Library
86,219 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.
Results
-
imgx
MCP serversAI image generation and editing MCP server. Gemini + OpenAI, iterative editing, undo/redo.
imgx-mcp@1.6.1 -
api-changelog
MCP serversSDK breaking-change tracker for AI agents — Anthropic/OpenAI/LangChain/MCP/Mistral.
@weiseer/api-changelog-mcp@0.1.1 -
Hubris
MCP serversOpenAI-compatible LLM gateway for Russia: 500+ models, ruble pricing, balance, chat.
hubris-mcp@0.1.1 -
codex4ever
MCP serversPlan OpenAI Codex usage from local quota, banked resets and extra-reset forecasts.
codex4ever@0.1.3 -
ModelLens
MCP serversSee which models actually work: probe, rank and recommend across OpenAI-compatible gateways.
modellens-mcp@0.1.3 -
Audio Transcription MCP
MCP serversTranscribe local audio and video using Whisper or the OpenAI API.
audio-transcription-mcp@0.1.0 -
Gridline
MCP serversFine-tune, evaluate and batch open models through Gridline's OpenAI-compatible API.
@gridlinegpu/mcp@0.1.2 -
neels-plugins
SkillsThe installation hub for Neel's open-source plugins: Digital Marketing Pro, ContentForge, SocialForge and CutForge. Strategy, content, social and video, portable across major agent environments.
git clone https://github.com/indranilbanerjee/neels-plugins.git -
OpenNotebookLM
AI repositoriesSelf-hosted alternative to Google's NotebookLM: import PDFs, web pages and YouTube transcripts, then get answers with citations back to the source. Hybrid dense + BM25 retrieval over a local SQLite database, with Claude, any OpenAI-compatible provider, or a model on your own machine.
git clone https://github.com/tom1030507/OpenNotebookLM.git -
class-action-finder
SkillsAn AI skill for Claude, Codex, and ChatGPT that scans your email for class action settlements, matches your purchases to open cases, verifies claim links against phishing, and tracks what you filed and got paid.
git clone https://github.com/yingying-chu/class-action-finder.git -
plugin-creator
SkillsCreate and scaffold plugin directories for Codex with a required `.codex-plugin/plugin.json`, optional plugin folders/files, and baseline placeholders you can edit before publishing or testing. Use when Codex needs to create a new local plugin, add optional plugin structure, or generate or update repo-root `.agents/plugins/marketplace.json` entries for plugin ordering and availability metadata.
$skill-installer <skill-name> -
Token Counter
MCP serversCounts tokens under OpenAI-compatible (tiktoken) encodings, by model or encoding name.
-
CloudQuell
MCP serversAsk about AWS, Azure, GCP, OpenAI, Anthropic and Snowflake costs, budgets, and anomalies.
-
dcp-mcp
MCP serversSaudi sovereign AI compute: OpenAI-compatible inference, rent GPU pods, manage storage.
-
evalview-mcp
MCP serversRegression testing for AI agents. Golden baselines, CI/CD, LangGraph, CrewAI, OpenAI, Claude.
evalview@0.6.0 -
SpeechWeave
MCP serversTranscribe local files and URLs with SpeechWeave's OpenAI-compatible Speech-to-Text API.
@speechweave/mcp@1.10.0 -
OpenRouter
Public APIsUnified API for 300+ LLMs from OpenAI, Anthropic, Meta, Mistral and more, with a free tier
-
TokenRoute
Public APIsOne OpenAI-compatible endpoint for hundreds of LLMs, with a free tier and per-token pricing
-
usage-planner
MCP serversPlan OpenAI Codex usage from local quota, banked resets and extra-reset forecasts.
usage-planner@0.2.7 -
codexwatch
MCP serversOpenAI Codex usage from your local logs: tokens, API-equivalent cost and plan limits.
codexwatch-cli@1.0.2 -
Driftline
MCP serversRetirement dates and replacements for OpenAI, Anthropic, Google and Bedrock models, checked daily.
@aidriftline/driftline@0.11.0 -
Awesome-Agent-Harnesses
Agents & frameworksCurated, verified survey of the agent harness — the layer around an LLM (loop, tools, memory, context, runtime) that turns it into an agent. 116 papers + Claude Code / Codex / Cursor / OpenHands tools + Anthropic / OpenAI / Karpathy essays. Agent = Model + Harness.
git clone https://github.com/NeuraLiying/Awesome-Agent-Harnesses.git -
security-threat-model
SkillsRepository-grounded threat modeling that enumerates trust boundaries, assets, attacker capabilities, abuse paths, and mitigations, and writes a concise Markdown threat model. Trigger only when the user explicitly asks to threat model a codebase or path, enumerate threats/abuse paths, or perform AppSec threat modeling. Do not trigger for general architecture summaries, code review, or non-security design work.
$skill-installer <skill-name> -
cli-creator
SkillsBuild a composable CLI for Codex from API docs, an OpenAPI spec, existing curl examples, an SDK, a web app, an admin tool, or a local script. Use when the user wants Codex to create a command-line tool that can run from any repo, expose composable read/write commands, return stable JSON, manage auth, and pair with a companion skill.
$skill-installer <skill-name>
Indexed entries aren't reviewed or tested by InnerVault. Details come straight from each source. Anything that can reach your accounts, files or browser can do damage, so read the source before you install it.