Library
85,861 resources from 11 public sources. 47 checked by hand; the rest are unreviewed.
Results
-
Query partner roster, headquarters (California), sector focus, and fund benchmarks for.
-
Query partner roster, headquarters (California), sector focus, and fund benchmarks for.
-
web-eval-agent
MCP serversAn MCP server that autonomously evaluates web applications.
git clone https://github.com/refreshdotdev/web-eval-agent.git -
lattice
MCP serversBounded repository context and verified patches for Codex and Claude Code. Explicit edit grants, source fingerprints, isolated worktrees, acceptance checks, and reproducible paired benchmarks.
git clone https://github.com/moulwyse/lattice.git -
Anvil
MCP serversProvider-agnostic AI dev pipeline: clarify → plan → build → review → PR across your repos, mixing LLM providers per stage with your own keys. No vendor lock-in, no markup.
git clone https://github.com/esanmohammad/Anvil.git -
olivares
MCP serversGround truth for enterprise AI: your AI coding tools, your accounts and every session on your own server, from one web console, CLI or API. Self-hosted, open source.
git clone https://github.com/olivaresai/olivares.git -
tripo-studio-plugin
MCP serversUnofficial Codex plugin for AI 3D creation with your Tripo Studio account. Generate, texture, rig, animate and export assets with MCP Apps and local Blender tools.
git clone https://github.com/GrinZero/tripo-studio-plugin.git -
mtg-mcp
MCP serversA Model Context Protocol (MCP) server for Magic: The Gathering Commander format, providing comprehensive card information, rulings, pricing, and deck validation tools.
git clone https://github.com/nathanmartins/mtg-mcp.git -
interview-mode
MCP serversStructured interviewer for Claude Code — probing questions, decision tracking, evolving checkpoints.
claude-interview-mode@0.5.1 -
stata-code
MCP serversAgent-native Stata bridge for empirical research — run DiD/IV/RDD and publication-ready tables from Claude Code, Jupyter, or VS Code on one token-economy result schema, with StatsPAI cross-validation. | 面向实证研究的智能体 Stata 桥接器——在 Claude Code、Jupyter、VS Code 中用一套省 token 的结果格式跑 DiD/IV/RDD 与出版级表格,并支持 StatsPAI 跨栈交叉验证。
git clone https://github.com/brycewang-stanford/stata-code.git -
Free to compete: testnet faucet funds everything. 12 synthetic moderation case exception cases:…
-
HuggingFace Trending Models (hftrendingwatch)
MCP serversHuggingFace trending models — what's hot now. $0.01/query. Be born in one call — free testnet funds.
-
Gonka Second Opinion (multi-model)
MCP serversA second opinion for AI agents: one prompt across several live Gonka models + roles, one call.
-
ai-model-license-lint
MCP serversReads the open-weight model IDs in your code and names the licence clause that binds you - 22 rules
@readystack/ai-model-license-lint@1.0.2 -
ai-model-retirement-lint
MCP serversFinds the LLM model IDs pinned in your code that vendors have already switched off, or have dated to
@readystack/ai-model-retirement-lint@0.1.5 -
Veqen Pricing: AI model costs
MCP serversCompare AI model prices and estimate workload costs with four read-only tools. No account needed.
-
ChatGPT, Gemini, Copilot & AI Mode answers
MCP serversAsk ChatGPT, Gemini, Copilot or Google AI Mode a prompt: full answer + every cited source.
-
Model retirement dates with sources, public cost-vs-quality benchmark, local usage-cost check. Free.
trust-engine-mcp@0.2.2 -
Query partner roster, headquarters (Massachusetts), sector focus, and fund benchmarks for.
-
Query partner roster, headquarters (Missouri), sector focus, and fund benchmarks for.
-
Query partner roster, headquarters (Massachusetts), sector focus, and fund benchmarks for.
-
Query partner roster, headquarters (California), sector focus, and fund benchmarks for.
-
Query partner roster, headquarters (California), sector focus, and fund benchmarks for.
-
Query partner roster, headquarters (Massachusetts), sector focus, and fund benchmarks for.
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.