Library
86,219 resources from 11 public sources. 46 checked by hand; the rest are unreviewed.
Results
-
Apex (smartapex.uk) AI Component Card Store
MCP serversRun verified read-only code tools: quant diagnostics + agent-ops preflight, no source exposure.
-
Post-quantum CMMC compliance scanner & AI agent attestation. FIPS 140-3, ML-DSA-65, 36K+ mappings.
ghcr.io/nouchix/pqc-khepra-mcp:v1.0.0 -
hivemind
MCP serversQuery multiple AI models (OpenAI, Anthropic, Google) for consensus responses.
@quantulabs/hivemind@0.1.3 -
Graqle
MCP serversGraph-powered codebase reasoning, impact analysis, and governance tools over MCP.
graqle@0.87.1 -
mcp-server
MCP serversQuery BigQuery, Snowflake, Redshift & Azure Synapse with natural language
-
# Overqualification Narrative Architect VERSION: 3.0 AUTHOR: Scott M (updated with 2025 survey alignment) PURPOSE: Detect, quantify, and strategically neutralize perceived overqualification risk in job applications…
-
eligibility-mcp
MCP serversDeterministic eligibility checker for grants, jobs and scholarships in Africa.
-
pSEO Engine
MCP serversProgrammatic SEO as callable tools: research, generate, audit and publish landing pages.
-
simmerdeep
PromptsSimmerdeep Crypto Quant: Version 2.0 (The Freshness Update) Act as my Senior Trading Mentor: a fusion of Stan Druckenmiller (global macro/intuition), Russell Napier (market regime & debasement cycles), and Martin…
-
claude-academic-skills
SkillsA curated bundle of 38 Claude Skills for quantitative, qualitative, experimental & mixed-methods research in business, finance & social science — from framing a question to submission and replication packages (bilingual 中/EN)
git clone https://github.com/Nero1688/claude-academic-skills.git -
VLC Media Player
MCP serversControl VLC Media Player from any MCP client: play, pause, seek, volume, playlist.
vlc-mcp-server@0.1.2 -
presence-mcp
MCP serversRead-only MCP access to presence: living project model and outcome telemetry.
presence-mcp@0.2.0 -
blockfill
MCP serversLocal-first crypto perp/spot execution (TWAP/maker) across 11 venues; keys stay on your machine.
blockfill@1.2.1 -
.github
SkillsTheColliery — quality tooling for AI coding agents. The series landing page, the shared doctrine (Phoenix-13 hooks + Quantum-11), the public permission matrix and the doc/repo/release patterns, the one-step DLC installer, and the suite benchmarks.
git clone https://github.com/TheColliery/.github.git -
momo-parser-mcp
MCP serversParses MTN MoMo and Airtel Money Uganda SMS into structured JSON.
-
mcp
MCP serversS&P 500 market data: filings, earnings, insider, Congress and institutional trades. No forecasts.
@quantustik/mcp-server@1.0.1 -
Invoice Checker
PromptsYou check an invoice's numbers and completeness. You do not give tax advice: do not say what rate should apply, whether tax is due, or whether a field is legally required. Invoice (lines, quantities, unit prices, any…
-
african-fintech-mcp
MCP serversMobile money fees, African tax rates, currency conversion and Uganda PAYE for AI agents.
-
--- name: invoice-line-item-and-vat-total-checker description: Checks invoices before you pay or send them - recomputes every line (quantity x unit price minus discount) and the VAT or sales tax per line, the tax…
-
apple-silicon-llm-bench
Datasets & benchmarksReproducible on-device LLM benchmarks for Apple Silicon (iPhone 17 Pro, M4 Max): Apple Core AI, MLX, llama.cpp, LiteRT-LM and Core ML on the same model and harness, every number with its quantization and capture session; hybrid Mamba-2 models (Nemotron-3 Nano, Granite-4.0-H, Falcon-H1) included.
git clone https://github.com/john-rocky/apple-silicon-llm-bench.git -
define-goal
SkillsHelp the user define a concrete, measurable goal before starting work, especially when they ask to use the goal tool, create a goal, set an objective, clarify success criteria, or turn a fuzzy intention into a quantitative outcome. Use this skill for goal creation and goal refinement only; it does not manage durable snapshots, decision logs, or long-running execution artifacts.
$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.