# ProbeLine (remote · probeline.io)

Perio diagnosis and risk, ICD-10-CM, peri-implant status, sourced implant specs. Paid via x402.

- Trust score: 71/100 (medium)
- Change this week: +2
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-21

## Components

- remote · `probeline.io`: 71/100 (this document), [markdown](https://verifymcp.io/servers/ryankaye212-tech-probeline/probeline.md), [page](https://verifymcp.io/servers/ryankaye212-tech-probeline/probeline)

## Channel facts

- Endpoint: `https://probeline.io/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `1.1.0`

## 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 2026-11-21.

- **Endpoint Security**: 74/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - No authorisation is required to call this server. Nothing on it is marked destructive, but we can't show that an anonymous caller can only read: full credit needs the server to list at least one tool and every tool to be verifiably read-only. We use a best-effort check of tool names and descriptions to tell read-only tools from tools that change things, so some genuinely read-only tools may not get full credit. Names that start with a read verb (get, list, read, search and similar) and accurate readOnlyHint annotations help. Meet that to earn full credit, or require authorisation.
  - HTTPS is enforced; there's no plaintext access path.
  - HSTS check failed: the Strict-Transport-Security header is absent.
  - 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**: 55/100
  - AI-judged instruction clarity (fair).
  - Context-footprint check failed: tool/resource definitions use about 1283 tokens (~142/item across 9 items; 9 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 37/100
  - Stability observed for 11 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 81/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 42% 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 9 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 10 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 ProbeLine MCP server?

ProbeLine is a hosted endpoint at https://probeline.io/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 ryankaye212-tech-probeline 'https://probeline.io/mcp'
```

### Cursor

```json
{
  "mcpServers": {
    "ryankaye212-tech-probeline": {
      "url": "https://probeline.io/mcp"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "ryankaye212-tech-probeline": {
      "type": "http",
      "url": "https://probeline.io/mcp"
    }
  }
}
```

### Codex

```toml
[mcp_servers.ryankaye212-tech-probeline]
url = "https://probeline.io/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "ryankaye212-tech-probeline": {
      "type": "remote",
      "url": "https://probeline.io/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add ryankaye212-tech-probeline --url 'https://probeline.io/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  ryankaye212-tech-probeline:
    url: "https://probeline.io/mcp"
```

### Netclaw

```json
{
  "McpServers": {
    "ryankaye212-tech-probeline": {
      "Transport": "http",
      "Url": "https://probeline.io/mcp"
    }
  }
}
```

### Vellum

```bash
assistant mcp add ryankaye212-tech-probeline -t streamable-http -u 'https://probeline.io/mcp'
```

### Other

```json
{
  "mcpServers": {
    "ryankaye212-tech-probeline": {
      "type": "http",
      "url": "https://probeline.io/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.

### 2026-11-20 (score 71, +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.

### 2026-11-18 (score 70, +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.

### 2026-11-17 (score 69, −1)

- [security] The server rewrote its instructions, which are the text every model session reads
- [functional regression] Schema quality: 128 → 142
- [functional improvement] Tool coverage: 37% → 42%
- [functional] Server version: 1.0.0 → 1.1.0
- [functional] New tool “assess_peri_implant”
- [functional] New tool “assess_periodontal_risk”
- [functional] New tool “get_component_compatibility”
- [functional] New tool “implant_complications_reference”
- [functional] New tool “lookup_icd10”

### 2026-11-16 (score 70, +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.

### 2026-11-14 (score 69, +1)

No change was recorded against any check on this day. Stability & Change Management went from 10 to 13. That category is still filling its 30-day observation window: 3 days of observed history at the previous scan, 4 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-11 (score 68, +1)

- [functional improvement] Stability: unverified → 0.03

### 2026-11-10 (score 67)

First indexed and scored.

## MCP tools (9)

### `search_implants` (~85 tokens)

Search implant systems (free)

List or search the dental implant database (manufacturer, line, connection, platforms, status). Free. Returns ids for get_implant.

Input parameters:

- `connection` (string)
- `manufacturer` (string)
- `q` (string): Free-text search, e.g. 'nobel active'
- `status` (string): e.g. 'current' or 'discontinued'

### `implant_complications_reference` (~66 tokens)

Implant complications reference (free)

Definitions, key findings, ICD-10-CM codes and checks for dental implant complications (mucositis, peri-implantitis, early failure, screw loosening/fracture, implant fracture). Free.

Input parameters:

- `category` (string)
- `id` (string)

### `diagnose_periodontitis` (~160 tokens)

diagnose periodontitis

Periodontal diagnosis from a de-identified 6-point chart: 2017 AAP/EFP stage, extent, grade, ICD-10-CM suggestions, rationale and documentation checklist. Clinical decision support for licensed dental professionals. Send no patient identifiers. Costs $0.25 USDC per call (x402, Base).

Input parameters:

- `chart` (array, required): One entry per present tooth
- `complexity` (object)
- `longitudinal` (object)
- `patient` (object): Risk factors only. Never send names, DOB, record numbers or dates of service.
- `phenotype` (string)
- `remaining_teeth` (integer): Defaults to number of teeth charted
- `teeth_lost_to_perio` (integer)

### `get_implant` (~87 tokens)

get implant

Full spec for one dental implant system: connection, platforms, diameters, lengths, abutment screw torque, multi-unit torque, driver, with a source URL for each value. Unknown values are null. Costs $0.05 USDC per call (x402, Base).

Input parameters:

- `id` (string, required): Implant id from search_implants, e.g. 'straumann-bl'

### `identify_implant` (~135 tokens)

identify implant

Rank likely dental implant systems from observed features (connection type, platform/body diameter, body shape, bone/tissue level), with reasons for each candidate. Costs $0.10 USDC per call (x402, Base).

Input parameters:

- `body_diameter_mm` (number)
- `body_shape` (string)
- `connection_type` (string): e.g. 'internal hex', 'external hex', 'conical', 'morse taper', 'tri-channel'
- `level` (string)
- `limit` (integer)
- `manufacturer_hint` (string)
- `platform_diameter_mm` (number)

### `lookup_icd10` (~237 tokens)

lookup icd10

ICD-10-CM lookup for periodontal and dental implant conditions by code, free text, or structured condition (e.g. periodontitis Stage III generalized -> K05.323). Public-domain code set; no CDT. Costs $0.05 USDC per call (x402, Base).

Input parameters:

- `acute` (boolean)
- `code` (string): Exact ICD-10-CM code, e.g. 'K05.323'
- `complete` (boolean): tooth_loss_periodontal: complete (edentulous) vs partial
- `condition` (string): Structured mapping; combine with the qualifiers below
- `diabetes_type` (integer)
- `extent` (string)
- `failure_type` (string)
- `kennedy_class` (string)
- `limit` (integer)
- `molar_incisor_pattern` (boolean)
- `non_plaque_induced` (boolean)
- `q` (string): Free text, e.g. 'generalized severe periodontitis' or 'peri-implantitis'
- `severity` (string)
- `stage` (string)

### `assess_periodontal_risk` (~176 tokens)

assess periodontal risk

Periodontal risk assessment (Lang & Tonetti PRA): six vectors banded low/moderate/high, patient risk with the rule applied, suggested maintenance interval, and tooth-level adverse prognostic factors. Costs $0.15 USDC per call (x402, Base).

Input parameters:

- `age` (number)
- `bone_loss_pct` (number): Worst-site radiographic bone loss, % of root length
- `bop_percent` (number): % of sites bleeding on probing
- `sites_pd_5_plus` (integer): Number of sites with PD >= 5 mm
- `smoking` (object)
- `systemic` (object)
- `teeth` (array): Optional tooth-level findings for prognostic factor flags
- `teeth_lost` (integer): Teeth lost of 28 (excluding third molars)

### `assess_peri_implant` (~175 tokens)

assess peri implant

Peri-implant status (health / mucositis / peri-implantitis) from clinical findings using 2017 World Workshop case definitions, with severity grade, ICD-10-CM suggestion and each criterion shown. Costs $0.15 USDC per call (x402, Base).

Input parameters:

- `baseline_pd_mm` (number): PD after prosthesis delivery, if known
- `bone_level_mm` (number): Radiographic bone level apical to the most coronal intraosseous part (no-baseline pathway)
- `bone_loss_since_baseline_mm` (number): Bone loss vs baseline radiograph, if known
- `bop` (boolean): Bleeding on gentle probing
- `implant_length_mm` (number)
- `max_pd_mm` (number)
- `suppuration` (boolean)

### `get_component_compatibility` (~91 tokens)

get component compatibility

Component compatibility for an implant system: its own abutment screw / multi-unit torques and driver, manufacturer-declared cross-system compatibility with sources, and similar interfaces flagged unverified. Costs $0.10 USDC per call (x402, Base).

Input parameters:

- `id` (string, required): Implant id from search_implants
- `platform` (string): Platform name, e.g. 'NP'

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/ryankaye212-tech-probeline/probeline#diagnostics

## Score history

- 2026-11-21: 71
- 2026-11-20: 71
- 2026-11-19: 70
- 2026-11-18: 70
- 2026-11-17: 69
- 2026-11-16: 70
- 2026-11-15: 69
- 2026-11-14: 69
- 2026-11-13: 68
- 2026-11-12: 68
- 2026-11-11: 68
- 2026-11-10: 67

## Common questions

### What is the ProbeLine MCP server?

ProbeLine is an MCP server listed in the public MCP registry as io.github.ryankaye212-tech/probeline. Perio diagnosis and risk, ICD-10-CM, peri-implant status, sourced implant specs. Paid via x402. This page covers its hosted endpoint (https://probeline.io/mcp).

### Is the ProbeLine MCP server safe to use?

ProbeLine scores 71 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 ProbeLine MCP server expose?

ProbeLine exposes 9 tools: search_implants, implant_complications_reference, diagnose_periodontitis, get_implant, identify_implant, and 4 more. Their descriptions and schemas cost roughly 1,212 tokens of context every time the server is loaded.

### Does the ProbeLine MCP server require authentication?

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

### Is the ProbeLine MCP server still maintained?

ProbeLine is still listed as active in the MCP registry. We last reached this channel on 21 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

### What did VerifyMCP test on the ProbeLine MCP server?

VerifyMCP ran 13 checks on ProbeLine, covering TLS certificate, Authorization, HTTPS, HSTS header and 9 more. Supply Chain Security and Provenance & Transparency do not apply to a hosted endpoint, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.

## Links

- Remote endpoint: https://probeline.io/mcp
- Website: https://probeline.io/
- Changelog RSS feed: https://verifymcp.io/servers/ryankaye212-tech-probeline/probeline.xml
- Changelog JSON feed: https://verifymcp.io/servers/ryankaye212-tech-probeline/probeline/changelog.json
- Trust report (JSON): https://verifymcp.io/servers/ryankaye212-tech-probeline/probeline.json
- HTML version of this page: https://verifymcp.io/servers/ryankaye212-tech-probeline/probeline
