Consentgate MCP server
io.github.jessepetersondev/consentgate-mcp·v0.1.1Gate AI agent actions behind a consent policy with human approval via Telegram. Fail-closed.
0 stars34 downloads/wk
Reviews
Write oneNobody has reviewed Consentgate yet.
If you have run it, two minutes of your experience saves the next person an afternoon.
Consentgate tools (2)
write = sends, deletes, buys or postsRead from the package source without running it. The installed server may list more.
check_actionCheck whether an action is permitted by the ConsentGate owner's consent policy BEFORE you perform it.
request_approvalRequest a human's explicit approval for an action and BLOCK until they decide or the timeout elapses.
Public scan report
scanner v0.1.9 · 2026-09-27 · same rubric, same numbers if you re-run it
- Code scan2 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 qualitystatic API keys via environment variables6/15
- Maintenancelast push 115 days ago8/15
- Maintainer identityregistry namespace matches repository owner; GitHub account older than a year8/10
How Consentgate compares
Against every graded AI and agents MCP server, from our own scans and uptime checks. Updated after each scan run.
- Safety score
- 72/100
- higher than 40% of 4,460 AI and agents servers
- Tools
- 2
- 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
- 34
- more than 23% of 1,538 AI and agents servers with a package
What its tools let an agent do: 2 read
Install Consentgate in Claude Code, Cursor or VS Code
Runs npx -y consentgate-mcp on your machine. Read the scan report first; the gateway never runs local packages.
claude mcp add consentgate-mcp -- npx -y consentgate-mcp
What the publisher says
From the Consentgate repository's README, as published. We do not edit it. Read it on GitHub
consentgate-mcp
A Model Context Protocol server that lets any MCP-capable agent (Claude Desktop, Claude Code, Cursor, custom agents, …) gate its own actions behind a human's consent policy via ConsentGate.
The agent asks before it acts; you stay in control. High-stakes actions can block on an explicit Approve / Deny tap delivered to your Telegram.
Tools
Both fail closed: anything other than an explicit allow means do not proceed.
Prerequisites
account (Dashboard → Telegram → Connect). check_action works on any plan.
- A ConsentGate account and an API key → https://consentgate.fyi/dashboard/keys (cg_…).
- For requestapproval (interactive approvals): the Pro plan and** a linked Telegram
Configuration
Environment variables:
Claude Desktop
Add to claudedesktopconfig.json (Settings → Developer → Edit Config):
{
"mcpServers": {
"consentgate": {
"command": "npx",
"args": ["-y", "consentgate-mcp"],
"env": { "CONSENTGATE_API_KEY": "cg_your_key_here" }
}
}
}Claude Code
claude mcp add consentgate --env CONSENTGATE_API_KEY=cg_your_key_here -- npx -y consentgate-mcpGeneric MCP client
Run npx -y consentgate-mcp (stdio transport) with CONSENTGATEAPIKEY in the environment.
Run from source
Until the package is published to npm, point your client at the built file
(node /abs/path/to/mcp/dist/index.js) instead of npx consentgate-mcp.
cd mcp
npm install # also builds via the `prepare` script
npm run build # -> dist/index.js
CONSENTGATE_API_KEY=cg_… npm run smoke # lists tools + a live check_actionHow an agent should use it
A good agent policy:
Before performing any action that sends messages, spends money, deletes data, posts
publicly, or changes external state, call check_action. If the result is allow,
proceed. If deny, stop. If ask (or the action is high-stakes), call request_approval
and proceed only on an explicit allow.
Example (request_approval):
{
"action": "transfer_funds",
"category": "spending",
"metadata": { "amount": "$500", "to": "Acme Corp" },
"wait_seconds": 90
}
// -> blocks; you tap Approve in Telegram -> { "decision": "allow", "resolved_by": "human" }License
MIT
Nothing above is checked by us. What we check is on the safety report.
Consentgate: common questions
- Is Consentgate MCP server safe?
- Mostly: it is graded B (72/100). Read the Consentgate safety report
- How do I install Consentgate?
- It runs on your machine. Copy the Claude Code, Cursor, VS Code or Claude Desktop config from the install section.
- Does Consentgate need an API key?
- Yes. The registry entry asks for
CONSENTGATE_API_KEY. - Is Consentgate maintained?
- The last commit was 153 days ago (2026-06-04). The latest release is v0.1.1.
- What can I use instead of Consentgate?
- Servers from other publishers that do the same job: Emilia Protocol MCP server, CHAP Coordinator MCP server and HOL Guard MCP server.
- How does Consentgate compare with other AI and agents MCP servers?
- safety score 72/100 (higher than 40% of 4,460 AI and agents servers); tools 2 (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.
Alternatives to Consentgate
Same job from other publishers: the closest match first, then the best rated.
- Emilia ProtocolExact-action approval for consequential agent actions: request, track, and verify signed receipts.not reviewedEstablishedB
- CHAP CoordinatorAuditable records of human decisions over AI agent work. Approvals, edits, overrides, escalations.not reviewedEstablishedA
- HOL GuardLocal-first AI agent security evidence and approval workflows through HOL Guard's stdio MCP server.not reviewedEstablishedA
- not reviewedEstablishedA
- Agent-Native ChatMinimal chat-first app with durable threads, actions, and the app-agent loopnot reviewedEstablishedA