"Knative" matching MCP servers:

Enables orchestrator agents to route coding tasks to native CLI worker agents via MCP, providing tools for agent discovery, task submission, waiting, inspection, and cancellation.

Enables full-stack compiler development across the hw-native-sys workspace by combining repository operations (git health, code search, task running) with a knowledge layer for architecture docs, task routing, and abstraction/pass pipeline information.

Provides local cross-session memory for Codex by importing transcripts, indexing in SQLite, and exposing search, context, and memory management through MCP tools.

Enables MCP-compatible assistants to control Autodesk Fusion for mechanical modeling, assembly editing, CAM workflows, inspection, and model export through Fusion's native MCP endpoint.

Lets Codex delegate coding and review tasks to Gemini/Antigravity, Claude Code, and DeepSeek Harness through their native SDKs, while managing connections, isolated Git worktrees, and live task progress from a local panel.

Enables natural language control of HFSS (v2019-2025) for antenna modeling, simulation, and result extraction via win32com without PyAEDT.

A Django-native MCP application and tool registration framework inspired by Celery, providing async tool definitions, autodiscovery, and stdio/Streamable HTTP serving built on the official MCP Python SDK.

Enables an MCP client to inspect and edit native GraphPad Prism documents on macOS, including two-group column tables, descriptive analyses, violin and companion graphs, linked layouts, and exports to PDF, SVG, PNG, or CSV. It also records operation status, serializes mutations, and supports recovery workflows for uncertain native executions.

Enables MCP-capable agents to control the macOS mouse and keyboard using screenshots and Quartz-based input events, including app switching, clicks, scrolling, text entry, shortcuts, and action-triggered screenshots.

An MCP-native document research agent that provides search, summarization, and citation tools for iterative multi-step research, ending in validated structured JSON reports.

Enables AI assistants and automation tools to securely query ERPNext data through 16 read-only tools, with OAuth 2.0 or API-key authentication and usage telemetry.

Enables any MCP client (zcode, Claude Code, Cursor) to give its model bi-temporal long-term memory, auditable evidence-cited retrieval, LLM-assisted document extraction, and deterministic A* skill planning with precondition/effect verification. All four capabilities share one portable SQLite store and can be mounted independently on demand.

Enables AI clients to directly launch, control, and analyze AMD/Xilinx Vivado on Windows and Linux, supporting project management, synthesis, implementation, bitstream generation, timing/resource analysis, and simulation through a persistent Tcl session.

Provides tools for generating and editing images using OpenAI's gpt-image-1 model via an MCP interface, enabling AI assistants to create and modify images based on text prompts.

A governed AI agent platform that exposes GitHub Issues, Jira, and Slack as MCP servers, with mandatory human-in-the-loop approval for all write operations and full audit logging to PostgreSQL using PGVector semantic search.

Enables intelligent access to React Native Godot documentation, examples, API references, and troubleshooting guides through searchable tools optimized for LLM workflows.

Provides offline, high-accuracy OCR capabilities for images and PDFs using macOS's built-in Vision framework. Supports multi-language text extraction with intelligent block aggregation for tables and paragraphs, outputting structured JSON data suitable for document reconstruction.