# ConnectWise CPQ (oci · ghcr.io/wyre-ai/connectwise-cpq-mcp:v1.0.5)

MCP server for ConnectWise CPQ (Sell) — quotes, line items, customers, terms, and templates.

- Trust score: 54/100 (low)
- Change this week: +3
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-09-20

## Components

- oci · `ghcr.io/wyre-ai/connectwise-cpq-mcp:v1.0.5`: 54/100 (this document), [markdown](https://verifymcp.io/servers/wyre-ai-connectwise-cpq-mcp/ghcr-io-wyre-ai-connectwise-cpq-mcp-v1-0-5.md), [page](https://verifymcp.io/servers/wyre-ai-connectwise-cpq-mcp/ghcr-io-wyre-ai-connectwise-cpq-mcp-v1-0-5)

## Channel facts

- Registry: `oci`
- Package: `ghcr.io/wyre-ai/connectwise-cpq-mcp:v1.0.5`
- 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**: 0/100
  - Malware scan not yet available for this package.
  - Known CVEs could not be checked: this artifact ships no SBOM, so there is no dependency list to read. Publishing one would let us assess it.
  - Install-script risk not yet assessed.
  - Dependency health could not be checked: this artifact ships no SBOM, so there is no dependency list to read. Publishing one would let us assess it.
- **Provenance & Transparency**: 45/100
  - Source repository is publicly reachable at the declared URL.
  - Provenance check failed: no build-provenance attestation is published.
  - Clear OSI-approved license (Apache-2.0).
  - Actively maintained (last published 25 days ago).
  - Disclosure check failed: no security disclosure policy was found in the source repository.
- **Schema Quality & AI Usability**: 87/100
  - 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).
  - AI-judged instruction clarity (excellent).
  - Tool/resource definitions use about 2587 tokens (~99/item across 26 items; 25 tools + 1 resources), lean.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 83/100
  - Stability observed for 25 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.
  - All 5 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation.
  - An AI judge read all 26 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a current MCP spec version (2026-07-28).
  - Supports UI / widget rendering.

**Unverified: 1 category.** A category scored 0 because we could not verify it: a data source with nothing on this package, evidence we could not reach, or a check we could not run. We only credit what we can confirm.

## Install

### How do I install the ConnectWise CPQ MCP server?

ConnectWise CPQ runs locally as a container image, launched with docker run --rm -i ghcr.io/wyre-ai/connectwise-cpq-mcp:v1.0.5. Ready-made configuration for Claude, Cursor, VS Code, Codex and 3 more is on this page, copied from each client's own documentation.

### Claude

```bash
claude mcp add wyre-ai-connectwise-cpq-mcp -- docker run --rm -i ghcr.io/wyre-ai/connectwise-cpq-mcp:v1.0.5
```

### Cursor

```json
{
  "mcpServers": {
    "wyre-ai-connectwise-cpq-mcp": {
      "command": "docker",
      "args": [
        "run",
        "--rm",
        "-i",
        "ghcr.io/wyre-ai/connectwise-cpq-mcp:v1.0.5"
      ]
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "wyre-ai-connectwise-cpq-mcp": {
      "command": "docker",
      "args": [
        "run",
        "--rm",
        "-i",
        "ghcr.io/wyre-ai/connectwise-cpq-mcp:v1.0.5"
      ]
    }
  }
}
```

### Codex

```bash
codex mcp add wyre-ai-connectwise-cpq-mcp -- docker run --rm -i ghcr.io/wyre-ai/connectwise-cpq-mcp:v1.0.5
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "wyre-ai-connectwise-cpq-mcp": {
      "type": "local",
      "command": [
        "docker",
        "run",
        "--rm",
        "-i",
        "ghcr.io/wyre-ai/connectwise-cpq-mcp:v1.0.5"
      ],
      "enabled": true
    }
  }
}
```

### Hermes

```yaml
mcp_servers:
  wyre-ai-connectwise-cpq-mcp:
    command: "docker"
    args: ["run", "--rm", "-i", "ghcr.io/wyre-ai/connectwise-cpq-mcp:v1.0.5"]
```

### Netclaw

```json
{
  "McpServers": {
    "wyre-ai-connectwise-cpq-mcp": {
      "Transport": "stdio",
      "Command": "docker",
      "Arguments": [
        "run",
        "--rm",
        "-i",
        "ghcr.io/wyre-ai/connectwise-cpq-mcp:v1.0.5"
      ]
    }
  }
}
```

### Other

```json
{
  "mcpServers": {
    "wyre-ai-connectwise-cpq-mcp": {
      "command": "docker",
      "args": [
        "run",
        "--rm",
        "-i",
        "ghcr.io/wyre-ai/connectwise-cpq-mcp:v1.0.5"
      ]
    }
  }
}
```

## 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.

### 2026-09-19 (score 54, +1)

No change was recorded against any check on this day. Stability & Change Management went from 77 to 80. That category is still filling its 30-day observation window: 23 days of observed history at the previous scan, 24 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-17 (score 53, +1)

No change was recorded against any check on this day. Stability & Change Management went from 70 to 73. That category is still filling its 30-day observation window: 21 days of observed history at the previous scan, 22 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-15 (score 52, +1)

No change was recorded against any check on this day. Stability & Change Management went from 63 to 67. That category is still filling its 30-day observation window: 19 days of observed history at the previous scan, 20 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-12 (score 51, +1)

No change was recorded against any check on this day. Stability & Change Management went from 53 to 57. That category is still filling its 30-day observation window: 16 days of observed history at the previous scan, 17 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-10 (score 50, +1)

No change was recorded against any check on this day. Stability & Change Management went from 47 to 50. That category is still filling its 30-day observation window: 14 days of observed history at the previous scan, 15 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-08 (score 49, +1)

No change was recorded against any check on this day. Stability & Change Management went from 40 to 43. That category is still filling its 30-day observation window: 12 days of observed history at the previous scan, 13 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-06 (score 48, +1)

No change was recorded against any check on this day. Stability & Change Management went from 33 to 37. That category is still filling its 30-day observation window: 10 days of observed history at the previous scan, 11 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-04 (score 47, +1)

No change was recorded against any check on this day. Stability & Change Management went from 27 to 30. That category is still filling its 30-day observation window: 8 days of observed history at the previous scan, 9 at this one. The score rises as the window fills, whether or not the server changes.

## MCP tools (25)

### `cpq_test_connection` (~23 tokens)

Verify ConnectWise CPQ credentials and report the authenticated API user.

### `cpq_search_quotes` (~201 tokens)

Search quotes with Manage-style conditions, field selection, and paging. With no conditions it asks for (or defaults to) a created-since date range.

Input parameters:

- `conditions` (string): Manage-style condition string. Strings "double-quoted", booleans True/False, dates bracketed DATE-ONLY (time components are rejected): createDate >= [2026-07-01]. Example: idQuote = "<guid>" and isAr…
- `includeFields` (string): Comma-separated list of fields to return. Strongly encouraged — QuoteView has 204 properties (e.g. id,name,quoteNumber,quoteVersion,quoteTotal).
- `page` (number): 1-based page number (default 1).
- `pageSize` (number): Results per page (default 100, max 1000).
- `showAllVersions` (boolean): Include every quote version, not just the latest (default false).

### `cpq_get_quote` (~37 tokens)

Get a quote by GUID id (full QuoteView) — renders the quote card.

Input parameters:

- `id` (string, required): Quote GUID id.

### `cpq_get_quote_versions` (~62 tokens)

List all versions of a quote number, or get the latest/a specific version.

Input parameters:

- `quoteNumber` (number, required): Integer quote number.
- `version` (number|string): Optional: 'latest' or a version integer. Omit to list all versions.

### `cpq_search_quote_items` (~199 tokens)

Search quote line items. Filter by quote or tab via conditions (idQuote = "<guid>" or idQuoteTabs = "<guid>").

Input parameters:

- `conditions` (string): Manage-style condition string. Strings "double-quoted", booleans True/False, dates bracketed DATE-ONLY (time components are rejected): createDate >= [2026-07-01]. Example: idQuote = "<guid>" and isAr…
- `includeFields` (string): Comma-separated list of fields to return. Strongly encouraged — QuoteView has 204 properties (e.g. id,name,quoteNumber,quoteVersion,quoteTotal).
- `page` (number): 1-based page number (default 1).
- `pageSize` (number): Results per page (default 100, max 1000).
- `showAllVersions` (boolean): Include every quote version, not just the latest (default false).

### `cpq_get_quote_item` (~30 tokens)

Get a quote line item by id.

Input parameters:

- `id` (string, required): Quote item GUID id.

### `cpq_list_quote_customers` (~32 tokens)

List the customer records attached to a quote.

Input parameters:

- `quoteId` (string, required): Quote GUID id.

### `cpq_search_quote_tabs` (~190 tokens)

Search quote tabs/sections. Filter by quote via conditions (idQuote = "<guid>").

Input parameters:

- `conditions` (string): Manage-style condition string. Strings "double-quoted", booleans True/False, dates bracketed DATE-ONLY (time components are rejected): createDate >= [2026-07-01]. Example: idQuote = "<guid>" and isAr…
- `includeFields` (string): Comma-separated list of fields to return. Strongly encouraged — QuoteView has 204 properties (e.g. id,name,quoteNumber,quoteVersion,quoteTotal).
- `page` (number): 1-based page number (default 1).
- `pageSize` (number): Results per page (default 100, max 1000).
- `showAllVersions` (boolean): Include every quote version, not just the latest (default false).

### `cpq_list_quote_terms` (~130 tokens)

List payment/financing term options on a quote.

Input parameters:

- `conditions` (string): Manage-style condition string. Strings "double-quoted", booleans True/False, dates bracketed DATE-ONLY (time components are rejected): createDate >= [2026-07-01]. Example: idQuote = "<guid>" and isAr…
- `page` (number): 1-based page number (default 1).
- `pageSize` (number): Results per page (default 100, max 1000).
- `quoteId` (string, required): Quote GUID id.

### `cpq_list_templates` (~21 tokens)

List quote templates (the source objects for quote creation).

### `cpq_list_tax_codes` (~114 tokens)

List tax codes and rates.

Input parameters:

- `conditions` (string): Manage-style condition string. Strings "double-quoted", booleans True/False, dates bracketed DATE-ONLY (time components are rejected): createDate >= [2026-07-01]. Example: idQuote = "<guid>" and isAr…
- `page` (number): 1-based page number (default 1).
- `pageSize` (number): Results per page (default 100, max 1000).

### `cpq_list_recurring_revenues` (~117 tokens)

List recurring-revenue period definitions.

Input parameters:

- `conditions` (string): Manage-style condition string. Strings "double-quoted", booleans True/False, dates bracketed DATE-ONLY (time components are rejected): createDate >= [2026-07-01]. Example: idQuote = "<guid>" and isAr…
- `page` (number): 1-based page number (default 1).
- `pageSize` (number): Results per page (default 100, max 1000).

### `cpq_list_users` (~120 tokens)

List CPQ users (API users, approvers, admins).

Input parameters:

- `conditions` (string): Manage-style condition string. Strings "double-quoted", booleans True/False, dates bracketed DATE-ONLY (time components are rejected): createDate >= [2026-07-01]. Example: idQuote = "<guid>" and isAr…
- `page` (number): 1-based page number (default 1).
- `pageSize` (number): Results per page (default 100, max 1000).

### `cpq_create_quote_from_template` (~136 tokens)

Create a new quote by copying a template or existing quote — the API's only quote create path. Provide templateId, or templateName to resolve (ambiguous names are elicited). newName renames the copy via a follow-up PATCH.

Input parameters:

- `newName` (string): Optional name for the new quote (applied via follow-up PATCH).
- `templateId` (string): GUID of the template (or quote) to copy.
- `templateName` (string): Template name to resolve when the GUID is unknown. Ambiguous matches are elicited; without elicitation support, candidates are listed as an error.

### `cpq_update_quote` (~152 tokens)

⚠ HIGH-IMPACT. Update quote fields (name, status, dates, custom fields) via JSON Patch. Changes to quoteStatus, isArchive, isLost, expirationDate, orderPorter* or approval fields can flip customer-facing/workflow state — status, archive, and order-porter changes affect what the customer sees. Confirm with the user before invoking.

Input parameters:

- `fields` (object): Partial object of fields to set — each entry becomes an RFC 6902 replace op. Use this OR `patch`, not both.
- `id` (string, required): Quote GUID id.
- `patch` (array): Raw RFC 6902 JSON Patch operations. Use this OR `fields`, not both.

### `cpq_create_quote_item` (~102 tokens)

Add a line item to a quote tab. If idQuoteTabs is omitted, a single tab is used automatically and multiple tabs prompt a selection.

Input parameters:

- `idQuote` (string, required): Quote GUID id.
- `idQuoteTabs` (string): Quote tab GUID id (elicited if omitted and the quote has several tabs).
- `item` (object, required): Line item fields (e.g. mfgPartNumber, description, quantity, basePrice, cost).

### `cpq_update_quote_item` (~95 tokens)

Update a quote line item (pricing, quantity, flags) via JSON Patch.

Input parameters:

- `fields` (object): Partial object of fields to set — each entry becomes an RFC 6902 replace op. Use this OR `patch`, not both.
- `id` (string, required): Quote item GUID id.
- `patch` (array): Raw RFC 6902 JSON Patch operations. Use this OR `fields`, not both.

### `cpq_update_quote_customer` (~101 tokens)

Update a customer record on a quote via JSON Patch.

Input parameters:

- `fields` (object): Partial object of fields to set — each entry becomes an RFC 6902 replace op. Use this OR `patch`, not both.
- `id` (string, required): Customer record GUID id.
- `patch` (array): Raw RFC 6902 JSON Patch operations. Use this OR `fields`, not both.
- `quoteId` (string, required): Quote GUID id.

### `cpq_create_quote_term` (~56 tokens)

Add a payment/financing term option to a quote.

Input parameters:

- `quoteId` (string, required): Quote GUID id.
- `term` (object, required): Term fields (e.g. name, periods, interestRate, paymentAmount).

### `cpq_update_quote_term` (~98 tokens)

Update a quote term via JSON Patch.

Input parameters:

- `fields` (object): Partial object of fields to set — each entry becomes an RFC 6902 replace op. Use this OR `patch`, not both.
- `id` (string, required): Quote term GUID id.
- `patch` (array): Raw RFC 6902 JSON Patch operations. Use this OR `fields`, not both.
- `quoteId` (string, required): Quote GUID id.

### `cpq_delete_quote_item` (~101 tokens)

⚠ DESTRUCTIVE — IRREVERSIBLE. Permanently delete a quote line item. Confirm with the user before invoking.

Input parameters:

- `confirm_destructive_action` (boolean): Explicit confirmation for this irreversible action. Required only when the client declared no elicitation capability and therefore cannot be prompted (e.g. the gateway); interactive clients are promp…
- `id` (string, required): Quote item GUID id.

### `cpq_delete_quote_term` (~112 tokens)

⚠ DESTRUCTIVE — IRREVERSIBLE. Permanently delete a quote term option. Confirm with the user before invoking.

Input parameters:

- `confirm_destructive_action` (boolean): Explicit confirmation for this irreversible action. Required only when the client declared no elicitation capability and therefore cannot be prompted (e.g. the gateway); interactive clients are promp…
- `id` (string, required): Quote term GUID id.
- `quoteId` (string, required): Quote GUID id.

### `cpq_delete_quote_customer` (~112 tokens)

⚠ DESTRUCTIVE — IRREVERSIBLE. Remove a customer record from a quote. Confirm with the user before invoking.

Input parameters:

- `confirm_destructive_action` (boolean): Explicit confirmation for this irreversible action. Required only when the client declared no elicitation capability and therefore cannot be prompted (e.g. the gateway); interactive clients are promp…
- `id` (string, required): Customer record GUID id.
- `quoteId` (string, required): Quote GUID id.

### `cpq_delete_quote_version` (~115 tokens)

⚠ DESTRUCTIVE — IRREVERSIBLE. Permanently delete a specific version of a quote. Confirm with the user before invoking.

Input parameters:

- `confirm_destructive_action` (boolean): Explicit confirmation for this irreversible action. Required only when the client declared no elicitation capability and therefore cannot be prompted (e.g. the gateway); interactive clients are promp…
- `quoteNumber` (number, required): Integer quote number.
- `quoteVersion` (number, required): Integer version to delete.

### `cpq_delete_quote` (~108 tokens)

⚠ DESTRUCTIVE — IRREVERSIBLE. Permanently delete a quote and all of its line items, tabs, and terms. Confirm with the user before invoking.

Input parameters:

- `confirm_destructive_action` (boolean): Explicit confirmation for this irreversible action. Required only when the client declared no elicitation capability and therefore cannot be prompted (e.g. the gateway); interactive clients are promp…
- `id` (string, required): Quote GUID id.

## Diagnostics

Captured diagnostic sections: Provenance. The full working is on the page: https://verifymcp.io/servers/wyre-ai-connectwise-cpq-mcp/ghcr-io-wyre-ai-connectwise-cpq-mcp-v1-0-5#diagnostics

## Score history

- 2026-09-20: 54
- 2026-09-19: 54
- 2026-09-18: 53
- 2026-09-17: 53
- 2026-09-16: 52
- 2026-09-15: 52
- 2026-09-14: 51
- 2026-09-13: 51
- 2026-09-12: 51
- 2026-09-11: 50
- 2026-09-10: 50
- 2026-09-09: 49
- 2026-09-08: 49
- 2026-09-07: 48
- 2026-09-06: 48
- 2026-09-05: 47
- 2026-09-04: 47
- 2026-09-03: 46
- 2026-09-02: 43
- 2026-09-01: 43
- 2026-08-31: 43
- 2026-08-30: 43
- 2026-08-29: 43
- 2026-08-28: 43
- 2026-08-27: 43
- 2026-08-26: 43

## Common questions

### What is the ConnectWise CPQ MCP server?

ConnectWise CPQ is an MCP server listed in the public MCP registry as io.github.WYRE-AI/connectwise-cpq-mcp. MCP server for ConnectWise CPQ (Sell), quotes, line items, customers, terms, and templates. This page covers its container image (ghcr.io/wyre-ai/connectwise-cpq-mcp:v1.0.5).

### Is the ConnectWise CPQ MCP server safe to use?

ConnectWise CPQ scores 54 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 ConnectWise CPQ MCP server expose?

ConnectWise CPQ exposes 25 tools: cpq_test_connection, cpq_search_quotes, cpq_get_quote, cpq_get_quote_versions, cpq_search_quote_items, and 20 more. Their descriptions and schemas cost roughly 2,564 tokens of context every time the server is loaded.

### Is the ConnectWise CPQ MCP server still maintained?

ConnectWise CPQ 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 ConnectWise CPQ MCP server under?

ConnectWise CPQ 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

- Repository: https://github.com/WYRE-AI/connectwise-cpq-mcp
- Changelog RSS feed: https://verifymcp.io/servers/wyre-ai-connectwise-cpq-mcp/ghcr-io-wyre-ai-connectwise-cpq-mcp-v1-0-5.xml
- Changelog JSON feed: https://verifymcp.io/servers/wyre-ai-connectwise-cpq-mcp/ghcr-io-wyre-ai-connectwise-cpq-mcp-v1-0-5.json
- HTML version of this page: https://verifymcp.io/servers/wyre-ai-connectwise-cpq-mcp/ghcr-io-wyre-ai-connectwise-cpq-mcp-v1-0-5