Library
85,762 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.
Results
-
Scoby journey patterns
MCP serversCheck a planned flow against shipped apps: missing steps and edge cases.
-
wizard
SkillsGenerate an interactive bash wizard that walks a human through steps only they can perform. Use when provisioning infrastructure, setting up credentials or CI secrets, walking an unfamiliar third-party dashboard, or running a one-off migration or cutover. Don't invoke this for steps the agent can perform itself.
-
jev-social
SkillsOpen-source, local-first social media research agent for Instagram, TikTok, and LinkedIn. Jev routes read-only steps; socai CLI captures cited browser evidence.
git clone https://github.com/socai-io/jev-social.git -
claude-booping
SkillsA playbook framework for Claude Code and the sprint loop built on it — deterministic state machinery, model-driven steps, plain-markdown vault
git clone https://github.com/A/claude-booping.git -
OpenAdapt
Tools & appsFor EHRs, payer portals, and any app your team clicks through. A person or an agent shows the task; OpenAdapt turns it into a local program that repeats the steps with no model calls, checks each save, and stops when something doesn't match.
git clone https://github.com/OpenAdaptAI/OpenAdapt.git -
claude-plan-skills
SkillsAgent skills for managing multi-step tasks as GitHub issues. Create, implement, update, and close execution plans that survive across sessions.
git clone https://github.com/gjoranv/claude-plan-skills.git -
LowlandData Jobs
MCP serversJob postings: German roles from StepStone, and any company's Greenhouse or Lever board.
-
ac-jobs
MCP serversAdmission gate for AI agents: submit a step, get admit/hold/reject vs your constitution.
ac-jobs-mcp@0.1.1 -
CAD MCP Server
MCP serversMeasure STEP CAD files with your AI assistant: walls, clearances, draft, and revision diffs.
cad-mcp-server@0.8.1 -
.NET Debugger for MCP
MCP serversGive an AI agent a real .NET debugger: breakpoints, stepping, locals, expression evaluation.
DotnetDebugger.Mcp@0.7.1 -
Testorim
MCP serversAI browser tests from your coding agent: a verdict, failing steps, report, video and trace.
@testorim/cli@0.4.1 -
CallFlow AI
MCP serversPaid sales-call scoring and CRM next-step analysis for AI agents.
-
writ
MCP serversPolicy checks for AI agent writes (ALLOW/DENY/STEP_UP) with a tamper-evident audit log.
writ-mcp@0.2.5 -
mlua-swarm
MCP serversMCP server for mlua-swarm: engine that compiles flow.ir Blueprints and dispatches agent steps.
ghcr.io/ynishi/mse:0.32.1 -
mcp
MCP serversDebug a bad AI-agent run from your editor: which intent fails, at which step, and why.
@intencion/mcp@0.1.1 -
Riffle
MCP serversYour agent uses the web as text, not screenshots. Several steps per call, only changes come back.
@noetive/riffle@0.2.0 -
Summer
MCP serversAsk live marketing data anything to get verified answers, client-ready reports, and next steps.
-
Consegna.video
MCP serversClient portal for video studios: clients, projects, steps, quotes, call sheets, travel log.
-
agentl
MCP serversValidate, plan, preview and run YAML data pipelines (ETL with LLM steps) and debug failed runs.
agentl-etl@0.9.0 -
PlugMyAI
MCP serversPlain-English directory of which apps connect to ChatGPT, Claude, Gemini and Grok, with steps.
-
Eggtimer.app
MCP serversShareable timer links for countdowns, clock times, Pomodoro, Tabata and step recipes. No account.
-
Ecomhint
MCP serversEcommerce store audits: read findings with evidence and fix steps, track tasks, run new audits.
-
Ventriloquist
MCP serversTurn Mac apps into MCP tools via the accessibility API: no screenshots, no model per step.
ventriloquist-mcp@0.5.0 -
Argentic
MCP serversRun agents for hours. Argentic keeps their context sharp and records every step.
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.