"Slow thinking, distributed thinking, and reasoning abilities research" matching MCP servers:

Enables AI coding agents to deploy and manage full multi-service applications on Constructor from a single request, covering image builds, service configuration, start/stop lifecycle, logs, and file syncing on research desks. It handles browser-based sign-in and token renewal automatically so agents can inspect deployments and report results without manual setup.

Monitor failing GitHub Actions workflows, auto-fix them with OpenCode, and retry the run — driven by a workflow_run webhook, coordinated through an MCP server.

Get your research artifact ready for Artifact Evaluation before the deadline: scan the repo, scaffold the easy fixes, verify the run path, and generate the appendix.

Unified capability catalogue with formally verified cartridges, distributed community hosting, and the Teranga menu system for single gateway access to a vast rabbfe of MCP, LSP, NeSy and related servers.!

Karpenter is a Kubernetes Node Autoscaler built for flexibility, performance, and simplicity.

A production-ready template for building Model Context Protocol (MCP) servers in Python, using Docker Compose for containerized development and CI/CD.

Query Prometheus from CLI or any MCP client, with retries, caching, and an optional metrics exporter.

A boilerplate for building FastMCP servers, providing a basic setup for testing, linting, formatting, and publishing to NPM.

Enables interaction with Celery distributed task queues through MCP tools. Supports task management, monitoring worker statistics, and controlling asynchronous job execution through natural language.

A stdio MCP server that lets an AI client inspect a project, see available hosting providers, and check status, then — after explicit confirmation — deploy it live, research its market, and compose a prompt.md. Deploys run through each provider's own CLI on the user's logged-in account, so no provider credentials are ever handled by the server.

Provides Kubernetes deployment intelligence with typed query tools and AI-synthesized risk briefs, enabling users to list workloads, get detailed snapshots, query Prometheus metrics, record deployment history, and generate risk assessments before promoting to production.

Enables AI assistants to interact with Woodpecker CI to debug pipeline failures, analyze build logs, troubleshoot configurations, and perform pipeline and repository actions such as triggering, restarting, canceling, approving, activating, and updating settings.

. A good description should be concise and describe what the server enables users to do, e.g. * Enables to interact with WordPress sites...' Then a huge block? Actually the user message includes the README content inside tags, then after the readme, there is a large block of text starting with '{

An open source MCP server empowering SREs with intelligent observability, predictive analytics, and AI-driven automation across Kubernetes, OpenShift, and Tekton environments.

Interact with OneDev for CI/CD spec editing, pull request review, and issue workflow automation etc.

Agent trace diff and prompt regression detection — compares two agent runs to find exactly where reasoning diverged.

A Model Context Protocol server implementation that allows AI models to interact with and manage Spinnaker deployments, pipelines, and applications through a standardized interface.

A production-ready template for building Model Context Protocol servers in Python, featuring example tools, structured logging, and multiple transport protocols.

Enables Codex on macOS to accelerate builds, tests, Docker, and research pipelines by compiling work into a typed intermediate representation and executing only conflict-checked, independent atoms in parallel while preserving task semantics. It provides live progress and time-saved reporting without changing permissions or automatically retrying timed-out side effects.

Enables AI agents to query build/deploy status and request operations on a self-hosted Docker/Compose deployment platform, with Observer and Operator skills and approval-based write actions.

Provides access to PyTorch CI/CD analytics data including workflows, jobs, test runs, and log analysis through an MCP interface.

A basic MCP server template built with FastMCP framework that provides example tools for echoing messages and retrieving server information. Serves as a starting point for developing custom MCP servers with Docker support and CI/CD integration.

Enables MCP clients to inspect Google Play releases, reviews, Android vitals, and scoped bulk reports, and to prepare explicitly authorized changes using locally supplied service-account credentials. Reads are default, while optional writes and sensitive reads require explicit configuration and single-use execution.

Provides AI assistants with access to Capawesome documentation and Cloud management tools, enabling app, build, and deployment operations via API token authentication.

Local MCP decision gate for AI agents and CI/CD: check candidate actions against owner-controlled policy and proposal-bound evidence. Three read-only tools report admissible options, missing evidence, and SHA-256 receipts. No selection, execution, or DeltaX API key.

Mneme exposes a governed Decision Index so MCP clients can propose candidate architectural decisions and query decision state, applicability, and traceability. Proposals remain non-authoritative: accepting or activating protections stays under explicit human control.

Supply-chain gate for AI agent skills and MCP servers: poison-scan tool definitions, hash-pin the vetted set into a lock file and verify drift in CI. truecopy-mcp is a drop-in stdio proxy that filters a live server's tools/list down to its pinned, unmodified, unpoisoned tools.

Fail-closed merge gate for AI coding agents: verify_repo runs the tests that existed before the change against a git working tree and answers MERGE, BLOCK or INCONCLUSIVE. The agent names what to judge; the operator pins the baseline and the floors.

Agent-readiness scorecard for any MCP server: protocol checks, 0-100 score and actionable findings.

Enables AI coding agents and CI to vet npm dependencies before they reach the lockfile, flagging hallucinated, slopsquatted, or otherwise risky packages with evidence-backed verdicts.