Skip to main content
Glama
di-omics

plr-mcp

by di-omics
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Local

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
PLR_MCP_BACKENDNoLiquid handling backend (chatterbox, star, ot2, evo)chatterbox
PLR_MCP_OT2_HOSTNoIP address of the OT-2 robot (required when backend is ot2)

Instructions

Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.

This server publishes no instructions, or was last inspected before Glama recorded them.

Capabilities

Features and capabilities supported by this server

Protocol revision2025-11-25

CapabilityDetails
tools
{
  "listChanged": false
}
prompts
{
  "listChanged": false
}
resources
{
  "subscribe": false,
  "listChanged": false
}
experimental
{}

Tools

Functions exposed to the LLM to take actions

NameDescription
setup_deckA

Initialize the liquid handler and place labware. Call this before any liquid handling tool.

backend: 'chatterbox' (simulation, no hardware), 'star' (Hamilton STAR), 'ot2' (Opentrons OT-2, needs host), or 'evo' (Tecan Freedom EVO). Defaults to the server's configured backend. For chatterbox and star a 1000 uL tip rack and a Corning 96-well plate are auto-loaded onto a STARLet deck. host: OT-2 robot IP address (only used when backend='ot2').

deck_stateA

List the resources currently assigned to the deck and the run mode.

pick_up_tipsA

Pick up tips from the tip rack. wells is a PyLabRobot range such as 'A1', 'A1:H1' (a full column), or 'A1:D1'.

drop_tipsC

Return tips to the tip rack at the given range.

aspirateB

Aspirate volume microliters from each plate well in wells.

dispenseB

Dispense volume microliters into each plate well in wells.

transferA

Transfer volume microliters from source wells to dest wells in one head pass (pick up tips, aspirate, dispense, drop tips). Source and dest ranges must have the same well count, at most one column.

read_plateA

Read the plate in the reader. mode is 'absorbance' (uses wavelength), 'fluorescence' (uses excitation/emission/focal_height), or 'luminescence' (uses focal_height).

thermocyclerA

Control the thermocycler. action is one of: set_block (needs block_temp), set_lid (needs lid_temp), open_lid, close_lid, deactivate, status. Temperatures are in Celsius.

heater_shakerA

Control the heater-shaker. action is one of: set_temperature (needs temperature in Celsius), shake (needs speed in rpm, optional duration in seconds), stop, deactivate, status.

Prompts

Interactive templates invoked by user choice

NameDescription

No prompts

Resources

Contextual data attached and managed by the client

NameDescription

No resources

Deploy Server
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

TDQS

A3.6/5.0

Scored across 10 tools

Disambiguation5/5

Each tool targets a distinct operation (aspirate, dispense, transfer, tip handling, deck setup, heater-shaker, thermocycler, plate reader) with no overlaps. Actions are clearly separated.

Naming Consistency5/5

All tool names use lower_snake_case with clear verb_noun patterns (e.g., pick_up_tips, drop_tips, read_plate). Naming is uniform and predictable.

Tool Count5/5

10 tools cover core liquid handling and lab equipment operations without being excessive. Each tool earns its place for a robotics lab server.

Completeness4/5

Covers setup, liquid transfers, tip management, temperature control, and reading. Minor gaps like explicit mixing or pause/move commands exist, but transfer can handle mixing.

Maintenance

ActivitySlowing
ResponsivenessNo issues

Resources