Agentai
Call the agent.ai public Actions API through the agentai MCP tools — web scraping, search, LinkedIn/Twitter/Instagram/Bluesky data, company and person enrichment, LLM/image/audio generation, agent discovery and invocation, plus 170+ catalog actions via invoke_action. Use when the user wants agent.ai data or actions, mentions agent.ai, or needs enrichment/social/scraping capabilities this environment lacks natively.From its SKILL.md
npx -y skills add OnStartups/builder-plugins --skill agentaiAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
2 things to look at
- no licenseNo license file was found in the repository. Code published without one is not open source by default, so using it at work is a question for whoever answers licensing questions where you are.
- 1 stars1 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
What its file declares
Copied from the file, not written here
The file declares its own license as MIT. That is the author’s claim about this one file, and it is not the same thing as the license GitHub reports for the repository, which is listed with the other numbers below.
SKILL.md
2.8 KB, as published. Nobody here has run it
agent.ai Actions
What this plugin provides
An MCP server exposing the agent.ai public Actions API (POST https://api-lr.agent.ai/v1/action/<name>, Bearer auth):
- 51 typed tools for the general-purpose endpoints —
grab_web_text,get_search_results,get_google_news,get_linkedin_profile,get_company_object,enrich_person,invoke_llm,generate_image,invoke_agent,rest_call,describe_agent,search(agent discovery), and the rest of the data-retrieval / social / business-data / outputs / workflow set. list_actions{category?}— browse the full 185-action catalog (29 categories); marks Builder-UI-only actions.describe_action{action_type}— label, category, inputs, endpoint, and full input JSON schema.invoke_action{action_type, inputs, output_variable_name?}— call ANY public action, including the agent-pack pipelines (Company Research v2, Meeting Prep, Prospect Research, Content Marketing Team, HubSpot v2, ...) that don't have a dedicated typed tool.
Setup
Requires AGENTAI_API_KEY in the environment before Claude Code starts. Get a key at agent.ai/user/settings#credits. Calls consume agent.ai credits.
Workflow
- Prefer the typed tool when one exists — schemas are exact (enums, required fields).
- For anything else:
list_actions(optionally by category) →describe_actionto get the input schema →invoke_action. output_variable_nameis optional everywhere; the server defaults it when the API requires one.- Agent-pack pipelines: use the
run_full_*/*_run_optimized_pipelineorchestrated action for one-shot results; use granular step actions only when branching or caching intermediate stages. - To run a published agent:
searchto find it,describe_agentfor its inputs/outputs, theninvoke_agentwith{id, input}.
Notes
- Actions marked Builder-UI only (input capture, control flow, Google Doc/Sheet outputs, Generative UI) cannot be called via the API;
invoke_actionrejects them with an explanation. - Full catalog reference:
references/actions-by-category.mdin this plugin. - Errors surface as tool errors with the API's message; a 4xx usually means a missing/invalid input or insufficient credits.