# OpsDoctor (npm · opsdoctor-mcp)

AI-powered CRM diagnostics, workflow audits, and industry benchmarks for SMBs.

- Trust score: 68/100 (medium)
- Change this week: +4
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-09-20

## Components

- npm · `opsdoctor-mcp`: 68/100 (this document), [markdown](https://verifymcp.io/servers/jhicks935-lab-opsdoctor/opsdoctor-mcp.md), [page](https://verifymcp.io/servers/jhicks935-lab-opsdoctor/opsdoctor-mcp)

## Channel facts

- Registry: `npm`
- Package: `opsdoctor-mcp`
- Version: `2.1.0`
- Transport: `stdio`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, 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 2026-09-20.

- **Supply Chain Security**: 98/100
  - No malware found by supply-chain analysis.
  - No known CVEs affecting this package version or its production dependencies.
  - No install/post-install scripts declared.
  - 59 of 156 dependencies flagged as unhealthy (1 deprecated).
- **Provenance & Transparency**: 19/100
  - Repository check failed: the declared repository URL returned HTTP 404.
  - Provenance check failed: no build-provenance attestation is published.
  - Clear OSI-approved license (Apache-2.0).
  - Actively maintained (last published 10 days ago).
  - Security-disclosure policy not yet verified: we couldn't inspect the source repository.
- **Schema Quality & AI Usability**: 70/100
  - AI-judged instruction clarity (excellent).
  - Context-footprint check failed: tool/resource definitions use about 1051 tokens (~175/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**: 33/100
  - Stability observed for 10 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 6 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 OpsDoctor MCP server?

OpsDoctor runs locally as an npm package, launched with npx -y opsdoctor-mcp. 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 jhicks935-lab-opsdoctor -- npx -y opsdoctor-mcp
```

### Cursor

```json
{
  "mcpServers": {
    "jhicks935-lab-opsdoctor": {
      "command": "npx",
      "args": [
        "-y",
        "opsdoctor-mcp"
      ]
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "jhicks935-lab-opsdoctor": {
      "command": "npx",
      "args": [
        "-y",
        "opsdoctor-mcp"
      ]
    }
  }
}
```

### Codex

```bash
codex mcp add jhicks935-lab-opsdoctor -- npx -y opsdoctor-mcp
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "jhicks935-lab-opsdoctor": {
      "type": "local",
      "command": [
        "npx",
        "-y",
        "opsdoctor-mcp"
      ],
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add jhicks935-lab-opsdoctor --command npx --arg -y --arg opsdoctor-mcp
```

### Hermes

```yaml
mcp_servers:
  jhicks935-lab-opsdoctor:
    command: "npx"
    args: ["-y", "opsdoctor-mcp"]
```

### Netclaw

```json
{
  "McpServers": {
    "jhicks935-lab-opsdoctor": {
      "Transport": "stdio",
      "Command": "npx",
      "Arguments": [
        "-y",
        "opsdoctor-mcp"
      ]
    }
  }
}
```

### Vellum

```bash
assistant mcp add jhicks935-lab-opsdoctor -t stdio -c npx -a -y opsdoctor-mcp
```

### Other

```json
{
  "mcpServers": {
    "jhicks935-lab-opsdoctor": {
      "command": "npx",
      "args": [
        "-y",
        "opsdoctor-mcp"
      ]
    }
  }
}
```

## 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.

### 2026-09-18 (score 68, +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.

### 2026-09-17 (score 67, +3)

- [functional improvement] Stability: unverified → 0.23

### 2026-09-10 (score 64)

First indexed and scored.

## MCP tools (6)

### `run_diagnostic` (~170 tokens)

Diagnose a CRM or operational issue using AI. Provide the CRM name, symptoms, and optionally industry and company context. When an industry is specified, the diagnostic incorporates industry-specific knowledge (common systems, red flags, technology stack). Returns root causes, step-by-step fixes, verification steps, and prevention tips.

Input parameters:

- `client_name` (string): Optional: client or company name for audit history tracking
- `company_context` (string): Optional: company size, team structure, or other relevant context
- `crm_name` (string, required): Name of the CRM system (e.g. HubSpot, Salesforce, Zoho, Go High Level, Dubsado)
- `industry` (string): Optional: industry vertical for context-aware diagnostics
- `symptoms` (string, required): Description of the issue or symptoms being experienced

### `run_workflow_audit` (~300 tokens)

Audit an operational workflow. Supports 4 modes: "quick" (default) — single-pass AI audit returning score and recommendations. "intake" — returns 7 structured discovery questions to gather detailed workflow information (no AI call). "assess" — processes intake answers through AI for dimensional scoring. "followup" — deep-dive second pass incorporating follow-up answers.

Input parameters:

- `client_name` (string): Optional: client or company name for audit history tracking
- `followup_answers` (string): Required when mode is "followup". Answers to the follow-up questions from the assess stage.
- `industry` (string): Industry (e.g. real-estate, insurance, legal, dental, home-services, production, streaming-entertainment)
- `intake_answers` (object): Required when mode is "assess" or "followup". The 7 intake answers.
- `mode` (string): Audit mode. "quick" (default): single-pass audit. "intake": returns structured intake questions. "assess": dimensional scoring from intake answers. "followup": deep-dive from follow-up answers.
- `previous_scores` (object): Required when mode is "followup". Dimension scores from the assess stage.
- `team_size` (string): Approximate team size (e.g. '3 people', '20 employees')
- `workflow_description` (string, required): Description of the workflow or process to audit

### `query_knowledge_base` (~143 tokens)

Look up discovery questions, green/red flag guides, conversation scripts, technology stack references, data governance guidance, and vendor management entries from the OpsDoctor knowledge base. Supports filtering by industry vertical and category. No AI call — instant keyword search over embedded content.

Input parameters:

- `category` (string): Filter by category. Omit or use 'all' to search across all categories.
- `industry` (string): Filter by industry vertical. Omit or use 'all' to search across all industries.
- `query` (string, required): What you want to look up (e.g. 'discovery questions for CRM migration', 'lead management red flags', 'insurance renewal pipeline')

### `get_audit_history` (~100 tokens)

Retrieve past diagnostic and audit results. Filter by client name, result type, or limit. Returns structured history entries with IDs that can be used with generate_report to produce branded PDFs.

Input parameters:

- `client_name` (string): Filter by client name (case-insensitive partial match)
- `limit` (number): Maximum results to return (default: 10, most recent first)
- `type` (string): Filter by result type. Default: "all"

### `generate_report` (~131 tokens)

Generate a branded PDF report from a diagnostic or audit result. Provide an audit_id to load from history, or pass inline result data. Saves the PDF to disk and returns the file path.

Input parameters:

- `audit_id` (string): ID of a history entry (from get_audit_history). Mutually exclusive with inline data.
- `client_name` (string): Optional: client name for the report filename.
- `report_data` (string): JSON string of the structured result. Required if audit_id is not provided.
- `report_type` (string): Required if providing inline data. "diagnostic" or "audit".

### `guided_audit` (~207 tokens)

Run a guided workflow audit through a structured multi-stage discovery process. Stages: "start" returns intake questions, "assess" scores the workflow, "followup" does a deep-dive, "complete" persists the final result. Each stage returns instructions for the next.

Input parameters:

- `client_name` (string): Client or company name for history tracking
- `followup_answers` (string): Required for followup and complete stages. Answers to follow-up questions.
- `industry` (string): Industry vertical (e.g. insurance, dental, real-estate)
- `intake_answers` (object): Required for assess, followup, and complete stages
- `previous_scores` (object): Required for followup and complete stages. Scores from the assess stage.
- `stage` (string, required): Current stage of the guided audit.
- `team_size` (string): Approximate team size
- `workflow_description` (string, required): Description of the workflow being audited (carry forward through all stages)

## Diagnostics

Captured diagnostic sections: Provenance, Dependencies. The full working is on the page: https://verifymcp.io/servers/jhicks935-lab-opsdoctor/opsdoctor-mcp#diagnostics

## Score history

- 2026-09-20: 68
- 2026-09-19: 68
- 2026-09-18: 68
- 2026-09-17: 67
- 2026-09-16: 64
- 2026-09-15: 64
- 2026-09-14: 64
- 2026-09-13: 64
- 2026-09-12: 64
- 2026-09-11: 64
- 2026-09-10: 64

## Common questions

### What is the OpsDoctor MCP server?

OpsDoctor is an MCP server listed in the public MCP registry as io.github.jhicks935-lab/opsdoctor. AI-powered CRM diagnostics, workflow audits, and industry benchmarks for SMBs. This page covers its npm package (opsdoctor-mcp).

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

OpsDoctor scores 68 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 20 September 2026. It declares no install or post-install scripts. 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 OpsDoctor MCP server expose?

OpsDoctor exposes 6 tools: run_diagnostic, run_workflow_audit, query_knowledge_base, get_audit_history, generate_report, guided_audit. Their descriptions and schemas cost roughly 1,051 tokens of context every time the server is loaded.

### Is the OpsDoctor MCP server still maintained?

OpsDoctor is still listed as active in the MCP registry. We last reached this channel on 20 September 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

### What licence is the OpsDoctor MCP server under?

OpsDoctor declares the Apache-2.0 licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.

## Links

- npm package: https://www.npmjs.com/package/opsdoctor-mcp
- Socket report: https://socket.dev/npm/package/opsdoctor-mcp
- Website: https://opsdoctor.app/
- Changelog RSS feed: https://verifymcp.io/servers/jhicks935-lab-opsdoctor/opsdoctor-mcp.xml
- Changelog JSON feed: https://verifymcp.io/servers/jhicks935-lab-opsdoctor/opsdoctor-mcp.json
- HTML version of this page: https://verifymcp.io/servers/jhicks935-lab-opsdoctor/opsdoctor-mcp