Statistical Process Control & Anomaly Alerts MCP server
Commit Nov 13, 2026Monitors metric streams using Shewhart charts and run rules to detect genuine statistical drift and process anomalies.
Also known as Saify-Technologies/saifs-ai-mcps-docs, process-control
- Stars
- 4
- Tools
- 5
- Downloads, 30 days
- —
- Latest version
- 1.0.1
- Last commit
- Nov 13, 2026
- License
- MIT
What is Statistical Process Control & Anomaly Alerts MCP?
Statistical Process Control & Anomaly Alerts monitors metric streams using Shewhart charts and run rules to detect genuine statistical drift and process anomalies. It exposes 5 tools, such as detect_shift, explain_signal, monitor_metric.
Summary generated from the project's README
About Statistical Process Control & Anomaly Alerts MCP server
Monitoring metric streams for genuine statistical drift and process anomalies is the primary function of this remote MCP server. It allows developers and operators to track various data points such as error rates, support response times, delivery SLAs, and conversion rates using advanced statistical methods. By utilizing Shewhart charts alongside Western Electric and Nelson run rules, the system identifies out-of-control signals while avoiding false alarms.
Users connect to the service via Streamable HTTP, making it accessible to Claude Desktop, Claude Code, and VS Code without local installation. The server requires OAuth 2.1 authentication with PKCE, which prompts a sign-in page during the initial setup. It provides specialized tools like detect_shift for identifying small sustained drifts using CUSUM and EWMA, monitor_metric for verdict reporting, and set_control_limits to establish a stable baseline using three sigma limits. The system acts as a decision support tool where human operators maintain final control over all actions.
What you can do with it
- 1Detecting subtle metric driftsAsk the AI to identify small, sustained changes in data that standard charts might overlook.
- 2Establishing statistical baselinesRequest the calculation of control limits based on a stable period of performance.
- 3Interpreting statistical alertsGet a detailed explanation of why a specific statistical rule was triggered.
- 4Continuous process monitoringSet up an automated watch on a specific process to receive alerts when rules are violated.
Written from the project's README. Every use case is checked against a quote from it.
How to install Statistical Process Control & Anomaly Alerts MCP
Formats verified 10 Nov 2026Add to CursorAdd to GooseInstall Statistical Process Control & Anomaly Alerts MCP in Claude Code
$ claude mcp add --transport http process-control https://process-monitor-mcp.saifs.ai/mcpInstall Statistical Process Control & Anomaly Alerts MCP in Cursor
~/.cursor/mcp.json
{
"mcpServers": {
"process-control": {
"url": "https://process-monitor-mcp.saifs.ai/mcp"
}
}
}Install Statistical Process Control & Anomaly Alerts MCP in VS Code
.vscode/mcp.json
{
"servers": {
"process-control": {
"type": "http",
"url": "https://process-monitor-mcp.saifs.ai/mcp"
}
}
}Install Statistical Process Control & Anomaly Alerts MCP in VS Code CLI
$ code --add-mcp '{"name":"process-control","type":"http","url":"https://process-monitor-mcp.saifs.ai/mcp"}'Install Statistical Process Control & Anomaly Alerts MCP in Codex
$ codex mcp add process-control --url https://process-monitor-mcp.saifs.ai/mcpInstall Statistical Process Control & Anomaly Alerts MCP in Codex config.toml
~/.codex/config.toml
[mcp_servers.process-control] url = "https://process-monitor-mcp.saifs.ai/mcp"
Install Statistical Process Control & Anomaly Alerts MCP in Gemini CLI
$ gemini mcp add -s user --transport http process-control https://process-monitor-mcp.saifs.ai/mcpInstall Statistical Process Control & Anomaly Alerts MCP in Gemini settings.json
~/.gemini/settings.json
{
"mcpServers": {
"process-control": {
"url": "https://process-monitor-mcp.saifs.ai/mcp",
"type": "http"
}
}
}Statistical Process Control & Anomaly Alerts MCP tools 5
Detected from the READMEdetect_shiftexplain_signalmonitor_metricset_control_limitswatch_process
| detect_shift | — | |
| explain_signal | — | |
| monitor_metric | — | |
| set_control_limits | — | |
| watch_process | — |
Automated checks
Ran Nov 13, 2026Full report →Not verified yet. A server needs a score of 80, no serious finding, and enough data for us to check. How checks work · What to fix for more points
- Source repository linked and reachablesaify-technologies/saifs-ai-mcps-docs is public and reachablegithub.com/saify-technologies/saifs-ai-mcps-docs ↗Pass
- Package names this repository as its sourceNot checked
- Build provenance (Sigstore attestation)Not checked
- Open source license (OSI)MITspdx.org/licenses/MIT.html ↗Pass
- Commit or release in the last yearLast commit or release 2026-11-13github.com/saify-technologies/saifs-ai-mcps-docs ↗Pass
- OpenSSF ScorecardNot checked
- Package name not close to a popular packageNot checked
- No critical advisory in the package or its dependenciesNot checked
- No hidden instructions to the model5 tool descriptions and the README read; no override phrases, credential paths or hidden charactersPass
- Destructive tools are labelledNo tool named like delete, drop or execPass
- Remote endpoint answers the MCP handshakeHTTPS endpoint answered 401 (sign-in required)Pass
README
View on GitHubStatistical Process Control & Anomaly Alerts
Continuous statistical monitoring of any metric stream — support response time, error rates, delivery SLAs, defect rates, conversion — alerting only on genuine out-of-control signals. Shewhart charts plus Western Electric / Nelson run rules, with CUSUM and EWMA for small sustained drifts that a 3σ chart misses. Decision support only; operators own stop/go.
| Registry name | ai.saifs/process-control |
| Endpoint | https://process-monitor-mcp-microsoft.saifs.ai/mcp |
| Transport | Streamable HTTP (remote, nothing to install) |
| Auth | OAuth 2.1 — PKCE (S256) and dynamic client registration; your client opens a sign-in page on first use |
| Publisher | SAIFS AI |
Install
VS Code / GitHub Copilot
Add to .vscode/mcp.json (workspace) or your user mcp.json:
{
"servers": {
"saifs-process-control": {
"type": "http",
"url": "https://process-monitor-mcp-microsoft.saifs.ai/mcp"
}
}
}
Then start the server from the MCP view and sign in when prompted.
Claude (claude.ai, Desktop)
Settings → Connectors → Add custom connector, and paste:
https://process-monitor-mcp-microsoft.saifs.ai/mcp
Claude Code
claude mcp add --transport http saifs-process-control https://process-monitor-mcp-microsoft.saifs.ai/mcp
Any other MCP client
Point it at https://process-monitor-mcp-microsoft.saifs.ai/mcp using the Streamable HTTP transport. The server returns 401 with a
WWW-Authenticate: Bearer … resource_metadata=… challenge, so OAuth-aware clients sign in automatically.
Tools
| Tool | What it does |
|---|---|
detect_shift |
CUSUM / EWMA for small sustained drifts that Shewhart charts miss. |
explain_signal |
Which rule fired, how many sigma, and what it means. |
monitor_metric |
In-control / out-of-control verdict plus which rule fired. |
set_control_limits |
Compute ±3σ limits from a stable baseline. |
watch_process |
Continuous watch; alert on rule violations. |
Example prompts
- “Is line 3 drifting out of spec?”
- “Alert me when defect rate shifts”
- “Calculate Cpk for this process”
Support
- Website: https://saifs.ai
- Issues: https://github.com/Saify-Technologies/saifs-ai-mcps-docs/issues
- Privacy: https://saifs.ai/privacy_policy
Statistical Process Control & Anomaly Alerts MCP questions
How do I add Statistical Process Control & Anomaly Alerts MCP to Claude Code?
Run claude mcp add --transport http process-control https://process-monitor-mcp.saifs.ai/mcp in your terminal. Add --scope user to make it available in every project.
How do I add Statistical Process Control & Anomaly Alerts MCP to Cursor?
Open ~/.cursor/mcp.json and add the server under mcpServers, using the Cursor config shown in the install section above.
What tools does Statistical Process Control & Anomaly Alerts MCP provide?
It exposes 5 tools, including detect_shift, explain_signal, monitor_metric, set_control_limits, watch_process.
How does the server handle small sustained drifts?
The server uses CUSUM and EWMA methods to detect small sustained drifts that standard 3σ charts might miss.