Library
85,762 resources from 11 public sources. 53 checked by hand; the rest are unreviewed.
Results
-
conkurrence
MCP serversMulti-model rating for AI evaluation. Agreement is reliability, not validity. Maintenance mode.
conkurrence@1.0.5 -
OpenTrain
MCP serversHire human data labelers, RLHF annotators, and evaluators from your coding agent.
@opentrain-ai/mcp@0.2.2 -
Research Repo Doctor
MCP serversDeterministic Artifact Evaluation preflight and run-path grader for research repositories.
rrdoctor@0.2.24 -
sidclaw-governance-mcp
MCP serversGovernance proxy for MCP servers — policy evaluation, human approval, audit trails.
@sidclaw/sdk@0.1.13 -
Braintrust
MCP serversAI evaluation and observability platform — query experiments, logs, datasets, and prompts.
-
PuzzleTide
MCP serversWord search, crossword, and sudoku generators, printable PDF worksheets, and verifiable LLM evals.
puzzletide-mcp@0.2.1 -
PaperBanana-CN
MCP serversGenerate and evaluate academic diagrams and plots with independent model connections.
paperbanana-cn@2.0.1 -
golden-dataset-mcp
MCP serversVersion-controlled golden datasets and RAG evaluation, no API key needed.
golden-dataset-mcp@0.1.2 -
flippa-mcp
MCP serversSearch, analyze, and evaluate online businesses for sale on Flippa.com marketplace.
flippa-mcp-server@1.0.2 -
rhumb-mcp
MCP serversAgent gateway for Index discovery, AN Score evaluation, and Resolve governed execution
rhumb-mcp@0.8.2 -
Learning Model Context Protocol
MCP serversBasic arithmetic tools with natural-language expression parsing and evaluation.
mcp-learning@0.3.0 -
AI Trainer Work
Public APIsOpen AI training jobs (RLHF, data annotation, expert evaluation) from 20+ platforms, with pay
-
truth-table-mcp
MCP serversEvaluate boolean logic expressions and build full truth tables - fully local.
@mrfentmen/truth-table-mcp@1.0.1 -
mathjs-mcp
MCP serversmathjs: evaluate any maths expression remotely with the math.js service - keyless.
@mrfentmen/mathjs-mcp@1.0.0 -
Callvu
MCP serversEvaluate Callvu, the Completion and Compliance Layer: processes, proof, costs and procurement.
-
Gridline
MCP serversFine-tune, evaluate and batch open models through Gridline's OpenAI-compatible API.
@gridlinegpu/mcp@0.1.2 -
AionLabs: Aion-RP 1.0 (8B)
ModelsAion-RP-Llama-3.1-8B ranks the highest in the character evaluation portion of the RPBench-Auto benchmark, a roleplaying-specific variant of Arena-Hard-Auto, where LLMs evaluate each other’s responses. It is a fine-tuned base model...
aion-labs/aion-rp-llama-3.1-8b -
DeepResearch-Bench-II
Datasets & benchmarksDeepResearch Bench II (DRB2) is the follow-up to DeepResearch Bench, with a stronger focus on measuring the gap between deep research systems and human experts. It does so by decomposing expert-written reports into hierarchical rubrics covering presentation, analysis, and evidence, and using them to evaluate model-generated.
git clone https://github.com/imlrz/DeepResearch-Bench-II.git -
claude-skills
SkillsSix Claude Code skills + an unattended build loop, each measured with and without the plugin. 19/19 evals passing.
git clone https://github.com/alonbaron/claude-skills.git -
ADHD in Children
MCP serversClinician-reviewed library on ADHD in children — evaluation, treatment, school, parenting.
-
Psychiatry for Children
MCP serversClinician-reviewed library on child psychiatric evaluation and medication decision-making.
-
company-technographics
MCP serversSearch 760K+ companies by technographics with direction of change: adopting, replacing, evaluating
-
noveum
MCP serversTrace, evaluate, and optimize your LLM, RAG, and agent apps with Noveum observability.
-
ADHD in Teens
MCP serversClinician-reviewed library on ADHD in teens — accommodations, executive function, evaluations.
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.