Library
85,762 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.
Results
-
Echoproof
MCP serversReplay real HTTP traffic against base and changed builds; flag behavior changes the intent omits.
echoproof@0.4.0 -
agent-magnet
MCP serversBehavioral memory layer for AI tools. Learns preferences and context across Claude, Cursor, Codex.
agent-magnet@0.1.11 -
dominion-observatory
MCP serversRuntime behavioral trust scoring for MCP servers. Check reliability before calling unknown tools.
-
Medius Docs
MCP serversMedius docs: the binary control protocol, device behavior, and the medius Rust library.
-
mcp-shrimp-task-manager
MCP serversShrimp Task Manager is a task tool built for AI Agents, emphasizing chain-of-thought, reflection, and style consistency. It converts natural language into structured dev tasks with dependency tracking and iterative refinement, enabling agent-like developer behavior in reasoning AI systems.
git clone https://github.com/cjo4m06/mcp-shrimp-task-manager.git -
rea-capcut
SkillsReaCut — REA × CapCut: an independent, open-source video editor rebuilt from REA-assisted, authorized local behavior and format research. No copied CapCut proprietary code or assets. Offline desktop app + Codex plugin.
git clone https://github.com/Xiangyu-CAS/rea-capcut.git -
jevgrep
MCP serversJev-powered semantic code search for coding agents — find behavior across repositories via CLI or MCP, with exact source excerpts and line numbers.
git clone https://github.com/nassim-arifette/jevgrep.git -
Harvv
MCP serversWebsite behavior analytics: dead clicks, rage clicks, funnels, speed, SEO and sales for your site.
-
agent-eval
MCP serversStatistical regression testing for LLM agents: p-value, effect size, and CI on behavior change.
agent-regress-cli@0.1.8 -
Converra
MCP serversFix production agent behavior with tested changes and a production verdict on every fix.
-
MCP Safety Warden
MCP serversMCP proxy adding security scanning, behavioral profiling, risk gating, and safe tool call execution.
mcpsafetywarden@1.7.7 -
Pending Medicare Enrollment Data
MCP serversBehavioral health NPIs newly pending Medicare provider enrollment; free validated preview.
-
corpus
MCP serversMaintained behavior records for the tools and platforms AI agents use, distilled from live docs.
-
Microsoft Clarity MCP
MCP serversMicrosoft Clarity MCP: behavioral UX analytics, rage clicks, dead clicks, scroll, and JS errors.
microsoft-clarity-mcp@0.1.3 -
super-ux
SkillsDefine product behavior, trace UX scenarios and keep copy consistent through brand voice, audits and code checks.
git clone https://github.com/ssheleg/super-ux.git -
BenchGecko
MCP serversAI model prices per provider, benchmarks, own AI behavior tests and AI economy data, with sources.
-
CDC PLACES Health Data
MCP serversCounty and tract-level health outcomes, behaviors, and preventive services from CDC PLACES
-
cdc-health-mcp-server
MCP serversSearch and query CDC public health data — mortality, vaccinations, surveillance, behavioral risk.
@cyanheads/cdc-health-mcp-server@0.12.0 -
Commerce Intelligence
MCP serversBehavioral-science tools for commerce: checkout, drop-off, pricing, churn. 5 free calls, then paid.
-
Mirror
MCP serversGive Claude an honest self-model — behavioral tendencies built from evidence, not session memory. Mi
-
comparison of social groups
PromptsCompare the values and behaviors of ${group_a} and ${group_b} in online spaces.
-
Atlas Primer Voice Roleplay
MCP serversCreate real-time AI voice roleplay simulations and behavioral assessments on Atlas Primer.
@atlasprimer/mcp-server@1.0.2 -
agent-eval-loop
SkillsBuild evals from traces, code, and coding sessions, then measure and improve AI agent behavior, including your coding agents
git clone https://github.com/relai-ai/agent-eval-loop.git -
meridian
Tools & appsZero-config Claude Code setup with enforced task scaffolding, structured memory, persistent context after compaction, plug-in code standards, optional TDD mode, and zero behavior changes for developers.
git clone https://github.com/markmdev/meridian.git
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.