← Index

ConnectWise RMM MCP

io.github.Servosity/connectwise-rmm-mcpv0.1.1Other

ConnectWise RMM (Asio) MCP: offline agents, patch posture, and script runs across every client.

The current version, v0.1.1, was published to the official MCP registry on 2026-10-16. It is distributed through a declared package, filed under Other by this index, and declares 9 environment variables. Removals and unreachable sources are measured across every server this index tracks, contract drift across the servers that answer in consecutive snapshots; the index's current counts put this record in context.

In-path gate · all MCP tools

Using ConnectWise RMM MCP in Claude, Cursor, Gemini CLI, Cline, or Zed?

MCP tool contracts can change remotely with no version bump. The mcpindex gate pins each contract and HOLDs the call when it drifts-before your agent acts. Zero credentials. This is not the package install for this server itself (use Install this server for that).

Install the mcpindex gate (one command)

Rewrites your MCP host config so each server launches behind the gate. Inspect first: curl -fsSL https://mcpindex.ai/install.sh | less

uv tool install mcpindex-gate && mcpindex-config-wire
Trust verdict · v1 advisory · method
REVIEWstatus: PARTIALfresh until 2026-11-14 21:05 UTC
screened 2026-10-15tier: scannedgranularity: description-levelsource: registry

Semantic screen found no manipulation pattern in the description. Conformance probe not yet run.

mcpindex.integrity.descriptionpassINFO

evidence“Tool runs scripts on clients, no hidden instructions.”via static_description

Limits of this verdict
  • - Semantic screen only - the deterministic conformance probe has not run on this server
  • - Confidence is reported but not yet calibrated (v1)
  • - Screen reads the tool description, not the live behavior
  • - advisory
  • - registry description only no input schema
  • - screen model 8b
  • - The registry listing (version, packages, links) changed after this screen ran - the description we assessed did not

Semantic screen: an LLM judge reads the tool description for hidden instructions (status PARTIAL). A pass means the description is not lying, not that the tool is safe: a high-capability tool with an honest description still warrants caution. The deterministic conformance probe has not been run on this server yet, so the screen here is semantic-only. Posture: advisory. Confidences are reported but not yet calibrated (calibrated=false at v1). Full verdict history is not shown on this page.

Own this server? Test a description on the public screen → It is a separate check from the verdict above, so the two can differ.

That verdict was true at screening time (snapshot 2026-10-20).

Contracts can change after screening, with no version bump. The gate pins ConnectWise RMM MCP’s tool contracts on first sight and holds any silent change before your agent acts - the check that keeps being true on Tuesday.

See your first HOLD in 2 minutes →

Related: how to trust an MCP server · screen before install · silent contract drift

Cite this record

People vet a server before wiring it in. One line on your project site or docs answers that with an independent record: screening verdict, registry provenance, contract drift history. It stays current as new screens and drift events land.

Markdown
[Independent trust record for ConnectWise RMM MCP](https://mcpindex.ai/server/io-github-servosity-connectwise-rmm-mcp) - screening verdict, registry provenance, and contract drift monitoring.
HTML
<a href="https://mcpindex.ai/server/io-github-servosity-connectwise-rmm-mcp">Independent trust record for ConnectWise RMM MCP</a> - screening verdict, registry provenance, and contract drift monitoring.
Embed this badge

A live verdict badge for your README or listing. It reflects the current screen, links back here, and updates when the verdict does.

Markdown
[![mcpindex](https://mcpindex.ai/api/v1/badge/io-github-servosity-connectwise-rmm-mcp)](https://mcpindex.ai/server/io-github-servosity-connectwise-rmm-mcp)
HTML
<a href="https://mcpindex.ai/server/io-github-servosity-connectwise-rmm-mcp"><img src="https://mcpindex.ai/api/v1/badge/io-github-servosity-connectwise-rmm-mcp" alt="mcpindex verdict" height="20" /></a>
Environment variables
CONNECTWISE_RMM_CLIENT_ID
requiredsecret

ConnectWise RMM (Asio) API client ID from Integrations > API Access in the ConnectWise portal. Its prefix picks the region (0e30 North America, 0e31 Europe, 0e32 Australia).

CONNECTWISE_RMM_CLIENT_SECRET
requiredsecret

Client secret paired with the API client ID. The connector exchanges the pair for a short-lived bearer token.

CONNECTWISE_RMM_OAUTH_SCOPE

Space-separated scopes to request. Leave blank to request every scope the connector uses; if your API key lacks one, the whole token request fails, so paste the line `connectwise-rmm-cli scopes` prints.

CONNECTWISE_RMM_BASE_URL

Leave blank to follow the client ID's region (NA openapi.service.itsupport247.net, EU openapi.service.euplatform.connectwise.com, AU openapi.service.auplatform.connectwise.com). Set it only to pin a different host.

CONNECTWISE_RMM_TOKEN_URL

Leave blank to mint tokens at <base URL>/v1/token for your region. Set it only if ConnectWise gives you a different token endpoint.

CONNECTWISE_RMM_USER_AGENT

Overrides the User-Agent the CLI sends on ConnectWise RMM requests. Leave blank to use the CLI's own.

CONNECTWISE_RMM_MCP_READ_ONLY

Set to 1 to make the MCP server read-only: it drops its write tools (run, sync; import is never an MCP tool) and refuses any non-GET API call. Leave blank for the full tool set.

CONNECTWISE_RMM_MCP_HTTP_TOKEN
secret

Required only when running the MCP server with --transport http (a remote or hosted deployment). Callers must send a matching Authorization: Bearer header. Not needed for the default local stdio transport that Claude Desktop uses.

PRINTING_PRESS_CLIENT_PROFILE
secret

Leave blank. This connector registers no tenant-gated profile source, so the value is read but changes nothing; one MCP server serves the one API key it is given.

MCP quality score · maturity, not trust · methodology
freshness
25
completeness
20
installability
25
documentation
15
stability
5
Alternatives in Other