Spec Driven Development
by formulahendry
MCP Server that facilitates spec-driven development workflows, not just Vibe Coding.
Runs on your computer★ 440MITUpdated 14 months ago
Install
Hunch
Overview
Description from the maker (original English)
Shared records for AI agents: engineering decisions, bug history, rules, and work state through MCP.
PopNx MCP’s three pillars
These three are never merged into one score: opinions, measurements and popularity are different things.
- User voiceiNo reviews yetReviews open together with accounts in a later step
- Our basic checksi1 of 1 passedChecked from public information; code not scanned yet
- UsageiNot measured yet★ –
What you can do with it
We have not written a plain-language summary for this one yet. Below are the facts we read from the registry.
- Connection: Runs on your computer
- Transport: stdio
- Category: Other
Install
Pick the AI app you use, then copy the settings.
Before you install
- Basic checks: 1 of 1 passed
- Runs on your computer with your user’s permissions (files, network, apps).
- The registry lists no key to fill in.
You need
- npmNode.js installed (for the npx command)
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": {
"hunch": {
"command": "npx",
"args": [
"-y",
"@davesheffer/hunch",
"mcp"
]
}
}
}Run this in your terminal
claude mcp add hunch -- npx -y @davesheffer/hunch mcpOr copy the settings yourself
Paste into .cursor/mcp.json in your project, or ~/.cursor/mcp.json
{
"mcpServers": {
"hunch": {
"command": "npx",
"args": [
"-y",
"@davesheffer/hunch",
"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.
Or copy the settings yourself
Paste into .vscode/mcp.json in your project
{
"servers": {
"hunch": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@davesheffer/hunch",
"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.
What it can do
Runs on your computer; the tool list appears in your AI app after you install it.
Basic checksi
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
- ✓ Pass
Maker matches the repo
The registry name was verified with the GitHub account davesheffer, which owns the repo
- … Not checked yet
Still maintained
We have not read this repo from GitHub yet
- … Not checked yet
Has a licence
We have not read this repo from GitHub yet
- – Not applicable
Endpoint responds
This one runs on your computer; there is no internet endpoint
- – Not applicable
Sign-in with OAuth
Runs on your computer and uses local settings instead
- … Not checked yet
No hidden instructions in tool descriptions
Runs on your computer; we can only read tool lists from internet endpoints
Compared with others in Otheri
- More stars than 0% of the other 32568 servers in this category
- Published to the registry more recently than 44% of the other 32568 servers in this category
- Basic checks equal to or better than 100% of the other 32568 servers in this category
Compared with every active server in this category in the registry. Stars count only when the publisher owns the repo.
Common questions
Is Hunch safe?
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.
What keys or codes does it need?
The registry does not list a required key, though some servers ask you to sign in on first use.
Does it run on my computer or in the cloud?
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).
Is it still maintained?
The GitHub repo last changed –, and the latest version (1.38.1) reached the registry 2 months ago.
Which apps can use it?
Apps that support MCP, such as Claude Desktop, Claude Code, Cursor and VS Code. You also need Node.js on your computer.
What can I use instead?
In the same category: Spec Driven Development, Remote Desktop Commander, FlyDocs
Alternatives
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
Remote Desktop Commander
by desktop-commander
Remote Desktop Commander: use files, terminal and processes on your own computers from any AI app.
Runs in the cloud★ 211Updated yesterday
Install
FlyDocs
by flydocs.ai
Spec-driven development workflow: your agent works issues, sessions and the status lifecycle.
Runs on your computerUpdated today
Install
README from the maker
Open the README
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.
Hunch
A shared record for AI agents: what was decided, what happened, and what still needs doing.
▶ [Watch Hunch Memory in 2 minutes](https://www.youtube.com/watch?v=m2PM6pV7D9Y), then the 7-episode series on setup, hooks, memory capture, delivery, rules, drift and teams.
A new agent session should not mean explaining the project all over again. A second agent should be able to check a recorded decision, see the evidence behind completed work, and find an outstanding commitment.
Hunch keeps that record in Git and makes the relevant parts available to your agents. It started with engineering memory: why code exists, which approach failed before, and which rules a change must preserve. It also ships a state server for sharing decisions, action records, and commitments across authorized organization, team, user, and repository scopes.
The goal is simple: agents working from the same maintained record, with sources they can inspect. Hunch supplies memory and checks; the assistant still does the work.
Start with your coding assistant
Requires Node 22.13+ and a Git repository.
npm i -g @davesheffer/hunchcd your-repo hunch init hunch backfill --since 90d # optional: draft memory from recent history
If the shell reports that hunch is not found, initialize without a global binary from the repository directory: npx -y @davesheffer/hunch@latest init.
Reload your assistant, then ask:
Why is this built this way, and what should I preserve when changing it?
hunch init indexes the code, configures supported assistant integrations, and adds memory instructions while preserving existing settings. For Codex hooks, review and trust the commands in /hooks, then start a new session. Memory is advisory by default. Blocking requires an explicitly trusted rule and strict enforcement.
Hunch works with Claude Code, Codex, Cursor, VS Code/Copilot, Windsurf, Antigravity, and other MCP clients. Automatic context and hook coverage vary by assistant; a connected MCP server alone does not prove they are running. Check your integration.
What you get today
| Need | How Hunch helps |
|---|---|
| Stop explaining old decisions | Saves decisions, rejected alternatives, bug history, corrections, and open findings with their sources. |
| Understand a change before making it | Connects memory to code symbols and dependencies; shows affected code and recorded architectural intent. |
| Keep agents informed across sessions | Delivers a focused brief for a task through MCP and supported lifecycle hooks. |
| Check the rules your team chose | Evaluates supported constraints and code relationships without a model in the blocking path. |
| See what happened during a task | Separates delivered memory, the agent's reported use, rule results, and observed command results in a contribution report. |
| Share project memory with teammates | Keeps repository memory in Git, with an optional dedicated private memory repository. |
| Share work state across agents | Serves authorized records through HTTP, MCP, the state CLI, and typed TypeScript and Python clients. |
| Inspect what the agents know | A read-only browser view shows current records, commitments, completed work and writer-supplied citations. |
| Keep access and conventions explicit | Optional per-record audiences, key-bound credentials and sourced conventions use the same state contract. |
For example, a team fixes a logout bug by keeping sessions on the server. Months later, an agent proposes removing that code. Hunch can surface the original reason and rejected alternative before the edit. A supported, trusted rule can flag the conflict; strict mode can block it. Recording the lesson and configuring the integration are what make this possible.
Day-to-day
| Command | Use it for |
|---|---|
hunch context " " --profile builder | Get a focused brief before starting |
hunch why | Understand decisions and past bugs behind code |
hunch structure [target] | Inspect indexed files and symbols |
hunch findings [scope] | See known gaps that still need work |
hunch impact origin/main | See what a branch could affect |
hunch check --working | Check current changes against recorded rules |
hunch conform | Check supported architectural relationships |
hunch now | Read recent decisions and the recorded roadmap |
hunch doctor | Diagnose setup and storage problems |
For enforcement after reviewing and trusting the relevant rules:
hunch firmness stricthunch check --staged --strict
Generated notes, observed habits, and imported documents do not silently gain blocking authority.
Update without losing your settings
From each repository that uses Hunch:
hunch updateIf the shell reports that hunch is not found, run npx -y @davesheffer/hunch@latest update from the repository instead.
Or ask your agent to “update Hunch.” The command installs the latest release, aligns configured integration pins, repairs known legacy launch commands, and refreshes Hunch instructions. It preserves unrelated settings and intentionally disabled hooks.
Installed interactive CLI commands can also show a cached update notice. At most once every 24 hours, a detached worker asks npm for the package's public latest version; hooks, MCP, CI, servers, the updater, non-interactive commands, and source checkouts skip that request. Set HUNCH_NO_UPDATE_CHECK=1 or NO_UPDATE_NOTIFIER=1 to disable it.
- A standalone npm project keeps Hunch in its existing dependency section at an exact version. Without a repository dependency, the global CLI is updated. Add
--globalto update both. - For other package managers or workspaces, update the dependency with that package manager, then run
hunch integrations repair-pins. - Restart or reconnect active assistants. In Codex, open
/hooksto review and trust changed commands, then start a new session. A changed version pin changes the command and requires renewed trust.
Verify the setup:
hunch integrations checkhunch integrations check --harness codex --probe --require mcp hunch integrations check --harness codex --require context
The first command checks configuration. The probe starts a fresh MCP process and reads memory. The context check requires observed hook delivery on the expected version, so run it after the new assistant session begins. --require fails when the named capability is not verified; none of these checks proves that a model followed the advice.
Remove Hunch from a repository
hunch uninstall --dry-run # show what would changehunch uninstall # remove what Hunch installed; keep .hunch/ (your memory) hunch uninstall --purge # also delete .hunch/, the derived cache and Hunch's .gitignore blocks
It removes the instruction blocks, MCP entries, agent and git hooks, merge driver, slash commands and CI workflow that Hunch installed, and leaves your own content in those files alone. If a file it needs to edit can't be parsed, it changes nothing and says which file. It writes .hunch-removed: while that file exists, no Hunch command sets Hunch up here again. Commit it so every clone stays opted out; to reinstall, delete it and run hunch init. Close running hunch mcp / hunch serve processes first, so they can't recreate files.
See what Hunch contributed
Task reports answer: what memory reached this task, what did the agent say it used, and what checks actually ran?
The normal agent instructions request a completion card with a link to a local evidence report. You can also inspect reports directly:
hunch task listhunch report --html
A delivered lesson, an agent's claim, and a passing test are different evidence. Hunch keeps them separate. Automatic presentation depends on the host following the task lifecycle; missing evidence stays unverified.
Share one living repository memory with your team
One maintainer connects a dedicated private Git repository:
hunch shared --repo git@github.com:acme/project-hunch-memory.gitgit add .gitignore .hunch/team.json git commit -m "chore: connect shared Hunch memory" git push
Teammates install Hunch, pull the code, and run hunch shared --trust once per machine: it shows the store URL from .hunch/team.json and connects only after that explicit consent. Then run hunch init. Until a machine trusts the store, Hunch refuses to clone it or route memory there. Normal Git access controls the shared repository. Credentials, local clone paths, and private overlays stay out of the committed pointer. Use hunch shared --sync to retry synchronization; add --no-auto-commit when captures should wait for explicit sync.
This shares a project's engineering memory. The state server below adds authenticated access across multiple scopes.
Deterministic organizational state
A coding agent needs to know why a module exists. An operations agent may need to know whether a customer action was completed or who owes the next follow-up. Both need a maintained record they can check.
Hunch ships hunch serve: a self-hosted HTTP service for organization, team, user, and repository records. A configured identity determines which scopes an agent may access. Optional record audiences further restrict access; optional key-bound credentials require proof from the configured private key on each request.
Open /operator on your server to inspect current records, completed work and commitments in a read-only browser view. Writer-supplied citations can point to an exact summary field or text passage and its recorded sources. They show traceability; they do not prove that a source supports a claim.
Agents can use the same contract through MCP, hunch state read|write|records|subscribe, the @davesheffer/hunch/state TypeScript client, or the Python client. The Python package is built and tested from this repository; it is not yet published to PyPI. Scoped conventions let a person record sourced user, team or organization preferences. Those preferences remain advisory and do not silently become blocking rules.
Records can describe decisions, action outcomes, commitments, entities, relationships, and summaries that name their dependencies. Actions retain their status, including unknown or unverified outcomes. Repeated writes have stable identities, conflicting current decisions are refused, and confirmed human records receive protections against agent overwrites. These are defined checks on structured records; Hunch cannot establish every fact in the outside world on its own.
This is what deterministic state means here: explicit rules govern the stored record, rather than having each agent reconstruct it from scratch. Git holds the durable data; SQLite is a rebuildable index. The server binds to loopback and requires deployment and agent integration by its operator. Hunch does not provide a managed CRM or email connector service.
See the full documentation.
The vision, and what is still being tested
The vision is continuity across people, tools, and agents: an operations agent records a customer
Only the beginning is shown; read the rest in the repo