Spec Driven Development
MCP Server that facilitates spec-driven development workflows, not just Vibe Coding.
Description from the maker (original English)
Would you make the shortlist? Score a job against your CV: fit, gaps, ATS score, likely questions.
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.
You need
Which app do you use?
Pick your app above. We remember it, so next time the button says “Install in …”.
Works in Claude on the web, desktop and mobile:
https://www.calibrd.com/mcpRun this in your terminal
claude mcp add --transport http agent https://www.calibrd.com/mcpPaste into .cursor/mcp.json in your project, or ~/.cursor/mcp.json
{
"mcpServers": {
"agent": {
"url": "https://www.calibrd.com/mcp"
}
}
}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": {
"agent": {
"type": "http",
"url": "https://www.calibrd.com/mcp"
}
}
}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.
ChatGPT connects only to servers on the internet:
https://www.calibrd.com/mcpMenu names can differ slightly by plan and over time.
Your choice stays on this device in a cookie; no account needed.
These settings are generated from the maker’s registry entry. If the README says otherwise, follow the README.
We have not read this server’s tool list yet; we check endpoints in rotation.
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 6, 2026
The registry name was verified against the domain calibrd.com (the registry checks domain ownership)
We have not read this repo from GitHub yet
We have not read this repo from GitHub yet
Not checked yet; we check endpoints in rotation
Not checked yet; we check endpoints in rotation
Not checked yet; we read the tool list when we check the endpoint
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.
The registry does not list a required key, though some servers ask you to sign in on first use.
It runs in the maker’s cloud. Connect over the internet with nothing to install, but what you send passes through the maker’s servers.
The GitHub repo last changed –, and the latest version (1.0.1) reached the registry 2 months ago.
Apps that support MCP, such as Claude Desktop, Claude Code, Cursor and VS Code. It connects by URL, so apps that accept remote MCP servers work too, such as ChatGPT in developer mode.
In the same category: Spec Driven Development, Remote Desktop Commander, dotnet-mcp
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.
MCP server for .NET symbols, XAML, source generators, and restricted workspace edit
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.
Will a hiring manager shortlist you for this role? Calibrd scores one job posting against your CV and answers that before you spend an evening on the application. It shows where you fall short at your level, the questions each round will ask, how your CV lands with a recruiter and with an applicant tracking system, and it drafts the cover letter when you decide the job is worth it.
This repository is the plugin manifest only. The server runs at https://www.calibrd.com/mcp.
Listed on Smithery and Glama, and in the official MCP registry as com.calibrd/agent.
Claude (claude.ai): Settings → Connectors → Add custom connector → URL https://www.calibrd.com/mcp.
Claude Code:
claude mcp add --transport http calibrd https://www.calibrd.com/mcp
Grok (grok.com / Grok Bot): grok.com/connectors → Custom → paste the URL.
Grok Build, Cursor, other MCP clients: copy .mcp.json into your project, or install this plugin from the xAI marketplace.
Give the tools a posting as text or as a link (public LinkedIn job pages, Greenhouse, Lever, Levels.fyi, careers pages). Connecting opens a Calibrd sign-in once. Reports are free, three a day. A pass removes the cap and unlocks every tool; payment is on calibrd.com, never in the chat.
| Tool | What it does | Gate |
|---|---|---|
calibrd_score_job | Match score 0–100 and the gaps at your level | Free |
calibrd_report | The full Calibrd report on one job | Free, 3 a day |
calibrd_review_cv | Recruiter and ATS scores, what to fix | Free |
calibrd_cover_letter | A draft from your CV for one job | One free, then a pass |
calibrd_status | What you have on Calibrd | Free |
calibrd_get_pass | A checkout link for a pass | Free to ask |
Most clients connect straight to https://www.calibrd.com/mcp and none of this is needed. bridge.mjs is here for the two cases that cannot: clients that speak only stdio, and directory scanners that need a process to start and introspect.
node ./bridge.mjs
No dependencies and no build step — it is one file on the Node standard library. It answers initialize and tools/list locally, so listing the tools needs no account and no network. Running one does: tools/call forwards to the hosted server with the bearer token in CALIBRD_ACCESS_TOKEN, and says so plainly when there isn't one. CALIBRD_MCP_URL overrides the endpoint.
The tool catalogue in bridge.mjs mirrors the hosted server. If the server gains or changes a tool, update the file — nothing enforces that automatically.
Calibrd Agent runs inside your assistant. Your CV, the job description and the report pass through your assistant's provider (Anthropic, OpenAI or xAI) under their terms. Calibrd itself keeps none of it: reports and CVs are generated and returned, not stored.
Full details: https://www.calibrd.com/agent and https://www.calibrd.com/privacy
MIT, for this manifest. Calibrd itself is a hosted service under its own terms.