workspaces` | List accessible workspaces and the default |
| `list_workflows` | Discover workspace and public workflows |
| `get_workflow_schema` | Retrieve launch metadata and parameter schema |
| `launch_workflow` | Launch with schema-compatible values |
| `list_executions` | Filter executions by workspace, workflow, name, or status |
| `get_execution` | Get status, task nodes, result files, and Console URL |
| `get_task_logs` | Get inline logs or a signed URL for complete logs |
Tool names and schemas can evolve. Discover the connected server's current
tools before calling them.
## Safe Launch Workflow
1. **Select a workspace**
- Call `list_workspaces`.
- Prefer the default only when it is clearly the intended target.
2. **Discover rather than guess**
- Call `list_workflows`.
- Identify the exact workflow and version.
3. **Fetch the schema**
- Call `get_workflow_schema`.
- Use returned types, required values, enums, defaults, and path rules.
4. **Resolve data**
- Use `list_files` only for the minimum directories needed.
- It lists metadata, not file contents.
- Use `get_file` for a selected file's access link. Prefer its Console link
for sharing; treat a presigned download URL as a temporary credential.
- Do not browse unrelated or sensitive directories.
5. **Prepare a launch summary**
- Workspace
- Workflow and version
- Input paths and parameters
- Output destination
- Expected resource/cost implications
6. **Confirm**
- Obtain user approval before launching paid compute.
- Reconfirm unusually large, GPU, or fan-out workloads.
7. **Launch**
- Call `launch_workflow` once.
- Preserve the returned execution identifier and Console URL.
8. **Monitor**
- Poll with `get_execution`.
- Use `get_task_logs` only for relevant nodes.
- Avoid repeatedly downloading full logs when an inline excerpt is enough.
## Example Agent Plan
```text
list_workspaces
→ choose workspace 12345
→ list_workflows
→ choose Bulk RNA-seq version X
→ get_workflow_schema
→ validate sample paths and output directory
→ present launch summary and request confirmation
→ launch_workflow
→ get_execution until terminal status
→ get_task_logs only if a task fails
```
## Cost and Data Safety
- Listing resources is read-only; launching is not.
- Do not launch during exploratory discovery.
- Do not expose signed log URLs; they may grant temporary access.
- Do not paste secrets into workflow parameters.
- Confirm paths belong to the selected workspace.
- Avoid broad file listing when exact paths are already known.
- Stop polling after a terminal state.
- Scientific validation still requires inspecting outputs and method
assumptions after orchestration succeeds.
## When MCP Is Unavailable
Use:
- Latch Console for interactive discovery and launch
- `latch_cli.services.launch.launch_v2` for Python automation
- `latch ls` or `LPath` for data inspection
- Latch Console for execution monitoring; `latch get-executions` remains in
2.77.1 but is deprecated and scheduled for removal
Do not simulate a missing MCP tool by inventing undocumented HTTP endpoints.
## Official Source
- Latch MCP guide: https://wiki.latch.bio/agent/latch-mcp
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| writing-skillsobra/superpowersUse when creating new skills, editing existing skills, or verifying skills work before deployment | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| xlsxanthropics/skillsUse this skill any time a spreadsheet file is the primary input or output. This means any task where the user wants to: open, read, edit, or fix an existing .xlsx, .xlsm, .xltx, .csv, or .tsv file (e.g., adding columns, computing formulas, formatting, charting, cleaning messy data); create a new spreadsheet from scratch or from other data sources; or convert between tabular file formats. Trigger especially when the user references a spreadsheet file by name or path — even casually (like "the xlsx in my downloads") — and wants something done to it or produced from it. Also trigger for cleaning or restructuring messy tabular data files (malformed rows, misplaced headers, junk data) into proper spreadsheets. The deliverable must be a spreadsheet file. Do NOT trigger when the primary deliverable is a Word document, HTML report, standalone Python script, database pipeline, or Google Sheets API integration, even if tabular data is involved. | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |
| shipping-and-launchaddyosmani/agent-skillsPrepares production launches. Use when preparing to deploy to production, or when asking what needs to be in place before shipping. Use when you need a pre-launch checklist, when setting up monitoring, when planning a staged rollout, or when you need a rollback strategy. | Stars: 119k | Updated | Claude CodeCodex | Verified | Install |
| childhoodthedotmack/claude-memBabysit a shipped release after merge, publication, or deployment. Verify published packages, production behavior, installed plugins, and late CI or user reports until the observation window is clean; use babysit for PR readiness before release. | Stars: 118k | Updated | Claude CodeCodex | Verified | Install |