Agentic Skills MCP server for AI agents
Let Claude, ChatGPT or your own agent read Agentic Skills: 2 typed functions through one MCP server. No Agentic Skills API key needed.
- Site
- agenticskills.io
- Functions
- 2
- Sign-in
- Not needed
- Works with
- MCP, HTTP, Node, Python
Connect
Just Agentic Skills
An MCP server for Agentic Skills alone, with one tool per function. Paste it into Claude, ChatGPT, Cursor or any MCP client as a remote server.
https://api.bowmark.ai/mcp/site/agenticskillsEvery site
One MCP server for Agentic Skills and every other site Bowmark covers. Your agent looks up what it needs and calls it.
https://api.bowmark.ai/mcpSet it up in your clientBoth need a Bowmark API key. The quickstart gets you one and a first result in a few minutes.
Functions
Open a function to see its arguments, what it returns and how to call it.
Read 2
getReads one agenticskills.io skill, MCP server, tool or workflow page by kind+slug or URL.Arguments
Name Type Required kindEntryKindNo slugstringNo urlstringOr an agenticskills.io entry URL instead of kind+slug.No Returns
AgenticSkillsEntrytype EntryKind = "skills" | "mcp" | "tools" | "workflows"; interface AgenticSkillsEntry { kind: EntryKind; slug: string; url: string; lastModified: string | null; name: string; description: string | null; author: { name: string; url: string | null } | null; license: string | null; keywords: string[]; category: string | null; subCategory: string | null; // an MCP server's transport, e.g. "Streamable HTTP" worksWith: string[]; // e.g. ["claude-code", "claude-ai"] dateModified: string | null; }HTTP endpoint
POST https://api.bowmark.ai/v1/sites/agenticskills/getCall it
import { bowmark } from "@bowmark/web"; const result = await bowmark.providers.agenticskills.get({ kind: "skills", slug: "docx" });import asyncio from bowmark_web import bowmark result = asyncio.run(bowmark.providers.agenticskills.get({"kind": "skills", "slug": "docx"}))curl -X POST https://api.bowmark.ai/v1/sites/agenticskills/get \ -H "Authorization: Bearer $BOWMARK_API_KEY" \ -H "Content-Type: application/json" \ -d '{"args":{"kind":"skills","slug":"docx"}}'// The body of a run: the MCP run tool, or POST /v1/run return await bowmark.providers.agenticskills.get({ kind: "skills", slug: "docx" });searchFinds agenticskills.io directory entries (skills, MCP servers, tools, workflows) whose slug matches the query keywords, read off the site's own…Arguments
Name Type Required querystringMatched against entry slugs; omit to list.No kindEntryKindNo limitnumber1-25, default 10.No Returns
AgenticSkillsEntry[]type EntryKind = "skills" | "mcp" | "tools" | "workflows"; interface AgenticSkillsEntry { kind: EntryKind; slug: string; url: string; lastModified: string | null; name: string; description: string | null; author: { name: string; url: string | null } | null; license: string | null; keywords: string[]; category: string | null; subCategory: string | null; // an MCP server's transport, e.g. "Streamable HTTP" worksWith: string[]; // e.g. ["claude-code", "claude-ai"] dateModified: string | null; }HTTP endpoint
POST https://api.bowmark.ai/v1/sites/agenticskills/searchCall it
import { bowmark } from "@bowmark/web"; const result = await bowmark.providers.agenticskills.search({ query: "seo", kind: "skills", limit: 3 });import asyncio from bowmark_web import bowmark result = asyncio.run(bowmark.providers.agenticskills.search({"query": "seo", "kind": "skills", "limit": 3}))curl -X POST https://api.bowmark.ai/v1/sites/agenticskills/search \ -H "Authorization: Bearer $BOWMARK_API_KEY" \ -H "Content-Type: application/json" \ -d '{"args":{"query":"seo","kind":"skills","limit":3}}'// The body of a run: the MCP run tool, or POST /v1/run return await bowmark.providers.agenticskills.search({ query: "seo", kind: "skills", limit: 3 });
Use it from code
- Node
npm i @bowmark/web - Python
pip install bowmark-web - HTTP
POST /v1/sites/agenticskills/<function> - OpenAPI
/v1/sites/agenticskills/openapi.json