Spec Driven Development
MCP Server that facilitates spec-driven development workflows, not just Vibe Coding.
Description from the maker (original English)
Install and run open-source OSINT tools in a local sandbox, asking before runs that touch a target.
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.
Which app do you use?
Pick your app above. We remember it, so next time the button says “Install in …”.
Download the maker’s .mcpb file
The link goes to the maker’s own file; we do not host or repackage it. Open the file and Claude Desktop installs it.
Run this in your terminal
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.
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.
These 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 against the domain otinstaller.com (the registry checks domain ownership)
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.
The registry does not list a required key, though some servers ask you to sign in on first use.
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 (0.16.1) reached the registry 13 days ago.
Apps that support MCP, such as Claude Desktop, Claude Code, Cursor and VS Code. You also need MCPB on your computer.
In the same category: Spec Driven Development, Remote Desktop Commander, Tools 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.
Web production tools for AI agents: contrast, JP text, WebP, JSON-LD, slugs, dates and 40+ more
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.
ot is the OSINT package manager. One command installs, runs, updates or removes any tool in the OTInstaller registry, the largest registry built only for OSINT tools (over 130 of them). No more cloning repositories, fixing Python versions and learning each tool's flags: every tool takes the same typed inputs, runs in a container that can't read your files, and saves its result in the same JSON shape.
Put ot (or ot.exe) somewhere on your PATH. Tools run in containers, so Docker Desktop or Podman must be running; with cosign installed, ot also verifies each image's signature. Then set it up:
ot start # pick starter packs and tools, AI agents and settings, then install
ot doctor # check Docker, cosign, the keychain and the registry
ot start asks at a terminal; ot start --tools --yes does the same from a script, and https://otinstaller.com/start builds the command for you.
ot search email # tools that take an email address
ot run osintverse-community/holehe e:someone@example.com ot runs # every run is saved under ./results; ot runs shows one ot pivot # what to run next on what a run found ot share # a link to the run's results that works for 24 hours
Typed inputs fill the matching input of any tool: u: username, e: email, d: domain, p: phone, ip: IP address and url: URL. Or let ot pick: ot auto someone@example.com runs every installed tool that takes an email address, and on a fresh machine offers to install a bundled playbook's tools first. ot playbook --list shows the playbooks. Tools that need an API key say so; ot keys setup walks you through them, and keys stay in your OS keychain.
--json (or OT_OUTPUT=json) gives JSON output and one-line JSON errors on stderr, and ot never prompts without a terminal. See https://otinstaller.com/docs/automation.ot mcp install claude (or claude-desktop, cursor, vscode, codex, gemini) adds ot's MCP server to your client. Agents ask you before any run that touches a target. See https://otinstaller.com/docs/agents.ot outdated lists installed tools with newer versions and ot update --all installs them. ot self-update installs a new release of ot after checking its signature.
ot counts installs and runs of registry packages, so the registry can show which tools are used and which versions fail. A count carries the tool and its version, how a run ended and how long it took, the container engine, what started it (a command, CI or an AI agent), and your OS, architecture and ot version. It never carries your inputs, targets or results, file paths, run ids, case names, keys or tokens, and tools installed from a local manifest are never counted. The registry keeps daily totals only.
ot telemetry # what is sent, and whether it is on
ot telemetry off # or set OT_NO_TELEMETRY=1 or DO_NOT_TRACK=1 OT_TELEMETRY_DEBUG=1 ot run … # print each count instead of sending it
Turning it off also stops the offer to report a failed run; DO_NOT_TRACK stops the daily update check too. Details: https://otinstaller.com/policy/privacy
Docs: https://otinstaller.com/docs/getting-started · CLI reference: https://otinstaller.com/docs/cli · Bugs and ideas: https://github.com/OTInstaller/feedback/issues · Source: https://github.com/OTInstaller/otinstaller
Licensed under the Apache License 2.0 (LICENSE).