Unleash scientific tools for your agents.
Your agent sends a prompt and the data. ScientistWorkbench runs the analysis in an isolated Linux sandbox with a curated life-science stack, an independent reviewer checks the report against what actually ran, and you get back a summary, figures, tables and the code — addressable forever by job id.
No seats, no installs, no subscription required. One API key works for HTTP and MCP.
How it works
Submit
One prompt plus input files (xlsx, csv, fasta, PDFs …) over HTTP or an MCP tool call. Returns a job_id immediately.
Sandbox
A fresh Ubuntu sandbox per job: Python/R, scipy, Biopython, MAFFT, FastTree, HMMER, RDKit, 24 life-science databases. Nothing shared between jobs or tenants.
Reviewed report
The agent writes summary.md (Objective · Method · Results · Assumptions · Files). A separate reviewer audits every claim against the execution log.
Collect
Summary, figures, tables, scripts, transcript and reviewer findings — as JSON, as files, or inline in your agent's context. Run hundreds in parallel.
What a job costs
Prepaid tokens, no seats. A job uses tokens in proportion to what it reads, computes and writes. Measured on the production engine:
| job | class | wall time | tokens |
|---|---|---|---|
| CRO assay QC Recompute plate statistics, refit IC50 curves, flag anomalies in a CRO xlsx deliverable | specialist (standard model) | ≈ 11 min | 185k tokens |
| Database lookup One structured question against UniProt / Open Targets / ChEMBL / DepMap / PubMed | lookup (standard model) | ≈ 4 min | 70k tokens est. |
| Research phylogeny Family selection, MAFFT + FastTree, ancestral reconstruction, structural superposition, 5 figures | research (frontier model) | ≈ 39 min | 1.11M tokens |
Built for agent frameworks, not chat
API- and MCP-native
Eight MCP tools (science_submit, science_wait, science_result …) and a plain HTTP job API. Works from Claude Code, Cursor, Claude Desktop, the Agent SDK, or curl.
Durable job ids + provenance
Every artifact has a sha256 and a stable science:<job_id>/<file> ref. Transcript, execution log and reviewer record ship with every result.
Parallel by default
Submit and poll. Each job is its own sandbox; concurrency is a setting, not a queue you wait in.
Isolation
Per-job sandboxes, per-tenant storage keys, read-only mounted inputs, no shared state, no training on your data.
Real runs
QC of a CRO IC50 deliverable (NCI-N87, two ADC candidates + benchmark + control)
specialist · standard model · 11 min · 2 figures · 173k tokens
“Take this data from the CRO and QC it and return a summary of the results.”
Proteins of unknown function in extremophiles: the MEMO1 family across the three domains of life
research · frontier model · 39 min · 5 figures · 1.11M tokens
“Give me an example of some proteins of unknown function in extremophiles. Choose the most interesting, and build a phylogenetic tree with related sequences acro…”
AI-generated analysis. Outputs may contain errors; verify numbers against the execution log and source files before relying on them. Not a substitute for review by a qualified scientist, and not medical advice: any use affecting patient care or healthcare decisions requires review by a qualified professional.