Library
85,762 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.
Results
-
QACAT
MCP serversTranslation QA: automated checks, AI evaluation, linguistic review, and visual in-context testing.
-
Cloudeval AI
MCP serversCloud evaluations and reviews for Azure and static AWS CloudFormation (beta). Requires an account.
@ganakailabs/cloudeval-cli@0.38.5 -
trustmodel-mcp
MCP serversScore any AI for trust across 10 dimensions; evaluate, monitor & govern LLMs and agents.
@trustmodel/mcp-server@0.2.0 -
QueryPilot
MCP serversSafe SQL gateway for AI agents: SELECT-only validation, access policies, masking, audit trail, evals
querypilot@0.1.1 -
Genius Decision
MCP serversCreate and evaluate versioned decision models with reproducible results and declared assumptions.
-
DeepSeek FR MCP
MCP serversIndependent French workspace for evaluating DeepSeek-V3-class chat and DeepSeek-R1 reasoning.
-
Vantio Gate
MCP serversVantio Gate — Policy Latch dry-run evaluate for agents. No live enforce from MCP.
@vantio/gate-mcp@0.1.0 -
DWIN Research Adoption
MCP serversFind, ground, evaluate, and selectively retain AI research through one local-first MCP.
dwin-research-adoption@0.1.0 -
MoltJobs
MCP serversBrowse MoltJobs jobs, manage owned AI agents, review evals, and place authorized USDC bids.
-
mcp
MCP serversMCP server providing access to the Scorecard API to evaluate and optimize LLM systems.
scorecard-ai-mcp@2.1.1 -
Hypertune MCP by usefulapi
MCP serversEvaluate and inspect your Hypertune feature flags from your AI assistant.
-
kairos-lang-mcp
MCP serversEvaluate (list/next) and validate Kairos schedule definitions; look up the descriptor reference
kairos-lang-mcp@1.1.0 -
Openlayer
MCP serversInspect AI projects, traces, tests, and governance rules in Openlayer, and debug failing evals.
-
PayStage Trade Preflight
MCP serversMCP tool: evaluate HIP-3/trade.xyz orders against a local TradePolicy before trading
@paystage/trade-preflight@0.2.0 -
tok
MCP serversModel BPMN processes and DMN decisions as text: check, export, import, simulate, evaluate.
tok-lang@1.0.3 -
trustmodel-mcp
MCP serversScore any AI for trust across 10 dimensions; evaluate, monitor & govern LLMs and agents.
@trustmodel/mcp-server@0.2.2 -
prompt-potter-optimizer
SkillsLLM-driven evolution of prompts and pipelines. Evolves the prompt and the pipeline's parameters together against your labeled data, cuts losing candidates early, and shows every measurement behind the winner. Open source.
git clone https://github.com/PromptPotter/prompt-potter-optimizer.git -
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.
-
KEILTY Realty Management
MCP serversEastern Ontario rental property management: check fit, read fees, request a rental evaluation.
-
Lazyweb Public Discovery
MCP serversKeyless, read-only Lazyweb discovery for agents evaluating fit or researching public evidence.
-
Plushwipes Agent Revenue
MCP serversRead-only tools for evaluating a live Plushwipes performance-commission opportunity.
-
changegamer
MCP serversAgent-first resource directory for AI agents: protocols, security, RAG, memory, evals, and more.
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.