Spec Driven Development
MCP Server that facilitates spec-driven development workflows, not just Vibe Coding.
Description from the maker (original English)
TalentLMS MCP server: users, courses, groups, branches, reporting, and assessments
These three are never merged into one score: opinions, measurements and popularity are different things.
We have not written a plain-language summary for this one yet. Below are the facts we read from the registry.
Pick the AI app you use, then copy the settings.
TALENTLMS_API_KEY, TALENTLMS_DOMAIN, TALENTLMS_REQUEST_TIMEOUTValues marked secret are keys to your account. Never share them or paste them into a chat.
You need
Which app do you use?
Pick your app above. We remember it, so next time the button says “Install in …”.
Open Claude Desktop → Settings → Developer → Edit Config, and paste this into claude_desktop_config.json
{
"mcpServers": {
"talentlms": {
"command": "npx",
"args": [
"-y",
"@mindstone/mcp-server-talentlms"
],
"env": {
"TALENTLMS_API_KEY": "your-value",
"TALENTLMS_DOMAIN": "your-value",
"TALENTLMS_REQUEST_TIMEOUT": "your-value"
}
}
}
}Run this in your terminal
claude mcp add talentlms --env TALENTLMS_API_KEY=your-value --env TALENTLMS_DOMAIN=your-value --env TALENTLMS_REQUEST_TIMEOUT=your-value -- npx -y @mindstone/mcp-server-talentlmsFill in the empty values before running it.
Paste into .cursor/mcp.json in your project, or ~/.cursor/mcp.json
{
"mcpServers": {
"talentlms": {
"command": "npx",
"args": [
"-y",
"@mindstone/mcp-server-talentlms"
],
"env": {
"TALENTLMS_API_KEY": "your-value",
"TALENTLMS_DOMAIN": "your-value",
"TALENTLMS_REQUEST_TIMEOUT": "your-value"
}
}
}
}Your browser asks to open the app, then the app shows the settings and asks you to confirm. Key values are left empty for you to fill in.
Paste into .vscode/mcp.json in your project
{
"servers": {
"talentlms": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@mindstone/mcp-server-talentlms"
],
"env": {
"TALENTLMS_API_KEY": "your-value",
"TALENTLMS_DOMAIN": "your-value",
"TALENTLMS_REQUEST_TIMEOUT": "your-value"
}
}
}
}Your browser asks to open the app, then the app shows the settings and asks you to confirm. Key values are left empty for you to fill in.
This one runs on your computer, and ChatGPT can only connect to servers on the internet. Pick another app.
Your choice stays on this device in a cookie; no account needed.
TALENTLMS_REQUEST_TIMEOUT envThese settings are generated from the maker’s registry entry. If the README says otherwise, follow the README.
Runs on your computer; the tool list appears in your AI app after you install it.
We check information anyone can see; we have not read the code. Checks that do not apply are left out of the count. · Checked Nov 7, 2026
The registry name was verified with the GitHub account mindstone, which owns the repo
We have not read this repo from GitHub yet
We have not read this repo from GitHub yet
This one runs on your computer; there is no internet endpoint
Runs on your computer and uses local settings instead
Runs on your computer; we can only read tool lists from internet endpoints
Compared with every active server in this category in the registry. Stars count only when the publisher owns the repo.
It passed 1 of 1 applicable basic checks. We have not read the code. Before adding a key or token, see what access the server asks for and use a key with only the permissions you need.
You need to fill in: TALENTLMS_API_KEY, TALENTLMS_DOMAIN
It runs on your computer. Your AI app starts it when needed, and data does not pass through the maker’s servers (unless it calls an online service itself).
The GitHub repo last changed –, and the latest version (0.4.0) reached the registry 3 months ago.
Apps that support MCP, such as Claude Desktop, Claude Code, Cursor and VS Code. You also need Node.js on your computer.
In the same category: Spec Driven Development, Remote Desktop Commander, Date Math
Servers in the same category from other makers, sorted by stars.
Reading a card:★ GitHub starsiThree pillars: reviews · checks · usageiUpdated = latest version published to the registryi
MCP Server that facilitates spec-driven development workflows, not just Vibe Coding.
Remote Desktop Commander: use files, terminal and processes on your own computers from any AI app.
Exact date/time math for agents: business days, holidays, time zones, cron, RRULE, SLA. x402 paid.
Copied from the maker’s repo as written. PopNx MCP has not reviewed or endorsed it. HTML, images and scripts are removed. Links lead off this site.
TalentLMS MCP server for Model Context Protocol hosts. Manage users, courses, groups, branches, categories, enrolments, reporting, and assessments in TalentLMS through a standardised MCP interface.
TALENTLMS_API_KEY)STATUS.jsonAfter clicking the button, your host will prompt you to fill: TALENTLMS_API_KEY, TALENTLMS_DOMAIN, TALENTLMS_REQUEST_TIMEOUT.
Manual config for Claude Desktop / Claude Code / Goose / Continue.dev (TalentLMS)
{
"mcpServers": { "TalentLMS": { "command": "npx", "args": [ "-y", "@mindstone/mcp-server-talentlms" ], "env": { "TALENTLMS_API_KEY": "", "TALENTLMS_DOMAIN": "", "TALENTLMS_REQUEST_TIMEOUT": "30000" } } } }
cd <path-to-repo>/connectors/talentlms
npm install npm run build
npx -y @mindstone/mcp-server-talentlms
node dist/index.js
TALENTLMS_API_KEY — TalentLMS API keyTALENTLMS_DOMAIN — TalentLMS subdomain (e.g. acme for acme.talentlms.com)TALENTLMS_REQUEST_TIMEOUT — request timeout in milliseconds (default: 30000)MCP_HOST_BRIDGE_STATE — optional path to a host bridge state file used for credential managementMINDSTONE_REBEL_BRIDGE_STATE — backwards-compatible alias for MCP_HOST_BRIDGE_STATE{
"mcpServers": { "TalentLMS": { "command": "npx", "args": ["-y", "@mindstone/mcp-server-talentlms"], "env": { "TALENTLMS_API_KEY": "your-api-key", "TALENTLMS_DOMAIN": "your-domain" } } } }
{
"mcpServers": { "TalentLMS": { "command": "node", "args": [" /connectors/talentlms/dist/index.js"], "env": { "TALENTLMS_API_KEY": "your-api-key", "TALENTLMS_DOMAIN": "your-domain" } } } }
List tools paginate: TalentLMS returns 20 items per page by default — pass page_size (max 1000) and page_number to page through larger tenants.
configure_talentlms — Configure TalentLMS API credentialslist_talentlms_users — List users (paginated)get_talentlms_user — Get a user's full profile by ID or emailcreate_talentlms_user — Create a new userupdate_talentlms_user — Update an existing user (name, email, login, password, bio, timezone, deactivation date; non-privileged user types only)set_talentlms_user_status — Activate or deactivate a userget_talentlms_user_courses — Get all courses a user is enrolled inlist_talentlms_courses — List courses (paginated)get_talentlms_course — Get full course details by IDcreate_talentlms_course — Create a new courseget_talentlms_course_users — Get all users enrolled in a courseenrol_talentlms_user — Enrol a user into a courseunenrol_talentlms_user — Remove a user from a courseget_talentlms_course_sso_link — Generate an SSO link to launch a user into a courselist_talentlms_groups — List groups (paginated)get_talentlms_group — Get group details including members and coursescreate_talentlms_group — Create a new groupadd_course_to_talentlms_group — Assign a course to a grouplist_talentlms_branches — List branches (paginated, multi-tenant)list_talentlms_categories — List course categories (paginated)get_talentlms_site_info — Get site-level statistics and configurationget_talentlms_timeline — Get activity timeline for users or coursesget_talentlms_user_progress — Get detailed progress for a user in a courseget_talentlms_leaderboard — Gamification leaderboard (users ranked by points; derived from the full user list, paged 1000 at a time so no user is dropped)get_talentlms_user_certifications — Get a user's issued certifications with expiration datesget_talentlms_test_answers — Get a user's answers for a test/quizget_talentlms_survey_answers — Get a user's responses to a surveyget_talentlms_ilt_sessions — Get instructor-led training sessions for a unit envelopes so the host model treats it as data, not instructions. Ids, statuses, timestamps, and other metadata are deliberately left raw so tool chaining (e.g. copying a user_id into the next call) keeps working.create_talentlms_user and update_talentlms_user only accept the non-privileged Learner/Trainer user types — Administrator/SuperAdmin accounts must be managed in the TalentLMS UI.FSL-1.1-MIT — Functional Source License, Version 1.1, with MIT future licence. The software converts to MIT licence on 2030-04-08.