Packages

Ollama MCP Bridge enabling AI agents to use Ollama local LLMs as MCP tools — routing tool calls and LLM inference requests to locally-running Ollama models, enabling agents to delegate tasks to local models (Llama 3, Mistral, Phi, Gemma, etc.), and providing a bridge between MCP-based agent frameworks and Ollama's local inference API.

Official OpsLevel MCP server enabling AI agents to interact with OpsLevel's service catalog and internal developer platform — querying service metadata, checking maturity scorecards, managing ownership, and accessing service health and compliance data.

Community MCP server for PostgreSQL enabling AI agents to execute queries, inspect schema, and manage data in PostgreSQL databases — the foundational relational database for agent data access.

Official MCP server from ScoutAPM (scoutapp org) for Scout APM — the developer-friendly application performance monitoring service. Enables AI agents to query Scout APM for transaction traces, performance bottlenecks, slow queries, memory/CPU metrics, and deployment tracking — supporting AI-driven performance analysis workflows.

Terminal MCP server enabling AI agents to execute shell commands and interact with the local terminal — running bash/shell commands, capturing stdout/stderr, managing working directories, and integrating system-level command execution into agent-driven development and automation workflows.

Efficiently consolidates project files into a single formatted output for LLM context, with intelligent filtering of binary/build artifacts, .contextfiles configuration, encoding support, and both CLI and MCP server interfaces.

Datadog MCP server enabling AI agents to interact with Datadog's observability platform — querying metrics and dashboards, searching logs, checking monitor status, retrieving APM traces, and integrating Datadog's monitoring capabilities into agent-driven incident response, SRE automation, and observability workflows.

KSail MCP server enabling AI agents to manage local Kubernetes clusters — creating and managing Kind/K3d clusters, deploying workloads, managing Kubernetes manifests, and integrating local Kubernetes development workflows into agent-driven DevOps and platform engineering automation.

MCP server for Mistral AI — the European open-weight and commercial LLM provider. Enables AI agents to call Mistral models (Mistral Large, Mistral Small, Codestral, Mixtral) for text generation, code completion, and embeddings. Useful for European data-residency requirements where US-based AI providers may be restricted.

MCP server providing AI agents with direct pandas DataFrame manipulation capabilities — loading CSV/Excel/JSON files into DataFrames, performing aggregations, filtering, joining, pivoting, and statistical analysis through MCP tool calls. Brings Python's most powerful data manipulation library into agent workflows without requiring code generation.

Official StackHawk MCP server enabling AI agents to trigger DAST (Dynamic Application Security Testing) scans, retrieve vulnerabilities, and integrate security testing into CI/CD agent workflows.

Community MCP server for Supabase providing AI agents access to PostgreSQL queries, table management, and Supabase platform operations via the Supabase REST API.

OpenAI Whisper MCP server enabling AI agents to transcribe audio and speech — converting audio files to text using OpenAI's Whisper model (locally or via API), processing audio from various formats (MP3, WAV, M4A, etc.), and integrating speech transcription capabilities into agent-driven workflows for meeting notes, podcast processing, voice command capture, and audio content analysis.

Atom of Thoughts (AoT) MCP server implementing a structured reasoning methodology where complex problems are decomposed into atomic thought units — small, discrete reasoning steps that can be individually validated and composed. Enables AI agents to apply systematic, verifiable reasoning patterns by breaking problems into independent atoms that can be parallelized, cached, and reused across different problems.

MCP server from Ansvar Systems for automotive cybersecurity standards and regulations. Provides AI agents access to automotive security frameworks including UN R155/R156 regulations, ISO/SAE 21434, TISAX, AUTOSAR security guidelines, and Chinese GB/T standards. Enables compliance research and gap analysis for automotive security programs.

MCP server providing 1C:Enterprise BSL (Business Script Language) platform context to AI agents — exposing the 1C platform API reference, object model, built-in functions, and development context to enable AI-assisted development for 1C:Enterprise applications. Primarily useful for 1C/BSL developers in Russia and CIS countries building business automation on the 1C platform.

MCP server providing structured reasoning and mental model frameworks to AI agents. Implements various thinking frameworks including first principles reasoning, second-order thinking, probabilistic reasoning, and other cognitive tools — helping AI agents reason more systematically and avoid common cognitive biases.

Code Execution Mode MCP server enabling AI agents to execute code in multiple programming languages — running Python, JavaScript, and other language snippets, returning execution results and errors, and integrating code execution capabilities into agent-driven programming assistance and code validation workflows.

ECharts MCP server enabling AI agents to generate data visualizations using Apache ECharts — creating interactive charts (line, bar, pie, scatter, geographic maps, etc.), configuring ECharts options from data and descriptions, and outputting chart configurations or rendered images for reports, dashboards, and data storytelling workflows.

GSAP Master MCP server enabling AI agents to work with GSAP (GreenSock Animation Platform) — generating GSAP animation code, providing GSAP API documentation and best practices, creating timeline-based animations, ScrollTrigger configurations, and integrating GSAP animation expertise into agent-driven web frontend development and creative coding workflows.