Spec Driven Development
MCP Server that facilitates spec-driven development workflows, not just Vibe Coding.
Description from the maker (original English)
Public DNS, certificate transparency, and identity observations.
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 …”.
Open Claude Desktop → Settings → Developer → Edit Config, and paste this into claude_desktop_config.json
{
"mcpServers": {
"recon": {
"command": "uvx",
"args": [
"recon-tool",
"mcp"
]
}
}
}Run this in your terminal
claude mcp add recon -- uvx recon-tool mcpPaste into .cursor/mcp.json in your project, or ~/.cursor/mcp.json
{
"mcpServers": {
"recon": {
"command": "uvx",
"args": [
"recon-tool",
"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": {
"recon": {
"type": "stdio",
"command": "uvx",
"args": [
"recon-tool",
"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.
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 6, 2026
The registry name was verified with the GitHub account blisspixel, 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.
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 (2.27.0) reached the registry 10 days ago.
Apps that support MCP, such as Claude Desktop, Claude Code, Cursor and VS Code. You also need Python (uv) on your computer.
In the same category: Spec Driven Development, Remote Desktop Commander, topo^alpin
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.
Avalanche bulletins and mountain weather forecasts for any place in the Alps.
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.
Point recon at a domain to see its public technology and identity footprint: email providers and controls, identity indicators, SaaS services, and cloud infrastructure. No credentials, API keys, or active scanning. Use the CLI for a quick lookup, versioned JSON for automation, or the local MCP server from an agent.
recon reports evidence-backed observations, not a complete inventory or a security verdict. A domain does not establish an organization's boundaries.
Synthetic illustration, generated, not captured. The real formatter renders a deterministic, no-network fixture for Example Industries Ltd. No real organization is depicted, and no live lookup of reserved example.com reproduces this fixture.
Accessible text transcript
demo@recon:~$ recon example.com # synthetic fixture, not a captured run
6 sources: 5 matched, 1 no match Example Industries Ltd (unverified) example.com Reserved name: results are public residue, not an organization. ────────────────────────────────────────────────────────────────────────────── Provider Microsoft 365 + Proofpoint gateway Tenant a1b2c3d4-e5f6-7890-abcd-ef1234567890 • NA Tenant domain example-industries.onmicrosoft.example.com Auth Federated Confidence ●●● High (3 sources)
Services Email Microsoft 365, Proofpoint, DMARC reject, DKIM, SPF strict, MTA-STS enforce Identity Okta Cloud Cloudflare (CDN/edge), AWS Route 53 (DNS) Security Wiz Security Data & Analytics Snowflake, Datadog Collaboration Slack, Atlassian (Jira/Confluence), GitHub, Zoom Evidence roles: --explain
High-signal related domains login.example.com, support.example.com, status.example.com
Insights Federated identity observed; identity-vendor indicators: Okta Email security: observed controls: DMARC reject, DKIM, SPF strict, MTA-STS
macOS / Linux:
curl -fsSL https://raw.githubusercontent.com/pueo-labs/recon/main/scripts/install.sh | bash
Windows (PowerShell):
powershell -NoProfile -ExecutionPolicy Bypass -Command "irm https://raw.githubusercontent.com/pueo-labs/recon/main/scripts/install.ps1 | iex"
The installer sets up recon for your user account, including Python when needed. Open a new terminal afterward. Python 3.15 is the default development and release runtime; 3.11 through 3.15 remain supported. Already have a supported Python? Use pip install recon-tool in a virtual environment, or uv tool install --python 3.15 recon-tool / pipx install --python python3.15 recon-tool on managed distributions like Arch Linux and Omarchy. For review-before-run instructions, other package managers, updates, and recovery, see the installation guide.
recon --version # offline install check
recon doctor # online connectivity and installation diagnostics
Lookups make DNS queries visible to recursive and authoritative infrastructure. MTA-STS is the only default target-owned HTTP request; Google CSE and BIMI certificate probes require explicit --direct-probes. There is no port scanning or application crawling. Replace the placeholder to start:
recon "<domain-you-want-to-review>"
Ordinary lookups may reuse the 24-hour result cache and say so when they do; a result whose collection had unavailable sources is never reused. Use --no-cache to bypass the cache for both reading and writing; certificate-transparency enrichment has a separate cache. See first lookup and cache behavior.
The bare command stays compact. Request evidence or structured output when needed:
recon example.com # compact panel
recon example.com --explain # evidence and source status recon example.com --json # structured record recon example.com --plain # linear text for screen readers and grep recon review example.com # fresh, evidence-linked review bundle recon batch domains.txt --json # look up a supplied domain list recon delta example.com # compare with a cached baseline recon update # update through the original package manager
These examples use reserved domains; real lookups will not reproduce the synthetic illustration above. For multi-domain reviews, recon describes observed similarities and differences without inferring ownership or a corporate relationship. See the evidence-first review workflow and batch guide.
The PyPI package installs the CLI and MCP runtime. Connect the local server to Claude Desktop, Claude Code, Cursor, VS Code, Windsurf, or Kiro:
recon mcp install --client=claude-desktop
recon mcp doctor
Restart the client and begin with manual tool approvals. Ask for one domain's email and identity indicators, or a service comparison across supplied domains. Missing evidence means "not observed", not "not used"; collection failures remain explicit. Local execution is the default, and the project does not operate a hosted service.
See MCP setup and supported clients and skills, plugins, and their validation status.
recon includes a thin, keyboard-first desktop shell plugin for Omarchy located in integrations/omarchy/:
Enter to run bounded inspection, and press Ctrl+D to toggle baseline delta comparison.["recon", domain, "--json"]) without shell interpolation.See integrations/omarchy/README.md for installation and shortcuts.
| Need | Guide |
|---|---|
| Install, update, uninstall, or troubleshoot | Getting started |
| Find a command or flag | CLI reference |
| Build automation or hand off evidence | JSON schema, review bundles |
| Understand results and their limits | How it works, limitations, reporting observations |
| Linux and Omarchy environment setup | Linux / Omarchy guide |
| Check plans and shipped changes | Roadmap, changelog |
| Find architecture, security, research, or release procedures | Full documentation index |
Catalog corrections and documented vendor patterns are especially useful. Start with CONTRIBUTING.md for setup, verification, and contribution requirements; coding agents should also read AGENTS.md. For repeatable catalog work, start with the harness-neutral maintenance skill and offline example.
Use issues for bugs and feature requests. Keep public examples reserved and synthetic; never post evaluated company domains, tenant IDs, or per-domain results. See the private reporting paths and security policy. Intended for defensive use.