Library
86,219 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.
Results
-
xSkill AI
MCP serversAI content generation with 50+ models: image, video, TTS, voice cloning, and more.
-
cotforce-mcp
MCP serversGive brains to your small models. MCP server enforcing step-by-step Chain-of-Thought.
@slbdn/cotforce-mcp@1.1.3 -
optlens
MCP serversDebug and explain LP/MILP models: why infeasible, the smallest fix, what-if and sensitivity.
optlens@0.0.4 -
omnarai-mcp
MCP serversDeliberation + live 5-model council divergence over the Omnarai multi-AI attributed corpus.
omnarai-mcp@1.12.0 -
Readout
MCP serversMeasured readings on open-source dependencies: health, end-of-life, model prices, incidents.
-
Sighttrue
MCP serversMeasured readings on open-source dependencies: health, end-of-life, model prices, incidents.
-
Cicadas local MCP
MCP serversLocal Cicadas MCP for models, quotes and status. Authenticated API flows not yet verified.
https://github.com/kevinwowo/cicadas-local-mcp/releases/download/v0.1.0/cicadas-local-mcp-0.1.0.mcpb -
fleet
MCP serversEvery machine you have, for your agent: free GPUs, jobs, served models, software, over SSH.
agents-fleet@0.6.1 -
sidecrew
MCP serversCode changes and unit tests by local MLX models, behind a gate a machine can run.
sidecrew@0.2.0 -
Neurarch
MCP serversPre-checks a model change before GPU time or traffic: memory, layout, serving config, pins.
neurarch-mcp@0.21.0 -
fs-mcp-rs
MCP serversA fast, configurable filesystem server for the Model Context Protocol (MCP), written in Rust.
fs-mcp-rs@1.2.4 -
Codex Subagent
MCP serversDelegate coding tasks to the OpenAI Codex CLI, installed separately, with explicit model and effort.
codex-subagent-mcp@0.6.0 -
Skimless
MCP serversReading order for big pull requests: what to read first, what can wait. Offline, no model.
skimless@0.1.2 -
cursor-mcp
MCP serversCursor's agent (cursor-agent CLI) through MCP: any model your plan offers, resumable sessions.
@qmediat.io/cursor-mcp@1.2.3 -
CLS++ Memory
MCP serversCross-LLM persistent memory: store context once, recall it from any AI model.
clsplusplus@7.19.0 -
runcomfy-mcp
MCP serversRemote MCP for RunComfy: ComfyUI deployments, hosted models, LoRA training. 31 tools.
-
Ollama / vLLM Bridge
MCP serversCall your local Ollama or vLLM model over MCP with schema-validated JSON output
mcp-ollama-vllm@1.0.6 -
simplefunctions
MCP serversCalibrated world model for AI agents. 40 tools: world state, markets, trading. Kalshi + Polymarket.
@spfunctions/cli@1.7.22 -
cheap-eyes
MCP serversHands bulk reading to cheap OpenRouter models, masks secrets, checks each answer against the source
cheap-eyes@0.3.0 -
TokenMark
MCP serversMeasured local-LLM speeds and model picks for Strix Halo, DGX Spark, Mac and GPU cards.
@altronis/tokenmark-mcp@0.4.1 -
Hemrock MCP
MCP serversFinancial models in chat: cap tables, waterfalls, fund economics, SaaS, ecommerce, unit economics.
-
NanoBanana Pro 2
MCP servers4K AI image generation via NanoBanana Pro 2: Pro + Flash models, Google Search grounding
nanobanana-imagen-mcp@1.1.2 -
AI-Cost-CLI
MCP serversAI API cost calculator, recommender & MCP server. 29 models across text/image/video/audio.
aicost-cli@1.1.0 -
valem
MCP serversValem - Deterministic reactive state models. Create your own calculators/forms with AI
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.