LinkHut connector for AI agents

CALL ANY TOOL

11 tools for bookmarks in LinkHut: save and delete bookmarks, list recent and dated posts, filter by tag or URL, suggest tags, and rename or remove tags.

linkhut_add_post

Post add

Save a bookmark with a title, optional notes and tags. Returns result_code, which is done on success. Use to create or overwrite a bookmark for a URL. Use linkhut_delete_post to remove one.

Parameters

Name

Type

Required

Description

description

string

Required

Title of the bookmark.

url

string

Required

URL to bookmark, for example https://sourcehut.org/.

dt

string

Optional

Creation time to record for the bookmark; defaults to now.

extended

string

Optional

Notes or long description for the bookmark.

replace

string

Optional

Set to no to keep the existing bookmark when the URL is already saved; the server replaces it by default. One of: `yes`, `no`.

shared

string

Optional

Set to no to make the bookmark private. One of: `yes`, `no`.

tags

string

Optional

Comma-delimited tags to attach, for example git,oss.

toread

string

Optional

Set to yes to mark the bookmark as unread. One of: `yes`, `no`.

linkhut_delete_post

Post delete

linkhut_delete_tag

Delete tag

linkhut_get_last_update

Update get last

linkhut_get_posts

Get posts

linkhut_list_all_posts

List all posts

linkhut_list_post_dates

List post dates

linkhut_list_recent_posts

List recent posts

linkhut_list_tags

List tags

linkhut_rename_tag

Rename tag

linkhut_suggest_tags

Suggest tags

Build your Agent

Same auth pattern across LangChain, OpenAI, Anthropic, and Google ADK.

import { ScalekitClient } from "@scalekit-sdk/node";
import { createReactAgent } from "@langchain/langgraph/prebuilt";

const sk = new ScalekitClient(env.SCALEKIT_ENV_URL, env.SCALEKIT_CLIENT_ID, env.SCALEKIT_CLIENT_SECRET);

// LinkHut tools scoped to this user
const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["linkhut"], toolNames: [
    "linkhut_suggest_tags",
    "linkhut_add_post",
    "linkhut_list_recent_posts"] },
  pageSize: 100,
});

const agent = createReactAgent({ llm, tools });
await agent.invoke({ messages: [{ role: "user", content: "Save this article with suggested tags and show my recent bookmarks" }] });

import OpenAI from "openai";
import { ScalekitClient } from "@scalekit-sdk/node";

const sk = new ScalekitClient(env.SCALEKIT_ENV_URL, env.SCALEKIT_CLIENT_ID, env.SCALEKIT_CLIENT_SECRET);
const openai = new OpenAI();

const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["linkhut"] }, pageSize: 100,
});

const res = await openai.chat.completions.create({
  model: "gpt-5",
  messages: [{ role: "user", content: "Save this article with suggested tags and show my recent bookmarks" }],
  tools,
});

// Execute the tool call with the user's vaulted LinkHut OAuth token
await sk.tools.executeTool(res.choices[0].message.tool_calls[0], "user_123");

import Anthropic from "@anthropic-ai/sdk";
import { ScalekitClient } from "@scalekit-sdk/node";

const sk = new ScalekitClient(env.SCALEKIT_ENV_URL, env.SCALEKIT_CLIENT_ID, env.SCALEKIT_CLIENT_SECRET);
const anthropic = new Anthropic();

const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["linkhut"] }, pageSize: 100,
});

const msg = await anthropic.messages.create({
  model: "claude-sonnet-5",
  max_tokens: 1024,
  messages: [{ role: "user", content: "Save this article with suggested tags and show my recent bookmarks" }],
  tools,
});

// Tool call runs with the user's vaulted LinkHut OAuth token
await sk.tools.executeTool(msg.content, "user_123");

import { Agent } from "@google/adk/agents";
import { ScalekitClient } from "@scalekit-sdk/node";

const sk = new ScalekitClient(env.SCALEKIT_ENV_URL, env.SCALEKIT_CLIENT_ID, env.SCALEKIT_CLIENT_SECRET);

const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["linkhut"] }, pageSize: 100,
});

const agent = new Agent({
  name: "bookmarks_agent",
  model: "gemini-2.5-pro",
  instruction: "LinkHut tools scoped to this user",
  tools,
});

await agent.run("Save this article with suggested tags and show my recent bookmarks");

Try these prompts

Copy any prompt into your agent. Each maps directly to a LinkHut tool. Click to copy, paste into your agent, done.

Save

Copy the prompt

Copied

Save https://example.com/postgres-indexing with the tags postgres and performance.

Copy the prompt

Copied

Suggest tags for this article before I save it.

Copy the prompt

Copied

Save this link and mark it to read later.

Find

Copy the prompt

Copied

Show my 10 most recent bookmarks tagged ai.

Copy the prompt

Copied

Which days last month did I save the most bookmarks?

Copy the prompt

Copied

Have my bookmarks changed since yesterday?

Tags

Copy the prompt

Copied

List my tags and how many bookmarks use each.

Copy the prompt

Copied

Rename the tag js to javascript across all bookmarks.

Copy the prompt

Copied

Remove the tag temp from every bookmark that has it.

SEE HOW AUTH WORKS

Each user signs in to LinkHut once, and Scalekit stores and refreshes their tokens. Tokens stay vaulted, every call is scope checked, and every action is logged.

1

Authorize

Your user connects

LinkHut

once. We tie it to their identity and the meetings they approved — no shared bot account, no org-wide access

Who:

user ‘A’

when:

Once per user

access:

Limited to user

2

Store

Their

LinkHut

token lives in a vault scoped to them. User A's meetings are never reachable by an agent acting for user B, even on the same connection

vault:

encrypted

scope:

per-user

tokens:

auto-refreshed

3

Resolve

When your agent calls a

LinkHut

tool, we fetch the right token server-side. It never touches your agent, never appears in the LLM context, never shows up in your logs

speed:

~40ms

check:

before every call

seen by:

nobody

4

Audit

Every

LinkHut

tool call is logged — who triggered it, which meeting was fetched, what came back. 90 days of history, tied to the user who authorized it

history:

90 days

export:

SIEM-ready

logged:

every call

Test other agents

See the same per-user auth pattern across other productivity and knowledge connectors.

GTM and RevOps Teams

Competitive intelligence briefing agent

Scans Gong calls for competitor mentions, matches each one to its Notion battlecard, and DMs every affected rep a single Slack digest per cycle. Every call runs as the PMM who owns the briefing, never a shared bot.

Test other agents

See the same per-user auth pattern across other productivity and knowledge connectors.

GTM

Competitive intelligence briefing agent

Scan Gong calls for competitor mentions, match each one to its Notion battlecard, and DM every affected rep a single Slack digest.

Why Scalekit

Secure your agent's access. Connectors ship in minutes

01.

Shared tokens break per-user analytics

A shared LinkHut token looks fine in a demo. In production every bookmark the agent saves looks like one service account, and you cannot tell which user triggered it. Scalekit resolves the credential of the actual user who triggered the agent, never a shared bot.

// shared token
audit → bot_service_account

// scalekit
audit → user_abc ✓

02.

Authentication is not authorization

03.

Multi-tenancy is architectural

04.

LinkHut today. Ten connectors tomorrow.

“Our agents act across Salesforce, Gong, Google Drive, and more, on behalf of every customer. Scalekit behind the scenes meant we can keep adding tools without ever rebuilding how credentials or tool calling work.”

Venu Madhav Kattagoni

Head of Engineering / Von

FAQs

Frequently Asked Questions

Does the agent access LinkHut as the user or through a shared service account?

As the user. Each user signs in to LinkHut once, and Scalekit stores and refreshes their tokens. Bookmarks and tag changes the agent makes are attributed to that user in your audit trail, not a shared service account.

Where is the LinkHut OAuth token stored?

In Scalekit's managed AES-256 token vault, namespaced per tenant. Refresh is automatic. Revocation is a single dashboard action. Credentials never appear in prompts, logs, or LLM context.

Can I limit what the agent does in LinkHut?

Yes. Filter by tool name in listScopedTools to expose only what you want, for example the list and tag suggestion tools without linkhut_delete_post, which deletes a saved bookmark, or linkhut_delete_tag. Scalekit also enforces scope checks before every API call.

What happens when a user revokes LinkHut access?

The connection is invalidated on the next tool call. Subsequent requests for that user fail closed with a clear error. Other users in the tenant remain unaffected. The event is logged for audit.

Does deleting a tag delete the bookmarks that use it?

No. linkhut_delete_tag removes the tag from every bookmark that has it and keeps the bookmarks. To remove a bookmark itself, the agent uses linkhut_delete_post with the bookmark's URL.

LinkHut MCP server for AI agents

Tools your bookmarks agent reaches for on LinkHut, scoped per user.