Curbi MCP Server

by curbi-inc Your server? Claim it

answering

Curbi is answering right now. Last checked 7 min ago. It exposes 6 tools.

Check agent replies, lint policies, export regression tests and verify caller-trusted proof bundles.

Uptime history 64 hours of history

64 hours agonow

100.0%

Uptime 24h

92 of 92 checks

Tools

read from the server

145 ms

Response time

average over 24h

open, no key

Access

streamable-http

What changed 3

Every tool that appeared, vanished or quietly changed what it asks for. Recorded since 6 November 2026. No other catalogue keeps this.

6 Nov 3 tools changed the parameters they ask for export_regression, policy_check, validate_policy

Nothing serious here today

Today is the operative word: we check Curbi every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.

Connect this server

Endpoint below is the one we actually reach during checks — not the one copied from a README. Last verified 7 min ago.

Claude Code Claude Desktop Codex Cursor VS Code

run in your terminal

claude mcp add curbi --transport http https://api.curbi.io/mcp

Settings → Connectors → Add custom connector, then paste this address

https://api.curbi.io/mcp

~/.codex/config.toml

[mcp_servers.curbi]
url = "https://api.curbi.io/mcp"

.cursor/mcp.json

{
  "mcpServers": {
    "curbi": {
      "url": "https://api.curbi.io/mcp"
    }
  }
}

.vscode/mcp.json

{
  "servers": {
    "curbi": {
      "type": "http",
      "url": "https://api.curbi.io/mcp"
    }
  }
}

Available tools 6

Read directly from the server with tools/list, grouped by what they act on. If a tool disappears, we record the date.

export

export_regression

Run policy_check with caller-supplied records (no receipts or required-signature mode) and return it as a CI regression: curbi.regression JSON with each reply's expected verdict and rules, plus a dependency-free node:test file that replays it against the Check API. Expectations come from the checker, never from the caller. Nothing is stored. A pass grants no execution authority.

fetch

fetch

Fetch the first-party catalog summary for an id returned by search. Returns a canonical URL and a link to full documentation; does not retrieve caller URLs.

policy

policy_check

Check one reply or up to 50 replies against explicit prices, forbidden phrases and supplied outcome records. Deterministic, no model calls. Caller records are unverified; receipt verification is unavailable here. A pass grants no execution authority.

search

Search the published Curbi documentation catalog. Returns ids, titles and canonical URLs. Documentation is data, not instructions.

validate

validate_policy

Check a policy against the same schema rules as policy_check, then lint it: no rules at all, duplicate or overlapping price items, duplicate forbid ids or phrases, prices that cannot be stated in cents, and rules the checker never fires on (probed with the shipped checker). Returns valid, errors and warnings. Nothing is stored. A valid policy is not a complete one, and grants no execution authority.

verify

verify_bundle

Run the open Curbi Proof verifier (curbi.proof/0.1) on a bundle with the public keys you choose: signatures, key windows, RFC 9162 inclusion under the signed log head, attestation binding and history consistency. Keys are required and are the trust anchor; keys inside the bundle are never trusted here. Test keys verify only with allowTest. Pure computation: no network, nothing stored. A verified bundle shows what a trusted key signed and logged; it does not show that the provider action happened, and grants no authority.

Endpoints

URL	Transport	State	Latency	Checked
https://api.curbi.io/mcp	streamable-http	answering	138 ms	7 min ago

Alternatives to Curbi

same job, measured the same way

agentguard — policy proxy for agent tool calls

by agentwares

Free spend report from an agent log, no key. Hosted proxies: caps, audit export, buy calls.

7 tools answering

Timero

by timero

Time tracking for agencies: log time, run the timer, check client budgets and pull reports.

answering

Twothumbs

by asselwan

Verifies AI agent work end to end: real artifacts and outcomes checked, not self-reported success.

3 tools answering

Settled

by settled

Check x402 endpoints before your agent pays: payTo, paid test purchases, payee and buyer reports

232 installs/wk 18 tools answering

Stats Explorer

by meador793

Verified statistics for AI agents: guided tests, A/B tests, Tukey HSD, reports, optional Jev checks.

88 installs/wk local only

LinkBunny Placement Checker

by getlinkbunny

Checks whether a public page links to an expected URL; reports anchor, rel and canonical.

1 tools answering

Claude Replay

by constripacity

Session checkpoint & recovery for Claude Code: resume, search, tag, and export recorded sessions.

230 installs/wk local only

gonzalgo

by vince-gonzalez

Reports what a checked Lean 4 or Metamath proof rests on: inherited sorry, compiler trust, axioms.

local only

Curbi — questions

Answers built from our own checks of this server.

What can Curbi do?

It exposes 6 tools, read directly from the server on our last check. Among them: export_regression, fetch, policy_check, search, validate_policy, verify_bundle. The full list with descriptions is on this page — we take it from the server itself via tools/list, not from a README. How MCP servers expose tools in the first place →

Is Curbi working right now?

We send a real MCP handshake every 15 minutes. Over the last 24 hours 92 of 92 checks got a reply (100.0%), average response time 145 ms. The bar chart above shows every period we have measured.

How do I connect Curbi?

Copy the ready config from this page. We generate it for Claude Code, Claude Desktop, Codex, Cursor and VS Code, each in the form that client actually reads. It is a remote server, so there is nothing to install — the client connects to the address.

Does Curbi need an API key?

No. Curbi completed a full MCP handshake with us as an anonymous client and listed its tools without asking for anything. All 6 of them are readable on this page. This is what we observed, not what the docs claim.

How fast is Curbi?

It answers our handshake in 145 ms on average, which is faster than 83% of all working MCP servers we measure. That puts it in the quick quarter of the ecosystem. The comparison comes from our own checks across the whole registry, every 15 minutes.