Concierge Agent Protocol MCP server
io.github.conciergeprotocol/mcp·v0.1.6Ask a company through its Concierge Agent Protocol front door.
0 stars835 downloads/wk
Reviews
Write oneNobody has reviewed Concierge Agent Protocol yet.
If you have run it, two minutes of your experience saves the next person an afternoon.
Concierge Agent Protocol tools (3)
write = sends, deletes, buys or postsRead from the package source without running it. The installed server may list more.
cap_askRead a CAP message that was still being answered. Do not guess a reply while the status is working.
cap_checkRead a CAP message that was still being answered. Do not guess a reply while the status is working.
cap_discoverCheck whether a website has a CAP front door, and whether visitors can log in.
Public scan report
scanner v0.1.10 · 2026-10-24 · same rubric, same numbers if you re-run it
- Code scan3 source files scanned25/25
- –Live reliabilityno gateway calls yet and no remote to proben/a
- –Tool poisoningtools not inspected (local package is not executed); not countedn/a
- Auth qualitylocal package, no credentials required12/15
- Maintenancelast push 0 days ago15/15
- Maintainer identityregistry namespace matches repository owner7/10
How Concierge Agent Protocol compares
Against every graded AI and agents MCP server, from our own scans and uptime checks. Updated after each scan run.
- Safety score
- 91/100
- higher than 88% of 4,460 AI and agents servers
- Tools
- 3
- the typical AI and agents server has 6
- Tools that change things
- 0%
- typical: 0%. Fewer write tools means less an agent can break
- Downloads a week
- 835
- more than 91% of 1,538 AI and agents servers with a package
What its tools let an agent do: 3 read
Install Concierge Agent Protocol in Claude Code, Cursor or VS Code
Runs npx -y @conciergeprotocol/mcp on your machine. Read the scan report first; the gateway never runs local packages.
claude mcp add mcp -- npx -y @conciergeprotocol/mcp
What the publisher says
From the Concierge Agent Protocol repository's README, as published. We do not edit it. Read it on GitHub
Concierge Agent Protocol for JavaScript
Two packages for calling a CAP front door. @conciergeprotocol/client is the library. @conciergeprotocol/mcp is that library behind three tools, so Claude, Cursor, and other MCP hosts can ask a company.
The protocol is at conciergeprotocol.org. These packages only call a front door. A company publishes agent.txt. It does not publish an MCP server.
Install
- @conciergeprotocol/client
- @conciergeprotocol/mcp
npm install @conciergeprotocol/clientThe MCP server is a command. Install it, or run it with npx as in the block below.
npm install @conciergeprotocol/mcpClient
import { createClient } from '@conciergeprotocol/client'
const cap = createClient({ from: 'agent:my-assistant' })
const answer = await cap.ask('example.com', 'Do you have a free plan?')
console.log(answer.reply)A follow-up sends only the new question:
const thread = cap.thread('example.com')
await thread.ask('What do you sell?')
const price = await thread.ask('How much is the cheapest paid plan?')discover returns null when a site has no front door. ask throws NoDoorError for the same case, which is the signal to browse the site instead.
ask waits up to two minutes. If the company is still answering, the message comes back with status: 'working' and no reply. get reads it again.
Account questions use login. The client opens the company's page, and finishLogin stores the token for the next ask. The token stays in the token store you pass to createClient.
MCP
Cursor, Claude Desktop, and VS Code use the same block. In VS Code it goes in .vscode/mcp.json. In Cursor and Claude Desktop it goes in the MCP settings file.
{
"mcpServers": {
"cap": {
"command": "npx",
"args": ["-y", "@conciergeprotocol/mcp"],
"env": { "CAP_FROM": "agent:my-assistant" }
}
}
}CAPFROM defaults to agent:cap-mcp. The tools are capdiscover, capask, and capcheck. The server is listed in the MCP registry as io.github.conciergeprotocol/mcp. capask waits 60 seconds. If the company is still answering, it returns the message id and the model calls capcheck instead of guessing.
Release
Add a changeset, then merge to main:
bun run changesetPackage Checks runs on every push. When it passes on main, the publish workflow opens a version pull request, or publishes both packages and tags the release. The two packages stay on one version. When the npm publish succeeds, the same workflow lists the server in the MCP registry. The repository needs an NPM_TOKEN secret.
License
Apache 2.0
Nothing above is checked by us. What we check is on the safety report.
Concierge Agent Protocol: common questions
- Is Concierge Agent Protocol MCP server safe?
- Yes, by our scan: it is graded A (91/100). Read the Concierge Agent Protocol safety report
- How do I install Concierge Agent Protocol?
- It runs on your machine. Copy the Claude Code, Cursor, VS Code or Claude Desktop config from the install section.
- Does Concierge Agent Protocol need an API key?
- No secret keys are declared. It reads 1 setting from the environment.
- Is Concierge Agent Protocol maintained?
- The last commit was 12 days ago (2026-10-23). The latest release is v0.1.6.
- How does Concierge Agent Protocol compare with other AI and agents MCP servers?
- safety score 91/100 (higher than 88% of 4,460 AI and agents servers); tools 3 (the typical AI and agents server has 6); tools that change things 0% (typical: 0%. Fewer write tools means less an agent can break). Full comparison.