# ivive.app (remote · api.ivive.app)

Human hepatic clearance from in-vitro CLint, with the error band measured on known drugs.

- Trust score: 79/100 (medium)
- Change this week: +11
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-04

## Components

- remote · `api.ivive.app`: 79/100 (this document), [markdown](https://verifymcp.io/servers/app-ivive-ivive/api.md), [page](https://verifymcp.io/servers/app-ivive-ivive/api)

## Channel facts

- Endpoint: `https://api.ivive.app/mcp/`
- Transports: `streamable-http`
- Auth: `none`
- Version: `1.0.3`

## 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 2026-11-04.

- **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**: 57/100
  - AI-judged instruction clarity (good).
  - Context-footprint check failed: tool/resource definitions use about 1512 tokens (~252/item across 6 items; 6 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 60/100
  - Stability observed for 18 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 100/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 100% of tool parameters carry a description.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - We read all 6 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 7 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.

## Install

### How do I install the ivive.app MCP server?

ivive.app is a hosted endpoint at https://api.ivive.app/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 app-ivive-ivive 'https://api.ivive.app/mcp/'
```

### Cursor

```json
{
  "mcpServers": {
    "app-ivive-ivive": {
      "url": "https://api.ivive.app/mcp/"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "app-ivive-ivive": {
      "type": "http",
      "url": "https://api.ivive.app/mcp/"
    }
  }
}
```

### Codex

```toml
[mcp_servers.app-ivive-ivive]
url = "https://api.ivive.app/mcp/"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "app-ivive-ivive": {
      "type": "remote",
      "url": "https://api.ivive.app/mcp/",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add app-ivive-ivive --url 'https://api.ivive.app/mcp/' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  app-ivive-ivive:
    url: "https://api.ivive.app/mcp/"
```

### Netclaw

```json
{
  "McpServers": {
    "app-ivive-ivive": {
      "Transport": "http",
      "Url": "https://api.ivive.app/mcp/"
    }
  }
}
```

### Vellum

```bash
assistant mcp add app-ivive-ivive -t streamable-http -u 'https://api.ivive.app/mcp/'
```

### Other

```json
{
  "mcpServers": {
    "app-ivive-ivive": {
      "type": "http",
      "url": "https://api.ivive.app/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 79, +1)

No change was recorded against any check on this day. Stability & Change Management went from 57 to 60. That category is still filling its 30-day observation window: 17 days of observed history at the previous scan, 18 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-02 (score 78, +1)

No change was recorded against any check on this day. Stability & Change Management went from 50 to 53. That category is still filling its 30-day observation window: 15 days of observed history at the previous scan, 16 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-31 (score 77, +1)

No change was recorded against any check on this day. Stability & Change Management went from 43 to 47. That category is still filling its 30-day observation window: 13 days of observed history at the previous scan, 14 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-29 (score 76, +8)

- [security improvement] Authorization: unverified → partial
- [functional improvement] Tool coverage: 89% → 100%
- [functional] Server version: 1.0.2 → 1.0.3
- [cosmetic] “input_sensitivity” reworded the description of “clint_range”
- [cosmetic] “input_sensitivity” reworded the description of “fu_mic_range”
- [cosmetic] “predict_inputs” reworded the description of “assay_type”
- [cosmetic] “scale_to_human” reworded the description of “animals”

### 2026-10-27 (score 68, +1)

No change was recorded against any check on this day. Stability & Change Management went from 30 to 33. That category is still filling its 30-day observation window: 9 days of observed history at the previous scan, 10 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-25 (score 67, +1)

No change was recorded against any check on this day. Stability & Change Management went from 23 to 27. That category is still filling its 30-day observation window: 7 days of observed history at the previous scan, 8 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-23 (score 66, +1)

No change was recorded against any check on this day. Stability & Change Management went from 17 to 20. That category is still filling its 30-day observation window: 5 days of observed history at the previous scan, 6 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-21 (score 65, +5)

- [security improvement] HSTS header: fail → pass
- [security] Tool “similar_drugs” rewrote its description, which is the text the model reads
- [security] Tool “target_clint” rewrote its description, which is the text the model reads
- [functional regression] Schema quality: 200 → 235
- [functional improvement] Tool coverage: 63% → 89%
- [functional] Server version: 1.0.1 → 1.0.2
- [cosmetic] “predict_inputs” reworded the description of “smiles”
- [cosmetic] “similar_drugs” reworded the description of “n”
- [cosmetic] “similar_drugs” reworded the description of “smiles”
- [cosmetic] “target_clint” reworded the description of “assay_type”
- [cosmetic] “target_clint” reworded the description of “fu_mic”
- [cosmetic] “target_clint” reworded the description of “fu_p”
- [cosmetic] “target_clint” reworded the description of “model”
- [cosmetic] “target_clint” reworded the description of “rb”
- [cosmetic] “target_clint” reworded the description of “species”

## MCP tools (6)

### `predict_inputs` (~104 tokens)

Predict fu,p and fu,inc from a SMILES, with structure-only human CL and Vss as second opinions. Predictions, not measurements; check the applicability verdict.

Input parameters:

- `assay_type` (string): Incubation fu,inc is predicted for: microsomes or hepatocytes.
- `concentration` (number): Incubation concentration: mg microsomal protein/mL, or 10⁶ hepatocytes/mL.
- `smiles` (string, required): Structure as SMILES.

### `calc_clhep` (~401 tokens)

Hepatic and plasma clearance from in-vitro CLint, fu,mic and fu,p (IVIVE), with the observed-CL band and applicability warnings. If fu,p or fu,mic came from predict_inputs, tell the user the result rests on predicted inputs.

Input parameters:

- `assay_type` (string): Assay type for CLint scaling. microsomes: uses MPPGL (mg/g) × 1e-3; hepatocytes: uses HPGL (×10⁶ cells/g) × 1e-3.
- `clint` (number, required): Intrinsic clearance (µL/min/mg microsomal protein). Use ge=0: zero clearance is physiologically valid.
- `clint_censored` (boolean): Set when the assay reported CLint below its limit of quantification and `clint` is that limit rather than a measurement. CLint then lies in [0, clint), so every clearance output is an upper bound: `u…
- `correction_id`: Saved lab correction (/api/correction-equations) to apply. Must match species and assay_type. Corrects predicted plasma CL and replaces the reference band with one from the lab's compounds.
- `fu_mic` (number, required): Unbound fraction in microsomes (0–1). Corrects for non-specific microsomal binding.
- `fu_p` (number, required): Unbound fraction in plasma (0–1). Plasma protein binding correction.
- `model` (string): IVIVE model. well-stirred (venous equilibrium) or parallel-tube (sinusoidal perfusion).
- `rb` (number): Blood-to-plasma concentration ratio. fu_b = fu_p / Rb. Output is blood clearance.
- `species` (string, required): Species for physiological parameters (Qh, MPPGL, liver weight).

### `target_clint` (~252 tokens)

The in-vitro CLint an assay must read for a compound to reach a target plasma clearance (mL/min/kg): calc_clhep run backwards, e.g. to set a CLint cut-off for a screening cascade. Needs fu,mic and fu,p; refuses a target at or above the liver blood flow ceiling and returns that ceiling. Uncorrected IVIVE, so no error band.

Input parameters:

- `assay_type` (string): Assay the CLint is for; sets its units (µL/min/mg protein or µL/min/10⁶ cells).
- `fu_mic` (number, required): Unbound fraction in the incubation (0–1) the CLint would be measured at.
- `fu_p` (number, required): Unbound fraction in plasma (0–1).
- `model` (string): IVIVE liver model to invert.
- `rb` (number): Blood-to-plasma concentration ratio; raises the plasma CL ceiling (Qh × Rb).
- `species` (string, required): Species whose liver blood flow and scaling factors apply.
- `target_clp` (number, required): Plasma clearance to aim for (mL/min/kg). Must be below hepatic blood flow × Rb.

### `input_sensitivity` (~465 tokens)

How far plasma CL moves as each input is varied over a range, e.g. a predicted fu,p over its 50% range.

Input parameters:

- `assay_type` (string): Assay type for CLint scaling. microsomes: uses MPPGL (mg/g) × 1e-3; hepatocytes: uses HPGL (×10⁶ cells/g) × 1e-3.
- `clint` (number, required): Intrinsic clearance (µL/min/mg microsomal protein). Use ge=0: zero clearance is physiologically valid.
- `clint_censored` (boolean): Set when the assay reported CLint below its limit of quantification and `clint` is that limit rather than a measurement. CLint then lies in [0, clint), so every clearance output is an upper bound: `u…
- `clint_range`: CLint range in the assay's units, e.g. {"low": 10, "high": 40}.
- `correction_id`: Saved lab correction (/api/correction-equations) to apply. Must match species and assay_type. Corrects predicted plasma CL and replaces the reference band with one from the lab's compounds.
- `fu_mic` (number, required): Unbound fraction in microsomes (0–1). Corrects for non-specific microsomal binding.
- `fu_mic_range`: fu,mic range (0–1), e.g. {"low": 0.5, "high": 0.9}.
- `fu_p` (number, required): Unbound fraction in plasma (0–1). Plasma protein binding correction.
- `fu_p_range`: A predicted fu,p carries its 50% range; pass it to see what it costs.
- `model` (string): IVIVE model. well-stirred (venous equilibrium) or parallel-tube (sinusoidal perfusion).
- `rb` (number): Blood-to-plasma concentration ratio. fu_b = fu_p / Rb. Output is blood clearance.
- `species` (string, required): Species for physiological parameters (Qh, MPPGL, liver weight).

### `similar_drugs` (~112 tokens)

Nearest reference drugs to a SMILES (Tanimoto, Morgan radius 2), each with measured human plasma CL and the CL IVIVE predicted from its measured inputs. Use it to judge how far to trust calc_clhep for this chemotype: if IVIVE missed on the neighbours, expect it to miss here. Returns neighbours only, not a prediction for the query.

Input parameters:

- `n` (integer): How many reference drugs to return, nearest first.
- `smiles` (string, required): Structure as SMILES.

### `scale_to_human` (~105 tokens)

Predict human plasma CL from observed animal in-vivo CL (rat, dog, monkey), every applicable method with its measured error. Observed animal CL only, never predicted.

Input parameters:

- `animals` (array, required): One entry per species, e.g. [{"species": "rat", "cl": 40}, {"species": "dog", "cl": 12}].
- `fu_p_human`: Human unbound fraction, needed by the fu-corrected methods

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/app-ivive-ivive/api#diagnostics

## Score history

- 2026-11-04: 79
- 2026-11-03: 78
- 2026-11-02: 78
- 2026-11-01: 77
- 2026-10-31: 77
- 2026-10-30: 76
- 2026-10-29: 76
- 2026-10-28: 68
- 2026-10-27: 68
- 2026-10-26: 67
- 2026-10-25: 67
- 2026-10-24: 66
- 2026-10-23: 66
- 2026-10-22: 65
- 2026-10-21: 65
- 2026-10-20: 60
- 2026-10-19: 60
- 2026-10-18: 59
- 2026-10-17: 59

## Common questions

### What is the ivive.app MCP server?

ivive.app is an MCP server listed in the public MCP registry as app.ivive/ivive. Human hepatic clearance from in-vitro CLint, with the error band measured on known drugs. This page covers its hosted endpoint (https://api.ivive.app/mcp/).

### Is the ivive.app MCP server safe to use?

ivive.app scores 79 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 ivive.app MCP server expose?

ivive.app exposes 6 tools: predict_inputs, calc_clhep, target_clint, input_sensitivity, similar_drugs, scale_to_human. Their descriptions and schemas cost roughly 1,439 tokens of context every time the server is loaded.

### Does the ivive.app MCP server require authentication?

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

### Is the ivive.app MCP server still maintained?

ivive.app is still listed as active in the MCP registry. We last reached this channel on 4 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://api.ivive.app/mcp/
- Website: https://ivive.app/
- Changelog RSS feed: https://verifymcp.io/servers/app-ivive-ivive/api.xml
- Changelog JSON feed: https://verifymcp.io/servers/app-ivive-ivive/api.json
- HTML version of this page: https://verifymcp.io/servers/app-ivive-ivive/api