14,252 mods in this category, of every kind an
agent can take. Each one carries what it costs per session, what the
scan found, and whether it is the original.
Know what a GPU job needs before it takes a reservation. Bundles the neurarch-mcp server (sizetrainingjob, diagnoseoom, checkedit, checkparallellayout, checkservingconfig, checkpins, modelchanges, lintmodel, checkdesign and the rest), a PreToolUse hook that blocks a training launch whose job will not fit th.
★not rated 1
changed yesterdayA
tokens not measured
originalMIT
Structured, cited, real-world data from 300+ sources and the open web for your AI agents. Runs locally from the neuralverge-mcp-server npm package. Needs 1 environment variable to run.
★not rated 1
changed todayASocket: pass
tokens not measured
originalMIT
LLM API list prices with their source and last-confirmed date, past prices, and cost estimates that account for conversation history, caching, long-context tiers and reasoning tokens. Use when asked what a model costs, what it cost on a past date, what a workload or a month's usage would cost, or for a cheaper model.
Model-agnostic MCP control plane for the Human Agent Interface (HAI): bounded missions, session leases, drift checks and owner-gated actions so agent work stays observable and recoverable. Local-first, runs via uvx from PyPI.
★not rated 1 2d agoA
tokens not measured
originalMIT
Create, edit, and build Observable Notebooks using Notebook Kit. Use when working with .html notebook files, generating static sites from notebooks, querying databases from notebooks, or using data loaders (Node.js/Python/R) in notebooks. Covers notebook file format, cell types, CLI commands, database connectors, and…
A vision skill that sends images and screenshots to a visual analysis service. It adds image understanding to a model that otherwise works only with text.
AI command-line tool inspired by ffmpeg. Access any AI service from the command line with a unified interface. Runs locally from the ffmcp npm package.
★not rated 0 3mo agoA
tokens not measured
originalMIT
Use this skill for ANY interaction with vision-extension (the open-source vision pack at github.com/loudMore/vision-extension, containing the vision-extension MCP server) — installing/configuring it, calling its tools (mcpvision-extensiondescribeimage, mcpvision-extensioncompareimages, mcpvision-extensionextracttext)…
FreeGLM API — cloud media understanding by model family: VL vision chat, OCR, and grounding on DashScope Qwen or Zhipu GLM-4.6V-Flash; Omni A/V, ASR, and segmentation on DashScope.
Model Context Protocol server for FHIR R4 with validation, narrative generation, and comprehensive resource management. Runs locally from the fhir-mcp-server npm package.
A local MCP server that gives unimodal LLMs multimodal vision — image/video recognition with multi-turn iterative analysis. Runs locally from the @honlnk/picsense npm package.
★not rated 0 1mo agoA
tokens not measured
originalApache-2.0
MCP server "ragfilings" as configured in Rudra7777/agentic-rag-annual-reports. Runs ragfilings.mcp.server with .venv/bin/python. Needs 1 environment variable to run.
Use this skill when a source schema change has broken, or is about to break, a downstream transformation and the user wants a fix they can merge — not a summary. Triggers on: "a column was renamed, fix the dbt model", "this field is gone downstream", "schema drift", "our model still selects the old column", "generate…
MCP server for agentic AI-assisted development in SAP BW/4HANA. Runs locally from the bw-modeling-mcp npm package.
★not rated 0 3mo agoA
tokens not measured
originalMIT
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: