Spec Driven Development
MCP Server that facilitates spec-driven development workflows, not just Vibe Coding.
Description from the maker (original English)
MCP server that dispatches physical-world tasks to humans through a unified API
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.
RENTAHUMAN_API_KEY, MTURK_ACCESS_KEY_ID, MTURK_SECRET_ACCESS_KEY, MTURK_SANDBOX, MANUAL_WEBHOOK_URLValues 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": {
"human-dispatch": {
"command": "npx",
"args": [
"-y",
"human-dispatch-mcp"
],
"env": {
"RENTAHUMAN_API_KEY": "your-value",
"MTURK_ACCESS_KEY_ID": "your-value",
"MTURK_SECRET_ACCESS_KEY": "your-value",
"MTURK_SANDBOX": "your-value",
"MANUAL_WEBHOOK_URL": "your-value"
}
}
}
}Run this in your terminal
claude mcp add human-dispatch --env RENTAHUMAN_API_KEY=your-value --env MTURK_ACCESS_KEY_ID=your-value --env MTURK_SECRET_ACCESS_KEY=your-value --env MTURK_SANDBOX=your-value --env MANUAL_WEBHOOK_URL=your-value -- npx -y human-dispatch-mcpFill in the empty values before running it.
Paste into .cursor/mcp.json in your project, or ~/.cursor/mcp.json
{
"mcpServers": {
"human-dispatch": {
"command": "npx",
"args": [
"-y",
"human-dispatch-mcp"
],
"env": {
"RENTAHUMAN_API_KEY": "your-value",
"MTURK_ACCESS_KEY_ID": "your-value",
"MTURK_SECRET_ACCESS_KEY": "your-value",
"MTURK_SANDBOX": "your-value",
"MANUAL_WEBHOOK_URL": "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": {
"human-dispatch": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"human-dispatch-mcp"
],
"env": {
"RENTAHUMAN_API_KEY": "your-value",
"MTURK_ACCESS_KEY_ID": "your-value",
"MTURK_SECRET_ACCESS_KEY": "your-value",
"MTURK_SANDBOX": "your-value",
"MANUAL_WEBHOOK_URL": "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.
MTURK_SANDBOX envMANUAL_WEBHOOK_URL 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 zyntarasystems, 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: RENTAHUMAN_API_KEY, MTURK_ACCESS_KEY_ID, MTURK_SECRET_ACCESS_KEY
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 (0.2.2) reached the registry 7 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, Systemdox
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.
Your architecture in your agents' context: checks, specs, ADRs and docs over MCP, at write time.
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.
🌐 [humandispatch.ai](https://humandispatch.ai) — Homepage & provider docs
A universal dispatch layer for AI-agent-to-human task routing — Any business (law firms, VA services, freelancers, agencies) can plug in via webhooks and start receiving AI-dispatched tasks in minutes.
Routes tasks to registered webhook providers with smart matching, fallback chains, and proof-of-completion tracking. Any service provider registers a webhook, and the router matches tasks to providers based on capabilities, region, and budget.
# Clone and install
git clone https://github.com/zyntarasystems/human-dispatch-mcp.git cd human-dispatch-mcp npm install
cp .env.example .env
npm run build node dist/index.js
The easiest way to verify the server is working:
npx @modelcontextprotocol/inspector node dist/index.js
Open http://localhost:5173, enter the proxy session token shown in your terminal, and click Connect.
human_list_backends to see webhook_provider and manualhuman_register_provider:{
"name": "Test Provider", "webhook_url": "https://webhook.site/your-uuid", "webhook_secret": "a-secret-that-is-at-least-32-chars-long!", "categories": ["digital_micro"], "task_types": ["digital"], "regions": ["*"], "min_budget_usd": 0, "max_budget_usd": 500, "max_concurrent_tasks": 10 }
human_dispatch_task with Raw JSON input mode:{
"description": "Test task — verify the MCP server is routing correctly", "category": "digital_micro", "task_type": "digital", "budget": { "max_usd": 5, "currency": "USD" }, "deadline": { "complete_by": "2026-04-10T18:00:00Z", "urgency": "low" }, "proof_required": ["text_report"], "quality_sla": "low", "callback_url": null }
The task should route to your registered provider. If no providers match, it falls through to the manual backend.
{
"mcpServers": { "human-dispatch": { "command": "npx", "args": ["human-dispatch-mcp"] } } }
Note: HTTP transport binds to
127.0.0.1only. For remote access, place a TLS-terminating reverse proxy (e.g. nginx, Caddy) in front of the server. Never expose the port directly.
Required: HTTP transport refuses to start without
MCP_AUTH_TOKENset. AllPOST /mcprequests must includeAuthorization: Bearer. The/callbacks/task/:taskIdendpoint uses HMAC-signature auth instead — providers do not see the bearer token.
{
"mcpServers": { "human-dispatch": { "command": "npx", "args": ["human-dispatch-mcp"], "env": { "TRANSPORT": "http", "PORT": "3000", "MCP_AUTH_TOKEN": "a-long-random-string-32-chars-or-more" } } } }
| Tool | Description |
|---|---|
human_dispatch_task | Submit a task to be completed by a human worker via the best matching provider |
human_get_task_status | Poll the current status, worker info, and proof submissions for a task |
human_cancel_task | Cancel a pending or in-progress task |
human_list_tasks | List tasks with filters (status, backend, category) and pagination |
human_list_backends | Show available backends, their configuration status, and capabilities |
human_register_provider | Register a webhook provider to receive dispatched tasks |
human_list_providers | List registered providers with stats and filters |
human_remove_provider | Deregister a webhook provider |
┌─────────────┐
│ AI Agent │ │ (Claude, etc)│ └──────┬───────┘ │ MCP Protocol (stdio or HTTP) ▼ ┌──────────────────────────────────────┐ │ human-dispatch-mcp Server │ │ │ │ ┌────────────┐ ┌────────────────┐ │ │ │ Task Store │ │ Provider │ │ │ │ (in-memory)│ │ Registry │ │ │ └────────────┘ └───────┬────────┘ │ │ │ │ │ ┌────────────┐ ┌───────▼────────┐ │ │ │ Router │──│ Webhook │ │ │ │ (scoring) │ │ Provider │ │ │ └──────┬─────┘ │ Adapter │ │ │ │ └───────┬────────┘ │ │ │ │ │ │ │ ┌───────────▼─────────┐ │ │ │ │ Provider A (law) │ │ │ │ │ Provider B (VA) │ │ │ │ │ Provider C (photos) │ │ │ │ └─────────────────────┘ │ │ ▼ │ │ ┌────────────┐ │ │ │ Manual │ (always-on fallback) │ │ │ Adapter │ │ │ └────────────┘ │ └──────────────────────────────────────┘
Any business can register as a provider to receive AI-dispatched tasks. Here's how:
Your endpoint receives POST requests with these headers:
| Header | Description |
|---|---|
x-dispatch-signature | sha256= — HMAC-SHA256 of the request body using your shared secret |
X-Dispatch-Event | Event type: task.new, task.cancel, or provider.verify |
X-Dispatch-TaskId | UUID of the task |
task.new eventsRequest body:
{
"payload_version": 1, "event": "task.new", "task_id": "uuid", "description": "What needs to be done", "category": "photo_video", "task_type": "physical", "location": { "address": "123 Main St", "region": "US" }, "budget": { "max_usd": 25, "currency": "USD" }, "deadline": { "complete_by": "2026-04-10T18:00:00Z", "urgency": "medium" }, "proof_required": ["photo", "gps_checkin"], "quality_sla": "medium" }
payload_version is the request-shape version; pin your parser to a known version and reject unknown ones. Today only 1 is sent.
Respond with:
{ "accepted": true, "external_id": "your-internal-id" }
Or reject:
{ "accepted": false, "reason": "Outside service area" }
provider.verify eventsWhen a provider is registered, the server immediately POSTs a provider.verify event to confirm the endpoint is reachable and willing. A 200 alone is not enough — your endpoint must return { "verified": true } in the JSON body. Anything else (missing field, false, non-JSON) marks verification as unreachable. This makes registration require explicit consent from your endpoint, not just URL reachability.
POST to http:// /callbacks/task/ with headers:
x-provider-id: Your provider UUIDx-dispatch-signature: sha256= of the body{
"status": "completed", "proof": [ { "type": "photo", "url": "https://...", "submitted_at": "2026-04-10T12:00:00Z" } ], "actual_cost_usd": 20, "notes": "Task completed successfully" }
Always verify incoming webhooks using your shared secret:
const crypto = require('crypto');
const expected = 'sha256=' + crypto.createHmac('sha256', secret).update(rawBody).digest('hex'); const valid = crypto.timingSafeEqual(Buffer.from(expected), Buffer.from(signatureHeader));
HMAC canonicalization contract (load-bearing): the signature is computed over the exact bytes the request was POSTed with, not over a re-serialized JSON object. When you send a callback, sign the byte string you put on the wire — do not parse the body, re-stringify it, and sign that, because key ordering or whitespace may differ. Use JSON.stringify(payload) once, capture the resulting string, sign that string, send that string. The server applies the same rule on the receiving side: it captures the raw request body buffer before any JSON parser touches it.
The router automatically picks the best backend based on:
preferred_backends and fallback_chain are honored firstmanual backend is always available as the ultimate fallbackimport asyncio
from langchain_mcp_adapters.client import MultiServerMCPClient
async def dispatch_photo_task(): async with MultiServerMCPClient({ "human": { "command": "node", "args": ["path/to/human-dispatch-mcp/dist/index.js"], "transport": "stdio", } }) as client: tools = client.get_tools()
await client.call_tool("human_register_provider", { "name": "Photo Service Co", "webhook_url": "https://photos.example.com/webhook", "webhook_secret": "your-secret-that-is-at-least-32-characters", "categories": ["photo_video"], "task_types": ["physical"], "regions": ["US"], "min_budget_usd": 5, "max_budget_usd": 100, "max_concurrent_tasks": 20 })
result = await client.call_tool("human_dispatch_task", { "description": "Take a photo of the menu board at Starbucks on 5th Ave, NYC", "category": "photo_video", "task_type": "physical", "location": { "address": "5th Ave & 42nd St, New York, NY", "region": "US" }, "budget": {"max_usd": 15, "currency": "USD"}, "deadline": { "complete_by": "2026-01-15T18:00:00Z", "urgency": "medium" }, "proof_required": ["photo", "gps_checkin"], "quality_sla": "medium" }) print(result)
asyncio.run(dispatch_photo_task())
| Variable | Default | Description |
|---|---|---|
TRANSPORT | stdio | Transport mode: stdio or http |
PORT | 3000 | HTTP port (when TRANSPORT=http) |
MCP_AUTH_TOKEN | — | Bearer token required on every POST /mcp request when TRANSPORT=http. The HTTP transport refuses to start if unset. |
MANUAL_WEBHOOK_URL | — | Webhook URL for manual task notifications |
PROVIDERS_CONFIG | — | JSON array of provider objects to pre-seed on startup |
This server processes outbound HTTP requests on behalf of its callers and is intended to run inside trusted infrastructure. The relevant guarantees:
MCP_AUTH_TOKEN is mandatory; the server refuses to start without it. Bearer comparison is constant-time (timingSafeEqual).POST /mcp. The transport rejects requests whose Host header points at anything other than the configured loopback.MANUAL_WEBHOOK_URL, callback_url, proof URLs) goes through a structured validator: HTTPS only, no loopback, no RFC1918 / link-local / unique-local hosts, with a DNS resolution check at fetch time to defeat last-second rebinds. There is no opt-out — use a public tunnel (ngrok, cloudflared) for local testing.x-dispatch-signature over the raw request bytes before parsing JSON. A per-provider token bucket limits callback flood (30 burst, 5/sec sustained).completed, failed, or `caOnly the beginning is shown; read the rest in the repo