The io.github.openreadout/openreadout MCP server provides offline reading of raw lab-instrument files. It focuses on extracting metadata, generating previews, performing integrity checks, and supporting open-format export. The server is described as working with raw instrument file contents without requiring online services.
π οΈ Key Features
Read raw lab-instrument files offline
Extract metadata
Generate previews
Perform integrity checks
Export in open formats
π Use Cases
Offline inspection of raw lab-instrument files
Reviewing file metadata and previews before analysis
Verifying file integrity
Converting or exporting data using open-format export
β‘ Developer Benefits
Programmatic access to metadata, previews, and integrity checks
Open-format export support for downstream tooling
β οΈ Limitations
No additional capabilities beyond metadata, previews, integrity checks, and open-format export are described
OpenReadout lets AI agents read and analyze raw files from lab instruments like microscopes, mass specs, flow cytometers, plate readers and NMR. It reads 120+ formats without vendor software, and runs as an MCP server, a CLI, or a Python or R package.
Inspect images, channels, traces, spectra, tables, and metadata, in plain text or structured JSON
Check files for truncation, missing planes, and damaged structure, with exit code 4 when a file is corrupt
Export to OME-TIFF, OME-Zarr, mzML, NWB, CSV, Parquet, Arrow, JCAMP-DX, Allotrope ASM, and RDML, reading every export back to verify it
Preview image planes, traces, spectra, and plate heat maps as PNG
Analyze chromatographic peaks, plate assays (IC50, standard curves), qPCR (Cq, ΞΞCq), NMR peaks, patch-clamp features, spikes, and flow-cytometry gates, with documented methods
Batch over whole directories, index lab shares, and watch running acquisitions
On the Command Line
bash
# Install (macOS / Linux; other ways under Installation)
curl -fsSL https://raw.githubusercontent.com/openreadout/openreadout/main/scripts/install.sh | sh
# What is in the file?
openreadout info cells.lif
# β format: Leica LIF (lif) v2 size: 16.0 MiB images: 1 planes: 2# β [0] PEI_laminin_35k 2048x2048 z=1 c=2 t=1 uint16 px=0.3250 Β΅m# β objective: HC PL FLUOTAR L 20x/0.40 DRY# Is it complete?
openreadout check partial-copy.lif
# β error truncated block chain runs past end of file# β error missing_planes geometry needs 16777216 bytes but only 8969789 are stored# Integrate the peaks of a chromatogram
openreadout analyze peaks gc-run.ch --min-height 1
# β 4 peaks, area in pAΒ·min# β 1 4.852 min area 0.2779 25.08 %# β ...# Structured JSON for scripts and agents
openreadout info cells.lif --json
Terminal session: openreadout info describes a Leica LIF file, check reports that a truncated copy is incomplete and exits with code 4, export writes a verified OME-TIFF, analyze peaks lists four peaks in a GC chromatogram, and info --json piped to jq prints the pixel size.
Formats
Area
Formats
Export to
Light microscopy
Zeiss CZI, Nikon ND2, Leica LIF, Olympus OIR/VSI/OIB, Imaris, OME-TIFF and other TIFF variants, OME-Zarr, whole-slide images (including Philips iSyntax, Hamamatsu VMS and MIRAX)
Windsurf, Zed, Continue, and Cline are supported too. The server exposes 28 tools (openreadout_info, openreadout_check, openreadout_preview, openreadout_export, openreadout_peaks, ...) over JSON-RPC, so the client doesn't need shell access.
Each of these adds the skill and the MCP server from the openreadout/agent-plugins repository. The server runs the openreadout binary from your PATH, so install it first.
Assurance on every result: whether that kind of file was checked against another reader. --strict refuses anything that wasn't.
Previews the agent can look at, as PNG.
Figures from plot: plate grids, dose-response fits, gated dot plots and more, as PNG, SVG or PDF.
Fast metadata:info reads headers only, so a 100 GB file is as quick as a small one.
Read-only and offline.
Python and R
Python β pip install openreadout returns metadata as dicts and pixels as NumPy, dask, or xarray arrays, with plugins for bioio and napari. See the Python guide.
python
import openreadout
with openreadout.File("cells.lif") as f:
f.images[0]["channels"] # same keys as `info --json`
stack = f.to_xarray(0) # labelled with channel names and Β΅m
f.preview(composite=True) # shows itself in Jupyter
openreadout.plot(data={"file": "growth.pda"}, facet="plate").save("plate.pdf")
R β the R package returns arrays and data frames, and draws the same previews and figures. See the R guide.
Comparison
OpenReadout
Bio-Formats
bioio
czifile / nd2 / liffile
msconvert
Open source & free
β (MIT / Apache-2.0)
β (GPL)
β (plugins vary)
β (BSD)
β (vendor DLLs are not)
AI-native CLI + JSON + MCP
β
β
β
β
β
Zero install (single binary)
β
β (JVM)
β (Python)
β (Python)
β
No vendor DLLs
β
β
β
β
β
Integrity check
β
β
β
β
β
Microscopy
β
β
β
β (one format each)
β
Mass spectrometry
β
β
β
β
β
Ephys, flow, NMR, chromatography, plates, qPCR
β
β
β
β
β
Cross-platform
β
β
β
β
Windows (or Wine)
Validation
Each reader is tested against other readers on public instrument files. See how we validate.
The readers were written from public files, published specifications and permissively licensed readers (credited in NOTICE), without vendor SDKs or DLLs. GPL readers such as Bio-Formats are only run as black boxes in tests. See the clean-room policy and the per-format provenance logs.
Documentation
The documentation has guides for every command and format:
A file that does not work: run openreadout report FILE and attach the bundle to a new-variant issue. The bundle contains no data values, sample names, or paths.
Privacy
OpenReadout runs on your computer, makes no network connections and sends no telemetry. See PRIVACY.md.