MCP Servers

A collection of Model Context Protocol servers, templates, tools and more.

LIMS MCP Server — a Laboratory Information Management System: samples & chain of custody, tests/specs with OOS detection, ALCOA+ result amendments, gated batch release, HACCP, instruments, and food-safety incidents

Created 6/9/2026
Updated about 7 hours ago
Repository documentation and setup instructions

LIMS MCP Server

Crates.io License ADK-Rust Enterprise Registry Ready

A Laboratory Information Management System (LIMS) for ADK-Rust Enterprise food-beverage and pharmaceutical agents. 27 MCP tools covering samples & chain of custody, tests/assays with specifications, results with out-of-specification (OOS) detection and ALCOA+ data-integrity amendments, batch disposition/release gated on results, HACCP critical control points, instruments/calibration, and food-safety incidents — over an audit trail.

A platform, not a point solution

This is modeled as a general LIMS/QMS lab backbone (à la LabWare / STARLIMS / LabVantage), so a range of quality and safety agents are clients of one shared lab system:

| Agent | Domain | Uses | |-------|--------|------| | Batch Quality Release Agent | food-beverage | evaluate_batch, set_disposition, results_for_sample | | Food Safety Incident Triage | food-beverage | open_incident, update_incident, list_incidents | | HACCP Plan Assistant | food-beverage | create_ccp, record_ccp_reading, ccp_readings | | Lab Data Integrity Monitor | pharmaceuticals | data_integrity_review, get_result, amend_result, review_result |

Architecture

LIMS MCP Architecture

Capabilities

  • Samples & chain of custody — accessioned samples with an append-only custody log and status (received → in_testing → completed → disposed).
  • Tests & specifications — methods with numeric (min/max), count (max), or qualitative (expected value) specs.
  • Results & OOS — entering a result auto-evaluates it against the method spec (pass / oos / pending).
  • Data integrity (ALCOA+)amend_result requires a mandatory reason and appends an immutable amendment (the original value is never overwritten); amendments invalidate a prior review. review_result enforces segregation of duties (reviewer ≠ analyst). data_integrity_review surfaces amended, un-reviewed, and pass-with-amendment results.
  • Batches & release gatingevaluate_batch rolls up all results across a batch's samples; set_disposition refuses to release unless every result passes spec and is reviewed.
  • HACCP — critical control points with limits; record_ccp_reading flags deviations outside critical limits.
  • Instruments — calibration tracking with a due/overdue watchlist.
  • Incidents — food-safety/quality events; high/critical severity recommends a recall and places the linked batch on hold.

Governance posture

  • Two writes are gated (requires_approval): set_disposition (batch release/reject of physical product — classed external_write) and amend_result (changing a lab record of record).
  • Release has teeth — a batch cannot be released while any result is OOS, pending, or un-reviewed (verified in tests and live).
  • ALCOA+ by construction — Attributable, Legible, Contemporaneous, Original, Accurate: amendments preserve the original, capture who/when/why, and every data action is on the audit trail.
  • Reads are read_only. Sample data is fictitious.

Tools (27)

Samples & Custody (4)

register_sample · get_sample · list_samples · add_custody_event

Tests & Results (7)

create_method · list_methods · enter_result · get_result · results_for_sample · amend_result (gated) · review_result

Batches & Release (5)

create_batch · get_batch · list_batches · evaluate_batch · set_disposition (gated, external)

HACCP (4)

create_ccp · list_ccps · record_ccp_reading · ccp_readings

Instruments, Incidents & Integrity (7)

add_instrument · calibration_due · open_incident · update_incident · list_incidents · data_integrity_review · audit_log

Example

// Batch Quality Release: evaluate then (try to) release
{"name": "evaluate_batch", "arguments": {"batch_id": "BAT-1004"}}
{"name": "set_disposition", "arguments": {"batch_id": "BAT-1004", "disposition": "released", "reason": "all pass + reviewed"}}

// Lab Data Integrity Monitor: amend (original preserved) + review trail
{"name": "amend_result", "arguments": {"result_id": "RES-1010", "new_value": 99.0,
  "reason": "recalculation from raw chromatogram"}}
{"name": "data_integrity_review", "arguments": {}}

// HACCP + Incident
{"name": "record_ccp_reading", "arguments": {"ccp_id": "CCP-1016", "value": 68.0, "corrective_action": "re-pasteurized"}}
{"name": "open_incident", "arguments": {"title": "Pathogen detected", "batch_id": "BAT-1008", "severity": "critical"}}

Install & run

cargo install mcp-lims
mcp-lims            # serves MCP over stdio

Or build from source:

git clone https://github.com/zavora-ai/mcp-lims
cd mcp-lims && cargo build --release
./target/release/mcp-lims

Registry manifest

server_id = "mcp_lims"
display_name = "LIMS (Laboratory Information Management)"
version = "1.0.0"
domain = "food-beverage"
risk_level = "high"
writes_allowed = "gated"

The full mcp-server.toml declares all 27 tools with risk classes and approval gates for registry onboarding.

License

Apache-2.0

Quick Setup
Installation guide for this server

Installation Command (package not published)

git clone https://github.com/zavora-ai/mcp-lims
Manual Installation: Please check the README for detailed setup instructions and any additional dependencies required.

Cursor configuration (mcp.json)

{ "mcpServers": { "zavora-ai-mcp-lims": { "command": "git", "args": [ "clone", "https://github.com/zavora-ai/mcp-lims" ] } } }