Library
85,762 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.
Results
-
Rights-aware censorship, China-economic status, and tamper-evident AI evaluation tools.
-
Free to compete: testnet faucet funds everything. Classify a product blurb: category + sentiment
-
Human Creative AI Workflow & Eval Lab
MCP serversRemote MCP tools for 3-vendor AI workflow diagnostics, HAR sandboxes, 50v audits, and rubrics.
-
Sema
MCP serversMCP tools for Sema — eval, compile, build, format, and docs for a Lisp with LLM primitives.
https://github.com/sema-lisp/sema/releases/download/v2.0.0/sema.mcpb@2.0.0 -
AISafetyHot
MCP serversAI Safety HOT: daily AI safety news, papers and incidents in one place — jailbreaks, prompt injection, alignment, evals, governance. Website, daily digest, RSS and MCP.
git clone https://github.com/wuyoscar/AISafetyHot.git -
geminiupgradeqa-mcp
MCP serversRemote MCP for Gemini upgrade evals, prompt regressions, output diffs, and eval receipts.
-
remnic
MCP serversOpen-source memory and context for user-aware agents: scoped memory, provenance, retrieval quality, correction, boundaries, evals, and MCP/HTTP access.
git clone https://github.com/joshuaswarren/remnic.git -
cortex
MCP serversCortex - Generates interactive API documentation, typed SDKs, and MCP servers from OpenAPI, AsyncAPI, GraphQL, gRPC, OpenRPC, and Markdown.
git clone https://github.com/cortex-docs/cortex.git -
forgejudge
MCP serversOpen eval leaderboard + CI gate for autonomous coding agents (solve, score, trace).
forgejudge@0.1.0 -
retriEVAL
MCP serversLLM evals as MCP tools: score outputs for faithfulness, relevancy, and hallucination.
ghcr.io/hcarrillo001/retrieval-mcp:1.0.0 -
server
MCP serversObservability MCP server: query LLM cost/errors/latency & operate alerts/evals from Claude/Cursor
@argosvix/mcp-server@1.1.2 -
digline
MCP serversRead, measure and explain LLM eval runs of a digline suite. Cannot promote a baseline.
digline-mcp@0.10.0 -
Lore Context
MCP serversGoverned AI-agent memory, Evidence Ledger traces, evals, and portable context tools.
@lore-context/server@0.6.0-alpha.1 -
numguard
MCP serversVerify a number before an agent asserts it — evals, backtests (Deflated Sharpe), signed receipts.
numguard@0.1.1 -
ZeroWidth Caliper
MCP serversBuild datasets and rubrics, then run evals that score your AI in Caliper.
-
元铸工坊 SOSOFAST (yuanzhu)
MCP serversGoverned AI workflow assets: staged writes, evals-gated template forging, ontology via MCP.
yuanzhu@0.2.2 -
QueryPilot
MCP serversSafe SQL gateway for AI agents: SELECT-only validation, access policies, masking, audit trail, evals
querypilot@0.1.1 -
MoltJobs
MCP serversBrowse MoltJobs jobs, manage owned AI agents, review evals, and place authorized USDC bids.
-
Openlayer
MCP serversInspect AI projects, traces, tests, and governance rules in Openlayer, and debug failing evals.
-
Kojen
MCP serversTrain, evaluate, red-team and deploy AI agents: prompt tuning, LLM-judged evals, katas.
-
Orq.ai
MCP serversBuild and monitor LLM apps on Orq.ai: AI gateway, agents, prompts, evals, traces.
-
Speko AI
MCP serversManage Speko voice-AI agents, sessions, calls, phone numbers, knowledge bases, evals, and docs.
-
safetyreplay-mcp
MCP serversPaid remote MCP for safety replays, policy gates, eval receipts, and release evidence.
-
rubrkit
MCP serversMCP-native AI evaluation: rubric audits, eval suites, and proof reports for AI/LLM output.
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.