Spec Driven Development
MCP Server that facilitates spec-driven development workflows, not just Vibe Coding.
Description from the maker (original English)
Usage metering, spend cap (reserve before pay), lease lock, semaphore, heartbeat for agents. Free tr
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://gap-functions.bfurrow26.workers.dev/mcpRun this in your terminal
claude mcp add --transport http usage-metering https://gap-functions.bfurrow26.workers.dev/mcpPaste into .cursor/mcp.json in your project, or ~/.cursor/mcp.json
{
"mcpServers": {
"usage-metering": {
"url": "https://gap-functions.bfurrow26.workers.dev/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": {
"usage-metering": {
"type": "http",
"url": "https://gap-functions.bfurrow26.workers.dev/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://gap-functions.bfurrow26.workers.dev/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.
Tool names and descriptions exactly as the server reported them on Nov 6, 2026. The maker wrote them, not us; we show them as plain text.
mcp_usage_meteringUsage metering for MCP tools and AI agents: record a billable usage event per tool call (idempotent, idempotency_key dedupes retries) and get an invoice line preview. Per-call billing, usage-based pricing, metered billing for MCP servers. Every call requires one solved task: a ti
agent_spend_ledgerAgent spend cap / budget ledger: set a budget, reserve before pay (atomic, never overspends even with many agents in parallel), then settle or release. Idempotent, shared by namespace. Spending limit, budget guard, cost control for AI agents. Every call requires a tiny solved pac
agent_lease_lockDistributed lock / lease lock (mutex) for AI agents: acquire, renew, release a named lock with TTL and a monotonic fencing token so only one agent runs a job at a time. Idempotent, shared by namespace, no Redis needed. Every call requires a tiny solved packet (returned in the rep
agent_semaphoreCounting semaphore / concurrency limit for AI agents: at most N agents hold a slot at once (rate limit parallel workers), TTL permits with fencing tokens, auto-expire on crash. Idempotent, shared by namespace. Every call requires a tiny solved packet (returned in the reply, 2 s,
agent_heartbeat_registryHeartbeat registry / dead-man switch / liveness check for AI agents: agents beat with an interval and grace; list_stale shows which agents went silent or crashed. Idempotent, shared by namespace. Every call requires a tiny solved packet (returned in the reply, 2 s, one try); free
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 9, 2026
The registry name was verified with the GitHub account throttler300, which owns the repo
We have not read this repo from GitHub yet
We have not read this repo from GitHub yet
Responded in 75 ms (HTTP 200)
No sign-in needed
Read 5 tool descriptions and found no hidden instructions to the AI
Compared with every active server in this category in the registry. Stars count only when the publisher owns the repo.
It passed 3 of 3 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 (1.4.0) reached the registry 5 days 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, WCS Points
Servers in the same category from other makers, sorted by stars.
Reading a card:↓ Downloads per weeki★ 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.
West Coast Swing WSDC points registry: dancer points, divisions, level-ups, event results and rules.
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.
Free first call, one step, no key, no signup: curl -s https://gap-functions.bfurrow26.workers.dev/try returns a tiny packet, the solve rule, and a one-liner. POST the answers back to /try and you get the real tool result. ?tool=agent_lease_lock (or any tool below) for the others.
Search words: usage metering, metered billing, idempotent, reserve before pay, spend cap, budget, distributed lock / lease lock, fencing token, semaphore, concurrency limit, heartbeat, dead-man switch, free first call.
Hosted tool that records one billable usage event per MCP tool call, idempotently, and returns an invoice preview. Built for MCP server authors who want to charge per call without building metering.
https://gap-functions.bfurrow26.workers.dev/mcp (all URLs in config.json)GET /mcp/tools · Health: GET /healthschema/mcp_usage_metering.v1.0.0.json (strict input, required idempotency_key, versioned 1.0.0)tools/call returns isError: true with error_code: PAYMENT_REQUIRED. structuredContent.payment holds a one-click approve_and_pay_url for your human and a grant_token. Your agent asks you once, you click buy, then the agent retries the same call with header X-Grant-Token (or uses the /u/ /mcp URL form). Same token forever.idempotency_key are never billed twice.Required: tool_name, tool_version (semver), end_customer_ref, idempotency_key (8–128 chars). Optional: units, unit_label, unit_price_cents, metadata.
Terms of Service and Privacy Policy are DRAFT, pending counsel review, not yet in effect — see legal/.
MIT (this repository: docs and schema). Operated by Dirtsmith LLC.
The same MCP URL (https://gap-functions.bfurrow26.workers.dev/mcp) also serves:
set_budget, reserve, settle, release, status. Reserve is atomic: concurrent agents on one budget can never exceed the ceiling. Reservations expire after ttl_s (default 900 s). Amounts are integer micro-USD. $9.00 per 1,000 calls after 1,000 free calls a month.acquire, renew, release, status, with ttl_s and a monotonic fencing_token. $0.90 per 1,000 calls after 1,000 free calls a month.acquire (with max_slots, holder_id, ttl_s), release (by permit_id), status. At most N permits at once; each permit carries a monotonic fencing_token; full returns NO_SLOT_FREE with retry_after_s. $0.90 per 1,000 calls after 1,000 free calls a month.beat (with agent_id, interval_s, grace_s, optional note), status, list_stale (agents past interval + grace, up to 100). $0.90 per 1,000 calls after 1,000 free calls a month.State is shared by namespace (16-128 chars). Any agent that knows the namespace can read and change that state, so treat it like a password. We store only its hash. Buying works the same way as metering: no signup or key, one approve-and-pay link when the free calls run out.