WinCC Unified MCP Server
Enables AI assistants to interact with SIEMENS WinCC Unified SCADA systems through their GraphQL API, supporting operations like reading/writing tag values, browsing objects, querying historical data, and managing alarms.
Caution. Specific findings reduced this grade. They are listed on the page. 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
vogler75
Source: Glama
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.
login-userLogs a user in to WinCC Unified using username and password. Stores the session token for subsequent requests. It is optionally, because the MCP server could be started in the way that it is doing automatically a logon with the service account.
browse-objectsQueries tags, elements, types, alarms, logging tags and basically anything that has a configured name, based on the provided filter criteria. Each filter parameter can be an array, and the logical relation between each item is an "OR" relation. However, the logical relation between each filter p…
get-tag-valuesQueries tag values from WinCC Unified. Based on the provided names list. If directRead is true, values are taken directly from PLC. The nameFilters parameter can be used to search for objects either with exact matching, or with wildcards (*, ?). T his parameter can be very powerful: it can be us…
get-logged-tag-valuesQueries logged tag values from the database. Names is a mandatory parameter, each name in this list must either be a LoggingTag name or a Tag name. If either of the parameters startTime, endTime and maxNumberOfValues is not provided, it won't be used for filtering. However, at least one of the…
get-active-alarmsQuery active alarms from the provided systems. The filterString parameter must be a valid ChromQueryLanguage (based on, and very similar to SQL) string, more specifically its WHERE part (without including the WHERE word itself). You can use most of the simple expressions in CQL, that are valid…
get-logged-alarmsQuery logged alarms from the storage system. The filterString parameter must be a valid ChromQueryLanguage (based on, and very similar to SQL) string, more specifically its WHERE part (without including the WHERE word itself). You can use most of the simple expressions in CQL, that are valid i…
write-tag-valuesUpdates tags, based on the provided TagValueInput list. If a TagValueInput does not define a specific timestamp, the optional timestamp parameter will be used as a fallback. If the optional timestamp parameter is not set, the current time will be used instead. Sample timestamp: '2022-04-27T01:30:3…
acknowledge-alarmsAcknowledge one or more alarms. Each alarm identifier must have the name of the configured alarm, and optionally an instanceID, which identifies one active instance of the configured alarm. If the instanceID is 0 or not provided, all instances of the given alarm will be acknowledged. If an ala…
reset-alarmsReset one or more alarms. Each alarm identifier must have the name of the configured alarm, and optionally an instanceID, which identifies one active instance of the configured alarm. If the instanceID is 0 or not provided, all instances of the given alarm will be reset. If an alarm requires s…
Disclosed vulnerabilities in this server's declared npm dependencies (via OSV). Whether each is reachable depends on the installed versions.
mcp-remote exposed to OS command injection via untrusted MCP server connections
@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
GRAPHQL_PWD(Optional) Password for the service account.GRAPHQL_URLRequired. The full URL of your WinCC Unified GraphQL server.GRAPHQL_USRexport ="username1"MCP_PORTThe MCP server will start and listen on port 3000 by default. You can configure the port using the environment variable:Tool 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
9/9 tools missing one or more hints — login-user (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); browse-objects (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); get-tag-values (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint), +6 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.
Tests exist
No test files found
Add tests that exercise each declared tool.
Production dependencies are patched
1 critical, 3 high severity in production deps — mcp-remote@0.1.14 (critical), @modelcontextprotocol/sdk@1.12.1 (high)
Run npm audit fix, or upgrade the affected packages to a non-vulnerable version.
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/vogler75/winccua-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