# Verbex Lab Tools (remote · www.verbalexperiment.com)

Deterministic wet-lab calculators and lab document templates, with checked notebook entries.

- Trust score: 75/100 (medium)
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-05

## Components

- remote · `www.verbalexperiment.com`: 75/100 (this document), [markdown](https://verifymcp.io/servers/com-verbalexperiment-lab-tools/www.md), [page](https://verifymcp.io/servers/com-verbalexperiment-lab-tools/www)

## Channel facts

- Endpoint: `https://www.verbalexperiment.com/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `0.2.0`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-11-05.

- **Endpoint Security**: 80/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - No authorisation is required to call this server. Every tool declares its destructiveHint and none is destructive, so open access doesn't expose one.
  - HTTPS is enforced; there's no plaintext access path.
  - The HSTS (Strict-Transport-Security) header is present.
  - DNSSEC check failed: this domain isn't protected by DNSSEC.
- **Transport & Reachability**: 100/100
  - Verified streamable-http transport via a live MCP handshake.
- **Schema Quality & AI Usability**: 72/100
  - 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).
  - AI-judged instruction clarity (good).
  - Context-footprint check failed: tool/resource definitions use about 2328 tokens (~194/item across 12 items; 10 tools + 2 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 20/100
  - Stability observed for 6 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 94/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 80% of tool parameters carry a description.
  - Structured output schemas are declared (100% of tools); any adoption earns full credit.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - We read all 10 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 12 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.
  - Supports UI / widget rendering.

## Install

### How do I install the Verbex Lab Tools MCP server?

Verbex Lab Tools is a hosted endpoint at https://www.verbalexperiment.com/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

### Claude

```bash
claude mcp add --transport http com-verbalexperiment-lab-tools 'https://www.verbalexperiment.com/mcp'
```

### Cursor

```json
{
  "mcpServers": {
    "com-verbalexperiment-lab-tools": {
      "url": "https://www.verbalexperiment.com/mcp"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "com-verbalexperiment-lab-tools": {
      "type": "http",
      "url": "https://www.verbalexperiment.com/mcp"
    }
  }
}
```

### Codex

```toml
[mcp_servers.com-verbalexperiment-lab-tools]
url = "https://www.verbalexperiment.com/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "com-verbalexperiment-lab-tools": {
      "type": "remote",
      "url": "https://www.verbalexperiment.com/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add com-verbalexperiment-lab-tools --url 'https://www.verbalexperiment.com/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  com-verbalexperiment-lab-tools:
    url: "https://www.verbalexperiment.com/mcp"
```

### Netclaw

```json
{
  "McpServers": {
    "com-verbalexperiment-lab-tools": {
      "Transport": "http",
      "Url": "https://www.verbalexperiment.com/mcp"
    }
  }
}
```

### Vellum

```bash
assistant mcp add com-verbalexperiment-lab-tools -t streamable-http -u 'https://www.verbalexperiment.com/mcp'
```

### Other

```json
{
  "mcpServers": {
    "com-verbalexperiment-lab-tools": {
      "type": "http",
      "url": "https://www.verbalexperiment.com/mcp"
    }
  }
}
```

The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-11-04 (score 75, +1)

No change was recorded against any check on this day. Stability & Change Management went from 13 to 17. That category is still filling its 30-day observation window: 4 days of observed history at the previous scan, 5 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-02 (score 74, +1)

No change was recorded against any check on this day. Stability & Change Management went from 7 to 10. That category is still filling its 30-day observation window: 2 days of observed history at the previous scan, 3 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-31 (score 73, +1)

- [functional improvement] Stability: unverified → 0.03

### 2026-10-30 (score 72)

First indexed and scored.

## MCP tools (10)

### `search` (~155 tokens)

Search Verbex guides, templates and tools

Search Verbex guides and templates: practical guides (protocols and SOPs, lab notebooks, inventory, data integrity and GLP, equipment records, bench calculations) and the 16 lab documentation templates. Returns ids to pass to fetch, with titles and urls to cite. Not for calculations: to compute a mass, volume, dilution, master mix, LNP formulation or plate map, call that calculator directly.

Input parameters:

- `limit` (integer)
- `query` (string, required): What the scientist needs, in plain words, e.g. "freezer sample inventory" or "write an SOP".
- `type` (string): Optional: only guides or only templates. "tool" lists the calculators, which you can call without searching.

Output parameters:

- `results` (array)

### `fetch` (~100 tokens)

Read a Verbex guide, template or tool

Get the full text of a search result by id, as Markdown. Guides come with a short summary; templates include the blank template, a worked example where there is one, and a link to the editable Word or Excel file. Calculators return the method, the input fields and a worked example computed by the calculator.

Input parameters:

- `id` (string, required): An id from search, e.g. "template:experiment-plan" or "guide:lab-sop-template".

Output parameters:

- `id` (string)
- `metadata` (object)
- `text` (string)
- `title` (string)
- `url` (string)

### `solution_prep` (~316 tokens)

Solution prep (molarity and C1V1)

Use when someone asks how much solid to weigh for a molar solution (how many grams for X mM in Y mL, making up a buffer or salt solution), or how much stock to dilute to a target concentration (C1V1). mode "solid": mass of solid to weigh from molecular weight, target concentration and final volume. mode "stock": C1V1 = C2V2 dilution from a stock, solving for stockVolume, stockConcentration, targetConcentration or finalVolume. Returns the primary result, a step summary, warnings and safety notes.

Input parameters:

- `finalVolume` (number): V2 final preparation volume.
- `finalVolumeUnit` (string)
- `mode` (string): Use solid to calculate mass from molecular weight, or stock for C1V1 dilution.
- `molecularWeight` (number): Molecular weight in g/mol. Required when mode is solid.
- `solutionName` (string): Name for the solution being prepared.
- `solveFor` (string): For stock mode, choose which C1V1 variable to solve.
- `solvent` (string): Solvent or diluent to include in the preparation note.
- `stockConcentration` (number): C1 starting stock concentration.
- `stockConcentrationUnit` (string)
- `stockVolume` (number): V1 stock volume.
- `stockVolumeUnit` (string)
- `targetConcentration` (number): C2 final or desired target concentration.
- `targetConcentrationUnit` (string)

Output parameters:

- `card` (object|null): What the Verbex card draws; same values as the notebook entry.
- `humanUrl` (string)
- `notebookEntry` (string|null): Markdown entry to paste into a lab notebook.
- `result` (object|null)
- `safetyNotes` (array)
- `tool` (string)
- `toolVersion` (string)
- `validationErrors` (array)
- `warnings` (array)

### `serial_dilution` (~169 tokens)

Serial dilution planner

Use for any serial dilution (standard curves, titrations, dose series). Plans transfer and diluent volume per tube and the resulting concentration at each step, from a stock concentration, a constant dilution factor, the number of tubes and the final volume per tube.

Input parameters:

- `concentrationUnit` (string): Unit for stock and calculated final concentrations.
- `dilutionFactor` (number): Constant dilution factor applied at each dilution step.
- `finalVolume` (number): Final volume in each tube.
- `seriesName` (string): Name for the dilution series.
- `steps` (integer): Number of dilution tubes to generate.
- `stockConcentration` (number): Starting stock concentration before the first dilution.
- `volumeUnit` (string): Volume unit for transfer, diluent, and final tube volumes.

Output parameters:

- `card` (object|null): What the Verbex card draws; same values as the notebook entry.
- `humanUrl` (string)
- `notebookEntry` (string|null): Markdown entry to paste into a lab notebook.
- `result` (object|null)
- `safetyNotes` (array)
- `tool` (string)
- `toolVersion` (string)
- `validationErrors` (array)
- `warnings` (array)

### `pcr_master_mix` (~290 tokens)

PCR / qPCR master mix

Use when someone sets up a PCR or qPCR reaction mix for several wells. Calculates volume of each component per reaction and for the whole mix with excess, with water filling the remaining volume. Give each component a stock and final concentration (molar, ng/µL, x buffer, %), an amount per reaction (e.g. 1.25 U polymerase from 5 U/µL, 10 ng template from ng/µL), or a fixed volume. Template can be added per well separately. Do not list water; it is calculated.

Input parameters:

- `components` (array): Master mix components except water (water fills the remaining volume). Give each either a stock and final concentration (or amount per reaction), or a fixed volume per reaction.
- `excessPercent` (number): Extra master mix to cover pipetting loss, as a percent of the reactions.
- `reactionName` (string): Name for the master mix, e.g. 'IL-6 qPCR plate 2'.
- `reactionVolume` (number): Total volume of one reaction, including template.
- `reactionVolumeUnit` (string)
- `reactions` (integer): Number of reactions (wells), including controls.
- `templateVolume` (number): Template volume added to each well separately (not in the master mix).
- `templateVolumeUnit` (string): Defaults to the reaction volume unit.

Output parameters:

- `card` (object|null): What the Verbex card draws; same values as the notebook entry.
- `humanUrl` (string)
- `notebookEntry` (string|null): Markdown entry to paste into a lab notebook.
- `result` (object|null)
- `safetyNotes` (array)
- `tool` (string)
- `toolVersion` (string)
- `validationErrors` (array)
- `warnings` (array)

### `lnp_formulation` (~328 tokens)

LNP formulation (lipid nanoparticles)

Plan a lipid nanoparticle (LNP) formulation for RNA: from RNA mass, N/P ratio and lipid mol% (e.g. ionizable lipid/DSPC/cholesterol/PEG-lipid 50/10/38.5/1.5), calculate moles, mass and stock volume of every lipid, the ethanol and aqueous phase volumes at the chosen mixing ratio (default 3:1), and final RNA concentration, ethanol fraction and lipid:RNA ratio. Molecular weights must come from the user or certificates of analysis.

Input parameters:

- `aqueousToEthanolRatio` (number): Volume ratio of aqueous (RNA) phase to ethanol (lipid) phase at mixing; 3 means 3:1.
- `aqueousVolume` (number): Volume of the aqueous RNA phase.
- `aqueousVolumeUnit` (string)
- `formulationName` (string)
- `lipids` (array): Every lipid in the formulation; mol% must add up to 100 and exactly one is the ionizable lipid.
- `npRatio` (number): Molar ratio of ionizable-lipid amines (N) to RNA phosphates (P).
- `nucleotideMolecularWeight` (number): Average mass per nucleotide used to estimate RNA phosphate (g/mol).
- `rnaMass` (number): Mass of RNA (mRNA, siRNA, sgRNA) to encapsulate.
- `rnaMassUnit` (string)
- `rnaStockConcentration` (number): Concentration of the RNA stock.
- `rnaStockUnit` (string)

Output parameters:

- `card` (object|null): What the Verbex card draws; same values as the notebook entry.
- `humanUrl` (string)
- `notebookEntry` (string|null): Markdown entry to paste into a lab notebook.
- `result` (object|null)
- `safetyNotes` (array)
- `tool` (string)
- `toolVersion` (string)
- `validationErrors` (array)
- `warnings` (array)

### `plate_map` (~276 tokens)

Plate map (6- to 384-well)

Use when someone lays out a multiwell plate (ELISA, qPCR, cell or compound assays). Lays out a 6, 12, 24, 48, 96 or 384-well plate: standards, samples, controls and blanks with replicates, filled by row or column, optionally leaving edge wells empty and keeping replicate sets together. Returns a grid with a key and a well-by-well list.

Input parameters:

- `avoidEdges` (boolean): Leave the outer wells empty to reduce edge effects.
- `blanks` (integer): Number of blank wells, placed last.
- `controlReplicates` (integer): Defaults to the sample replicates.
- `controls` (array): Control names (e.g. 'NTC', 'Positive control'), placed after samples.
- `fillDirection` (string): Fill across rows (A1, A2, …) or down columns (A1, B1, …).
- `format` (integer)
- `keepReplicatesTogether` (boolean): Start a new row or column instead of splitting a replicate set.
- `plateName` (string)
- `replicates` (integer): Replicates per sample.
- `samples` (array): Unique sample names, in placement order.
- `standards` (object): Optional standard curve, placed first.

Output parameters:

- `card` (object|null): What the Verbex card draws; same values as the notebook entry.
- `humanUrl` (string)
- `notebookEntry` (string|null): Markdown entry to paste into a lab notebook.
- `result` (object|null)
- `safetyNotes` (array)
- `tool` (string)
- `toolVersion` (string)
- `validationErrors` (array)
- `warnings` (array)

### `protocol_template` (~143 tokens)

Lab protocol template

Build a structured lab protocol (purpose, materials, procedure, critical steps, acceptance criteria and more) for a protocol title, using a preset or custom sections. Returns Markdown and HTML ready to fill in or print.

Input parameters:

- `includeExecutionNotes` (boolean): Whether to include ELN execution notes for running the protocol.
- `includeVersionHistory` (boolean): Whether to include protocol version history when present in sectionItems.
- `preset` (string): Alias for presetId.
- `presetId` (string): Protocol scaffold preset to use.
- `protocolTitle` (string): Title for the protocol scaffold.
- `sectionItems`
- `sections`: Alias for sectionItems.

Output parameters:

- `card` (object|null): What the Verbex card draws; same values as the notebook entry.
- `humanUrl` (string)
- `notebookEntry` (string|null): Markdown entry to paste into a lab notebook.
- `result` (object|null)
- `safetyNotes` (array)
- `tool` (string)
- `toolVersion` (string)
- `validationErrors` (array)
- `warnings` (array)

### `eln_template` (~145 tokens)

Electronic lab notebook entry template

Build an electronic lab notebook (ELN) entry template for an experiment: objective, materials, procedure, observations and conclusion sections from a preset or custom list, optionally with timestamp fields and voice-capture prompts. Returns Markdown and HTML.

Input parameters:

- `experimentTitle` (string): Title for the ELN entry template.
- `includeTimestamps` (boolean): Whether to include record metadata fields.
- `includeVoicePrompts` (boolean): Whether to include Verbex-style section voice prompts.
- `preset` (string): Alias for presetId.
- `presetId` (string): ELN template preset to use.
- `sectionItems`
- `sections`: Alias for sectionItems.

Output parameters:

- `card` (object|null): What the Verbex card draws; same values as the notebook entry.
- `humanUrl` (string)
- `notebookEntry` (string|null): Markdown entry to paste into a lab notebook.
- `result` (object|null)
- `safetyNotes` (array)
- `tool` (string)
- `toolVersion` (string)
- `validationErrors` (array)
- `warnings` (array)

### `parse_reagent_label` (~127 tokens)

Reagent label parser

Turn text read from a reagent bottle or kit label (OCR or typed) into structured fields such as product name, catalog number, lot, expiry, concentration and storage. Parses the provided text only; send the label text, not an image.

Input parameters:

- `ocrConfidence` (number|null): Optional OCR confidence percentage from the OCR engine.
- `ocrText` (string): OCR text extracted from a reagent label image. The browser tool performs OCR locally; this endpoint parses provided text only.
- `sourceImageName` (string): Optional source image file name or identifier for review context.

Output parameters:

- `card` (object|null): What the Verbex card draws; same values as the notebook entry.
- `humanUrl` (string)
- `notebookEntry` (string|null): Markdown entry to paste into a lab notebook.
- `result` (object|null)
- `safetyNotes` (array)
- `tool` (string)
- `toolVersion` (string)
- `validationErrors` (array)
- `warnings` (array)

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/com-verbalexperiment-lab-tools/www#diagnostics

## Score history

- 2026-11-05: 75
- 2026-11-04: 75
- 2026-11-03: 74
- 2026-11-02: 74
- 2026-11-01: 73
- 2026-10-31: 73
- 2026-10-30: 72

## Common questions

### What is the Verbex Lab Tools MCP server?

Verbex Lab Tools is an MCP server listed in the public MCP registry as com.verbalexperiment/lab-tools. Deterministic wet-lab calculators and lab document templates, with checked notebook entries. This page covers its hosted endpoint (https://www.verbalexperiment.com/mcp).

### Is the Verbex Lab Tools MCP server safe to use?

Verbex Lab Tools scores 75 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

### What tools does the Verbex Lab Tools MCP server expose?

Verbex Lab Tools exposes 10 tools: search, fetch, solution_prep, serial_dilution, pcr_master_mix, and 5 more. Their descriptions and schemas cost roughly 2,049 tokens of context every time the server is loaded.

### Does the Verbex Lab Tools MCP server require authentication?

No. We connected to Verbex Lab Tools without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

### Is the Verbex Lab Tools MCP server still maintained?

Verbex Lab Tools is still listed as active in the MCP registry. We last reached this channel on 5 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

## Links

- Remote endpoint: https://www.verbalexperiment.com/mcp
- Website: https://www.verbalexperiment.com/agents/
- Changelog RSS feed: https://verifymcp.io/servers/com-verbalexperiment-lab-tools/www.xml
- Changelog JSON feed: https://verifymcp.io/servers/com-verbalexperiment-lab-tools/www.json
- HTML version of this page: https://verifymcp.io/servers/com-verbalexperiment-lab-tools/www