Find free AI skills and Workotron workflows for small businesses, and install the skills.
Maintain this server? Claim it
Call this server's tools from your browser. Nothing to install.
Requests go through mcptry because browsers can't call most MCP servers directly. Header values are sent to the server for that request only and are never stored or logged.
Tool list from our last check. Connect live to refresh it.
Give one of the user's marks. A thumb on a listing: up, down, or none to take it back; a skill is rated only after the user took it, so take it with take first. A helpful mark on a post, a comment on a listing or a post in a thread, which the user's own post never takes. Or, on a question the user asked, the mark on the reply that solved it. A post is named by its number, which its line states on the page's markdown: read the page with read first. It needs the user's key. One mark a call: pass thumb, or helpful with post, or solved with post. Mark only what the user told you to.
The listing's or the thread's address, full or as its path.
The post's number on the page at address, for a helpful or a solved mark.
A listing's thumb: up, down, or none to take it back.
On the user's own question, with post: true marks that reply as the answer. False takes the mark back and needs no post.
With post: true marks the post helpful for the user, false takes the mark back.
This tool isn't marked read-only, so it may change something on the server or in an account you connected.
Pick your client. Values in capitals, like YOUR_TOKEN, are yours to fill in.
Run in a terminal
claude mcp add --transport http skills https://skills.workotron.com/mcp
Give one of the user's marks. A thumb on a listing: up, down, or none to take it back; a skill is rated only after the user took it, so take it with take first. A helpful mark on a post, a comment on a listing or a post in a thread, which the user's own post never takes. Or, on a question the user asked, the mark on the reply that solved it. A post is named by its number, which its line states on the page's markdown: read the page with read first. It needs the user's key. One mark a call: pass thumb, or helpful with post, or solved with post. Mark only what the user told you to.
| Argument | Type | Description |
|---|---|---|
| post | integer | The post's number on the page at address, for a helpful or a solved mark. |
| thumb | string | A listing's thumb: up, down, or none to take it back. |
| solved | boolean | On the user's own question, with post: true marks that reply as the answer. False takes the mark back and needs no post. |
| address* | string | The listing's or the thread's address, full or as its path. |
| helpful | boolean | With post: true marks the post helpful for the user, false takes the mark back. |
{
"type": "object",
"required": [
"address"
],
"properties": {
"post": {
"type": "integer",
"minimum": 0,
"description": "The post's number on the page at address, for a helpful or a solved mark."
},
"thumb": {
"enum": [
"up",
"down",
"none"
],
"type": "string",
"description": "A listing's thumb: up, down, or none to take it back."
},
"solved": {
"type": "boolean",
"description": "On the user's own question, with post: true marks that reply as the answer. False takes the mark back and needs no post."
},
"address": {
"type": "string",
"description": "The listing's or the thread's address, full or as its path."
},
"helpful": {
"type": "boolean",
"description": "With post: true marks the post helpful for the user, false takes the mark back."
}
},
"additionalProperties": false
}Send a post as the user: a comment on a listing's discussion, a reply in a thread, or a new thread in the User Forum. It needs the user's key and the display name they picked. The post is marked as sent by an AI agent. It waits for review like any member's post, and until then only the user sees it. Write what the user asked you to say.
| Argument | Type | Description |
|---|---|---|
| on | string | The address to post at: a listing's, for a comment, or a thread's, for a reply. Absent to start a new thread, which takes a title. |
| kind | string | A new thread's kind: a question, or knowledge the user shares. A question when absent. |
| text* | string | The post, 2 to 4,000 characters. |
| title | string | A new thread's title, 2 to 140 characters. |
{
"type": "object",
"required": [
"text"
],
"properties": {
"on": {
"type": "string",
"description": "The address to post at: a listing's, for a comment, or a thread's, for a reply. Absent to start a new thread, which takes a title."
},
"kind": {
"enum": [
"question",
"knowledge"
],
"type": "string",
"description": "A new thread's kind: a question, or knowledge the user shares. A question when absent."
},
"text": {
"type": "string",
"description": "The post, 2 to 4,000 characters."
},
"title": {
"type": "string",
"description": "A new thread's title, 2 to 140 characters."
}
},
"additionalProperties": false
}A page of the directory as markdown: a listing's page with who it is for, what it does, when to use it, its files and its discussion; a business area's, a platform's or a tag's whole list; the Users Forum and Announcements channels and their threads. With no address it answers the first page, which says what the directory holds and links every business area. A page longer than 60,000 characters comes in parts: a part that is not the last ends with a line that says which from reads the next part. A skill's file, at the address take lists for it, comes as its text, for an app that cannot fetch that address itself: the first line, in square brackets, states the file's size and SHA-256 and is not part of the file, and everything after it is the file as it is. Write it unchanged and check its SHA-256. A file that is not text, or is larger than 256 KB, is fetched at its address.
| Argument | Type | Description |
|---|---|---|
| from | integer | The character to read from, as the last line of an earlier part says. 0 when absent. |
| address | string | The page's address: a full address from a search result or a page's link, or its path, like `unpaid-invoice-chaser` or `skills/finance`. Absent for the first page. Or the address of a skill's file, as take lists it, like `unpaid-invoice-chaser/files/SKILL.md`. |
{
"type": "object",
"required": [],
"properties": {
"from": {
"type": "integer",
"minimum": 0,
"description": "The character to read from, as the last line of an earlier part says. 0 when absent."
},
"address": {
"type": "string",
"description": "The page's address: a full address from a search result or a page's link, or its path, like `unpaid-invoice-chaser` or `skills/finance`. Absent for the first page. Or the address of a skill's file, as take lists it, like `unpaid-invoice-chaser/files/SKILL.md`."
}
},
"additionalProperties": false
}Find skills and Workotron workflows by words or by #tags, the best match first, 24 a page. Words match a listing's name, its one line and its texts, a typo forgiven on a longer word. A #tag is a business area (#finance, #marketing) or a product (#claude, #chatgpt). Each result carries the listing's name, its kind, its one line and its address: read the address with read, or install it with take. The result says how many pages the answer has: pass page to read the next. A search of words with no kind also answers the forum's threads that hold every word, each with its address to read.
| Argument | Type | Description |
|---|---|---|
| kind | string | Only skills, or only Workotron workflows. Absent for both. |
| page | integer | Which page of the answer, from 1. The first when absent. |
| query* | string | Words, #tags or both: `invoice reminders`, `#finance`, `newsletter #marketing`. |
{
"type": "object",
"required": [
"query"
],
"properties": {
"kind": {
"enum": [
"skill",
"workflow"
],
"type": "string",
"description": "Only skills, or only Workotron workflows. Absent for both."
},
"page": {
"type": "integer",
"minimum": 1,
"description": "Which page of the answer, from 1. The first when absent."
},
"query": {
"type": "string",
"description": "Words, #tags or both: `invoice reminders`, `#finance`, `newsletter #marketing`."
}
},
"additionalProperties": false
}Send a skill the user made to the directory for review, or a new version of a skill they shared. It needs the user's key and the display name they picked. It takes two calls and one upload. Call it first with no arguments: it answers the sharing agreement, the business areas and the products to pick from, and each field's bounds. Show the user the agreement and go on only when the user says yes to it. Then call it with agreement and details: it checks them and answers a one-time address. Send the skill's folder to that address yourself as one zip, with an HTTP PUT, within 15 minutes. The zip holds SKILL.md at its top, or one folder with SKILL.md at that folder's top. Nothing of the files rides in a tool call. The skill is listed only after Workotron reviews and approves it.
| Argument | Type | Description |
|---|---|---|
| details | object | What the listing says of the skill. The first answer gives each field's bounds and the ids to pick from. |
| replaces | string | The address of the user's own listed skill this is a new version of. Absent for a new skill. |
| agreement | string | The id of the sharing agreement the user said yes to, from this tool's first answer. Absent on the first call. |
{
"type": "object",
"required": [],
"properties": {
"details": {
"type": "object",
"required": [
"name",
"line",
"category",
"products",
"version",
"who_for",
"what_it_does",
"about"
],
"properties": {
"line": {
"type": "string",
"description": "What the skill does, in one line."
},
"name": {
"type": "string",
"description": "The listing's title: `Unpaid invoice chaser`."
},
"about": {
"type": "array",
"items": {
"type": "string"
},
"description": "The user's own description, a paragraph each."
},
"models": {
"type": "array",
"items": {
"type": "string"
},
"description": "The models the user recommends, by name."
},
"version": {
"type": "string",
"description": "The version as the user numbers it: `1.0`."
},
"who_for": {
"type": "array",
"items": {
"type": "string"
},
"description": "Who the skill is for, a line each."
},
"category": {
"type": "string",
"description": "The id of the one business area it is for: `finance`."
},
"products": {
"type": "array",
"items": {
"type": "string"
},
"description": "The ids of the products it works in: `claude`, `chatgpt`."
},
"what_it_does": {
"type": "array",
"items": {
"type": "string"
},
"description": "What the skill does, a line each."
},
"other_products": {
"type": "array",
"items": {
"type": "string"
},
"description": "Products the directory has no id for, by name."
}
},
"description": "What the listing says of the skill. The first answer gives each field's bounds and the ids to pick from."
},
"replaces": {
"type": "string",
"description": "The address of the user's own listed skill this is a new version of. Absent for a new skill."
},
"agreement": {
"type": "string",
"description": "The id of the sharing agreement the user said yes to, from this tool's first answer. Absent on the first call."
}
},
"additionalProperties": false
}What you need to install a skill: the address of its zip, the folder the zip holds, and each file's path, address, size and SHA-256. Fetch the zip and unpack it into your skills folder, or fetch each file and write it under the skill's folder. Nothing of the files rides in this result. If you cannot fetch an address, read each file with read at its address. With the user's key the skill counts as the user's own copy, counted once. A Workotron workflow is added in the Workotron app, and take says how.
| Argument | Type | Description |
|---|---|---|
| address* | string | The skill's address, full or as its path: `unpaid-invoice-chaser`. |
{
"type": "object",
"required": [
"address"
],
"properties": {
"address": {
"type": "string",
"description": "The skill's address, full or as its path: `unpaid-invoice-chaser`."
}
},
"additionalProperties": false
}We read every tool's name, description and inputs the way the model will, looking for instructions hidden from you. A clean result means no warning signs, not a guarantee. Scanned Nov 18, 2026.