Library
86,219 resources from 11 public sources. 46 checked by hand; the rest are unreviewed.
Results
Looks like a goal we have a starting path for: I want to research potential clients
-
Fitter
MCP serversTurn any website or API into structured JSON with LLM-authored declarative scraping configs.
https://github.com/PxyUp/fitter/releases/download/v1.8.3/fitter-mcp-darwin-arm64.mcpb -
pdf4vllm
MCP serversPDF reader for vision LLMs. Auto-detects text corruption and switches to image mode.
pdf4vllm-mcp@1.0.2 -
inferbench
MCP serversBenchmarks local LLM inference speed (tokens/sec) on your own hardware via MCP tools.
inferbench-cli@0.1.7 -
jsx-notation
MCP serversJSXN encoder/decoder — compact notation for React/Next.js files, optimized for LLMs
jsx-notation@0.1.6 -
vaultshell
MCP serversInjects secrets into shell commands at exec time; plaintext never reaches the LLM context
ghcr.io/sowhati/vaultshell:0.1.2 -
Model Council
MCP serversConsult other LLMs as tools — ask them, compare their answers, synthesize a conclusion.
model-council-mcp@0.14.0 -
Promptheus
MCP serversAI-powered prompt refinement with adaptive questioning and multi-provider support (6+ LLM backends)
promptheus@0.3.1 -
mcp
MCP serversLive, verified LLM API prices and deals: free models, discounts, compare, costs, price changes.
apipriceindex-mcp@0.3.0 -
parkour-mcp
MCP serversA content exploration toolkit that helps LLMs surface high signal, unsummarized web content.
https://github.com/blightbow/parkour-mcp/releases/download/v2.4.0/parkour-mcp.mcpb -
tuning-engines
MCP serversDomain-specific LLM fine-tuning — sovereign models trained on your data, zero infrastructure.
tuningengines-cli@0.3.5 -
llmconveyors
MCP servers53 tools for LLM Conveyors: job hunting, B2B sales, ATS scoring, resume tools.
llmconveyors-mcp@0.2.1 -
ellmos Homebase
MCP serversLocal-first LLM orchestration: memory, knowledge, state, routing, swarm, API discovery, plugins.
ellmos-homebase-mcp@0.1.0-alpha.29 -
assiststudio-runner
MCP serversWindows-only headless LLM task automation engine with scheduling via Windows Task Scheduler.
FieldCure.AssistStudio.Runner@2.0.4 -
webfetch
MCP serversSelf-hosted web search for LLM agents: search -> fetch -> rank pipeline with semantic caching
webfetch-llm@0.1.3 -
Kongen Labs — Pattern Intelligence
MCP serversLLM reasoning regime detection, cross-domain pattern transfer, and model routing.
kongenlabs-mcp@1.0.0 -
simpliq-server
MCP serversSimpliq Data Proxy MCP Server - Connects LLMs to SQL Databases via Semantic Mapping
simpliq-mcp-server-dev-test@0.1.1 -
GroundLens
MCP serversGuardrails for LLM answers: exact checks against sources, PASS/REVIEW/FAIL, signed records.
groundlens@6.0.5 -
shop-mcp
MCP serversRead-only Shopify catalogue and stock for LLM agents. Stdlib only, no dependencies.
shop-mcp@1.0.1 -
mcp-server
MCP serversBlock prompt injection, evasive spacing, and obscene content before it reaches your LLM.
@ingressward/mcp-server@1.0.0 -
neurodivergent-memory
MCP serversPersistent knowledge graph MCP server for neurodivergent thinking. BM25 search, no cloud LLM.
neurodivergent-memory@0.1.8 -
anybrowse
MCP serversConverts any URL to clean, LLM-ready Markdown using real Chrome browsers
-
mismem
MCP serversCooperative persistent memory for LLMs: episodes, memories and traits over SQLite (FTS5, Hebbian)
@lucasmella/mismem@0.2.0 -
KarmoLab
MCP serversMCP server for what LLMs get wrong: exact hashes, real randomness, and Korean rules.
karmolab-mcp@0.1.1 -
Memwyre
MCP serversUniversal persistent memory and knowledge retrieval layer for AI agents and LLMs.
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.