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.
-
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 -
evalsmith-mcp
MCP serversEvaluate RAG retrieval, agent tool calls and prompt regressions with deterministic metrics.
evalsmith-mcp@0.1.0 -
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 -
pi-harness
Agents & frameworksThe operational superset of Pi Coding Agent — everything Pi, plus observability, governance, recovery, evaluation and multi-agent orchestration. Pi Coding Agent 的运维超集——完整继承 Pi 的核心能力,并进一步扩展可观测性、治理、故障恢复、评估和多 Agent 编排。
git clone https://github.com/wangmiaozero/pi-harness.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.
-
aegis
MCP serversLocal stdio MCP server for the AEGIS governance client. The hosted evaluation service is offline.
aegis-governance@1.4.2
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.