Library
85,861 resources from 11 public sources. 47 checked by hand; the rest are unreviewed.
Results
-
Compass
MCP serversGround your LLM in EU financial, crypto and AI regulation, verbatim and cited, via Compass.
@licentium/compass-mcp@1.0.1 -
Toon Memory
MCP serversOffline persistent memory for AI coding agents — 35 tools, 80% fewer calls, no LLM
toon-memory@4.3.5 -
cogvault
MCP serversLocal hybrid-search memory for AI agents over plain Markdown. Multi-tenant, offline, no LLM.
cogvault@0.12.2 -
onomeo
MCP serversAsk free LLMs (DeepSeek, GLM, Gemini, Mistral) for a second opinion from any MCP client.
https://github.com/Owaid0723666/onomeo-mcp/releases/download/v0.1.0/onomeo-mcp.mcpb -
seracade
MCP serversLLM cost optimization. Audit your calls, prove savings, route to the cheapest quality model. BYOK.
seracade@2.8.0 -
tokenmizer
MCP serversGraph-backed session memory for LLMs: checkpoint, resume, file analysis, token-savings stats.
tokenmizer@0.3.1 -
contextkeeper
MCP serversZero model drift between AI agents. Session continuity for Claude, GPT, Gemini, and any LLM.
contextkeeper@0.2.7 -
vaultit
MCP serversZero model drift between AI agents. Session continuity for Claude, GPT, Gemini, and any LLM.
vaultit@0.6.1 -
spa-reader-mcp
MCP serversMCP Server that renders JavaScript SPA pages and extracts LLM-ready Markdown content
spa-reader-mcp@1.0.2 -
local-delegate
MCP serversDelegate mechanical text tasks to a local OpenAI-compatible LLM to save Claude quota.
local-delegate-mcp@0.53.0 -
zentric-protocol-mcp
MCP serversPrompt injection + PII detection for LLM apps and agent pipelines. Deterministic, sub-25ms.
zentric-protocol-mcp@0.1.3 -
omnideck
MCP serversLocal privacy-first tools: redact secrets, decode JWTs, compare LLM costs. No network calls.
omnideck-mcp@1.0.4 -
finance-mcp
MCP serversLive stock, crypto, SEC filings, insider trades, FX and macro data for LLM agents.
finance-data-mcp@0.2.0 -
web-content-extractor
MCP serversExtract and process web content into clean, structured formats optimized for LLMs.
@agenson-horrowitz/web-content-extractor-mcp@1.0.8 -
mcp-context-server
MCP serversAn MCP server that provides persistent multimodal context storage for LLM agents.
mcp-context-server@2.2.2 -
NeuralBrain
MCP serversNeuralBrain MCP Server - RAG, Vector Memory, LLM Routing, Agent Identity, x402 Payments
-
paper-preflight
MCP serversChecks every LaTeX reference against Crossref, dblp, arXiv, DataCite, PubMed and OpenAlex. No LLM.
paper-preflight@1.0.0 -
agentmailkit
MCP serversRun scheduled LLM-written email digests from local files and feeds. Local-first MCP server.
agentmailkit@0.2.2 -
aeo-mcp
MCP serversAEO tools for AI agents: crawler permissions, llms.txt, structured data, AI-readiness audit.
aeo-mcp@1.0.1 -
token-compressor
MCP serversCompress prompts 40-60% using local LLM + embedding validation. Preserves all conditionals.
token-compressor-mcp@0.1.1 -
mcp-grantiq
MCP serversSearch US grants + federal contracts (Grants.gov + SAM.gov) from any LLM.
-
activitypub-mcp
MCP serversRead-only-by-default MCP server: let LLMs explore the Fediverse — Mastodon, Misskey, Pleroma.
activitypub-mcp@3.2.1 -
cheaprouter
MCP serversRoutes each LLM completion to the cheapest capable provider across 8 providers (BYOK).
-
Compute Finance Oracle
MCP serversLive AI compute pricing oracle — real-time LLM model prices across providers
@compute-finance/mcp@0.12.2
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.