supcon-international/node-red-mcp-server (supcon-international/node-red-mcp-server) is an MCP server listed on the M8ven Trust Index. It scores 6 out of 100, grade F. It declares 27 tools. No publisher has claimed this listing.
Model Context Protocol (MCP) server for interacting with Node-RED
Warning. Serious findings were identified. Review the full report before connecting. Grades reflect the full trust pyramid: code, verification depth, and reputation. New projects cap at C until adoption is earned.
How we verified
Verified is a snapshot. Live keeps it current, and builds your track record.
⚡ Connect GitHub → continuous verification on every pushwhy connect →Who stands behind it
supcon-international
Source: Glama · also listed on npm
Claim it to get a verified publisher badge, a free copy of our full audit findings, and direct contact for any high-priority issues we find. Or connect your repo for our deepest verification, Live Monitored: read-only, revoke anytime. What we access →
Install from
The grade above is for the source repository. Registries can serve a different version, so we mark the ones we were not able to read.
These names and descriptions are the publisher's own, read from the source code. We print them as written. Our assessment is the findings above, not this list.
backup-flowsCreate a named backup of current Node-RED flows with optional reason
list-backupsList all available flow backups with details
get-backup-flowsGet the specific flows content from a backup by name
backup-healthCheck backup system health and provide recommendations
get-flowsRetrieves the complete list of flows from the Node-RED instance.
update-flowsUpdates the entire flow configuration of the Node-RED instance. Args: flowsJson (e.g.'[{type: 'tab', id: '396c2376c693d', label: 'Sheet 1'}]')
get-flowRetrieves the configuration of a specific flow by its ID. Args: id (e.g.'396c237c693dc')
update-flowUpdates the configuration of a specific flow by its id. Args: id (e.g.'396c237c693dc') flowJson (e.g.'{id: '91ad456e52b8', label: 'Sheet 1', nodes: [], configs: []}')
list-tabsLists all flow tabs (workspaces) in the Node-RED instance.
create-flowCreates a new flow in the Node-RED instance. Args: flowJson (e.g.'{id: '91ad456e52b8', label: 'Sheet 1', nodes: [], configs: []}')
delete-flowDeletes a specific flow from the Node-RED instance by its ID. Args: id (e.g.'396c237c693dc')
get-flows-stateRetrieves the current deployment state of all flows in the Node-RED instance. This tool returns the runtime state of the flows, including their active status.
set-flows-stateUpdates the deployment state of all flows in the Node-RED instance.
get-flows-formattedRetrieves a human-readable, formatted list of all flows in the Node-RED instance.
visualize-flowsGenerates a graph-like visualization of the flows in the Node-RED instance.
injectTriggers an inject node in the Node-RED instance by its ID. This tool simulates an input event for the specified inject node.
get-available-nodesRetrieves a list of all installed nodes their information (name,help,module) in the Node-RED instance.
get-node-detailed-infoRetrieves source code about a specific node module by its name. Args: module (e.g.'node-red/inject')
get-node-set-detailed-infoRetrieves source code about a specific node module by its name. Args: module (e.g.'@supcon-international/node-red-function-gpt-with-memory') set (e.g.'function-gpt')
install-node-moduleInstall a specific node module in the Node-RED instance. Args: module (e.g.'node-red-dashboard')
toggle-node-moduleEnables or disables a specific node module in the Node-RED instance. Args: module (e.g.'node-red/inject') enabled (e.g.'true')
toggle-node-module-setEnables or disables a specific node module set in the Node-RED instance. Args: module (e.g.'@supcon-international/node-red-function-gpt-with-memory') set (e.g.'function-gpt') enabled (e.g.'true')
find-nodes-by-typeSearches for nodes in the Node-RED instance by their type. Args: nodeType (e.g.'inject')
search-nodesSearches for nodes in the Node-RED instance by a query string, optionally filtering by a specific property. Args: query (e.g.'inject') property (e.g.'type') (optional)
get-settingsRetrieves the runtime settings of the Node-RED instance. This tool returns the current configuration settings of the Node-RED server.
get-diagnosticsRetrieves diagnostic information from the Node-RED instance. This tool returns detailed runtime diagnostics, including system status and performance metrics.
api-helpDisplays a help table of all available Node-RED Admin API methods, including their implementation status in the MCP server. This tool provides a quick reference for available API endpoints.
Disclosed vulnerabilities in this server's declared npm dependencies (via OSV). Whether each is reachable depends on the installed versions.
@modelcontextprotocol/sdk has cross-client data leak via shared server/transport instance reuse
Anthropic's MCP TypeScript SDK has a ReDoS vulnerability
Model Context Protocol (MCP) TypeScript SDK does not enable DNS rebinding protection by default
axios Vulnerable to Full Man-in-the-Middle via Prototype Pollution Gadget in `config.proxy`
axios Vulnerable to Credential Theft and Response Hijacking via Prototype Pollution Gadget in Config Merge
MCP_BACKUP_PATHCustom backup directory pathMCP_MAX_BACKUPSMaximum number of backups to keepTool annotations
No tools have read-only/destructive annotations
Add readOnlyHint or destructiveHint annotations to every tool so hosts can warn users before invoking.
All four hints declared on every tool
27/27 tools missing one or more hints — backup-flows (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); list-backups (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); get-backup-flows (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint), +24 more. OpenAI's directory rejects tools where any of the four hints are missing or non-boolean.
For every tool, set all four hints (readOnlyHint, destructiveHint, idempotentHint, openWorldHint) to explicit true/false values that match the handler’s actual behaviour.
Destructive tools are labelled
1 tool perform destructive updates without destructiveHint — backup-flows deletes at line 349 (fs.unlink(path.join(backupDir, backup.filename)))
Add destructiveHint:true to any tool whose handler calls .delete(), .upsert(), .update(), unlink, rm, DELETE, DROP, REPLACE INTO, or any operation that overwrites existing data.
Descriptions match behaviour
4 tools describe read intent but their handlers mutate — list-backups (line 235: fs.mkdir(backupDir, { recursive: true })); get-backup-flows (line 235: fs.mkdir(backupDir, { recursive: true })); backup-health (line 235: fs.mkdir(backupDir, { recursive: true }))
Rename the tool, rewrite the description, or move the side-effect into a separate clearly-named tool.
Tool inputs are validated
24/27 tool handlers declare input schemas (89%)
Declare an inputSchema with zod/joi/yup on every tool definition.
Tests exist
No test files found
Add tests that exercise each declared tool.
Production dependencies are patched
0 critical, 15 high severity in production deps — @modelcontextprotocol/sdk@1.11.0 (high), @modelcontextprotocol/sdk@1.11.0 (high)
Run npm audit fix, or upgrade the affected packages to a non-vulnerable version.
Tool description accuracy
4 tools have description/behavior mismatches: list-backups: description implies read-only but handler writes/deletes/executes; get-backup-flows: description implies read-only but handler writes/deletes/executes; backup-health: description implies read-only but handler writes/deletes/executes
Update tool descriptions to accurately reflect all capabilities — especially write, delete, or execute operations.
Claim the listing to review these findings one by one and send us a correction where you disagree, straight to the team. Claiming also means we tell you when the grade moves, and reach you first if we find anything urgent.
[](https://m8ven.ai/mcp/supcon-international/node-red-mcp-server)?variant=verified from the URL.Vetting this one by hand? Tool Check is an MCP that scores other MCPs. Add it once and ask Claude, ChatGPT, or any MCP client to grade a server, surface CVEs, check the publisher, and suggest safer alternatives — before you install.
https://m8ven.ai/api/mcp/tool-check