"Understanding Context Memory in Chat Systems" matching MCP connectors:

Third-party signed reads of how an AI agent behaved: drift, vows, and the town it works in.

Uptime and website monitoring for AI agents. Query monitor status, incidents, heartbeats, domain expiry, and status pages in your Vantaj Uptime workspace.

Connect Google Analytics to ChatGPT. Query GA4 data in plain English and get instant insights.

The Cortex MCP server provides read-only access to real-time engineering context from the Cortex developer portal, allowing AI coding assistants to answer natural language questions about your organization's catalog (microservices, libraries, domains, teams, infrastructure), scorecards (engineering standards and best practices), initiatives (goals and deadlines), and Engineering Intelligence metrics. It includes tools for querying documentation, tracking personal entities, and accessing AI-assisted insights across the entire Cortex ecosystem.

Analyze web performance and get optimization insights from GTmetrix, directly in your AI workflow.

MCP server providing access to the Scorecard API to evaluate and optimize LLM systems.

Enables monitoring and management of Ruckus Unleashed WiFi controllers, including APs, clients, WLANs, and system events. MCP server for Ruckus Unleashed (tested on R500/R600, built-in Embedthis-Appweb web server). Uses aioruckus to talk to the controller's AJAX API.

Evidence-governed screening of material decisions about physical assets and operational systems.

AI agent observability for production traces, natural-language insights, and improvement loops.

The statistical analyst in your AI chat — validated, citable, re-runnable analysis of your data.

Check infrastructure health, manage incidents, and run runbooks in Faultline.

Read-only MCP server for Yandex Metrika analytics. Query visits, sources, geography, devices and more in plain language — directly in Claude, Cursor, or any MCP client.

Enable secure connectivity between Sentry issues and debugging data, and LLM clients, using a Model Context Protocol (MCP) server.

MCP-native AI SRE: ask what's broken in production, get a reviewed GitHub fix PR.

MCP-native AI SRE. Exposes your production OpenTelemetry problems, traces, and logs over the Model Context Protocol, plus an AI remediation loop that opens a reviewed GitHub fix PR and verifies in production (reopening on regression). Tools include list_problems, get_problem, query_traces, detect_anomalies, and request_problem_remediation. Human-in-the-loop by default — the merge button stays yours.

Interact with a global network measurement platform.Run network commands from any point in the world

A paid remote MCP for OpenAI Codex context compressor, built to return verdicts, receipts, usage log

Query metrics, targets, entities, and team data in your Steep workspace via MCP.

Paid remote MCP for context-budget routing, schema cost estimates, usage audits, and readiness.

AI QA tester — real browsers scan sites for bugs, SEO, perf, and accessibility issues via chat.