Library
86,219 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.
Results
Looks like a goal we have a starting path for: I want to research potential clients
-
eth-legion
MCP serversFree shared LLM inference (no key), verifiable score certificates, public randomness beacon.
-
pixscii
MCP serversLLMs can't draw. This MCP can. Pixel art animation toolkit — draw, animate, compose, export.
pixscii@0.5.0 -
datasheet-lens
MCP serversComponent datasheets (PDF) for LLM agents: index, search, original pages; BOM and CAD checks
datasheet-lens@0.6.1 -
Orma Memory
MCP serversEpisode-first, zero-latency long-term memory for local LLMs and AI coding assistants.
orma-ai@0.1.13 -
Prembly MCP Server
MCP serversIdentity verification, compliance and fraud detection checks from Prembly, for LLM clients.
-
Liquid Inference
MCP serversAuction exchange for LLM inference: browse models and prices, preview and buy answers.
-
Timbre
MCP serversApple Mail on macOS for all LLMs (Claude, ChatGPT, Gemini, Mistral): local, safe, and undoable.
https://github.com/alejandrosml/timbre-download/releases/download/v0.7.6/timbre-0.7.6.mcpb -
frame-check
MCP serversDeterministic structural framing analysis for AI-generated documents; no LLM call of its own.
frame-check-mcp@1.2.2 -
toolmenu
MCP serversTests MCP servers as clients meet them: menu, calls, results, sign-in, releases. No LLM.
toolmenu@0.28.0 -
DoboCache
MCP serversStabilizes LLM prompt-cache prefixes so provider caching hits. One command setup, no baseURL edit.
dobocache@0.9.2 -
Kojen
MCP serversTrain, evaluate, red-team and deploy AI agents: prompt tuning, LLM-judged evals, katas.
-
trustmodel-mcp
MCP serversScore any AI for trust across 10 dimensions; evaluate, monitor & govern LLMs and agents.
@trustmodel/mcp-server@0.2.2 -
modelcost
MCP serversAI API Radar: cheapest LLM models, per-model price history, provider status and price changes.
@reneturcios/modelcost@0.1.0 -
FailLoud
MCP serversVerification harness for LLM agent outputs — catches the silent failures agents ship as done.
failloud@0.5.1 -
distill
MCP serversLocal PDF and Office to token-lean Markdown for LLMs. No uploads, no API keys.
distill-llm@0.4.0 -
Prompt Engine
MCP serversTurns rough prompts into detailed, LLM-ready prompts with multiple-choice clarifying questions.
prompt-engine-mcp@0.1.0 -
Orq.ai
MCP serversBuild and monitor LLM apps on Orq.ai: AI gateway, agents, prompts, evals, traces.
-
Overwing
MCP serversGuardrails for LLM output: pass / fail / review verdicts and one recommended action. Hosted or npm.
overwing-mcp@0.15.0 -
QuoteFirst
MCP serversGet dollar quotes from 200+ LLMs before any work runs; accept, execute, and verify quality.
-
MetehanGZL-pokemcp
MCP serversProvide detailed Pokémon data and information through a standardized MCP interface. Enable LLMs an…
-
browserbasehq-mcp-browserbase
MCP serversProvides cloud browser automation capabilities using Stagehand and Browserbase, enabling LLMs to i…
-
kirbah-mcp-youtube
MCP serversProvide token-optimized, structured YouTube data to enhance your LLM applications. Access efficien…
-
APICK AI
MCP serversLLM chat, text tools, image generation, editing, batch image jobs, and asynchronous video generation
-
Cleanor
MCP serversZero-auth MCP: image optimize, cited storage/format data, and dev utilities LLMs get wrong.
@cleanor/mcp@0.6.1
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.