MCP.Market

Logi Approval MCP server

by 1pass.dev·dev.1pass/logi-approval·v0.1.2
No reviews yet

logi Agent Approval Gate — human approval on the phone before high-risk agent actions.

B75/100grade B
Write a reviewInstall
What users say
No reviews yet
Be the first
Safety scan
B75/100

full report

Adoption
New

0 stars21 downloads/wk

Reviews

Write one

Nobody has reviewed Logi Approval yet.

If you have run it, two minutes of your experience saves the next person an afternoon.

Logi Approval tools (2)

write = sends, deletes, buys or posts

Read from the package source without running it. The installed server may list more.

  • logi__check_approval

    Use to poll a previously created approval by auth_req_id. Read-only. Returns current status and (when terminal) the decision metadata. Prefer logi__request_approval with wait_for_decision=true unless you specifically need non-blocking polling.

  • logi__request_approval

    Use BEFORE performing any high-risk action the user has flagged (budget changes, prod deploys, payments, mass communications). Sends a push to the user's phone with a Face ID + Number Matching prompt; blocks until they decide or timeout. ALWAYS check the returned status — 'approved' means proceed, anything else means ABORT and report. NEVER bypass.

Public scan report

scanner v0.1.9 · 2026-09-23 · same rubric, same numbers if you re-run it

no findings
  • Code scan7 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 47 days ago12/15
  • Maintainer identitynamespace and repository owner differ; website matches verified namespace6/10
Overall 75/100. Components that don't apply are left out of the denominator. Any critical finding is an F.RubricAppeal a findingJSON

How Logi Approval compares

Against every graded AI and agents MCP server, from our own scans and uptime checks. Updated after each scan run.

Safety score
75/100
higher than 45% 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
21
more than 7% of 1,538 AI and agents servers with a package

What its tools let an agent do: 2 read

Install Logi Approval in Claude Code, Cursor or VS Code

Runs npx -y @logi-auth/mcp-approval on your machine. Read the scan report first; the gateway never runs local packages.

claude mcp add logi-approval -- npx -y @logi-auth/mcp-approval
Add to Cursor

What the publisher says

From the Logi Approval repository's README, as published. We do not edit it. Read it on GitHub

logi (1pass) — Claude Code plugins

Agent plugins for logi / 1pass, the passkey-first sign-in service.

Install (Claude Code)

claude plugin marketplace add dcode-co/logi-plugins
claude plugin install logi-integrate@logi
claude plugin install logi-approval@logi   # optional

Then set the env vars each server needs:

start.1pass.dev (Settings → API Keys).

  • logi-integrate: LOGIAPIKEY — a Personal API Key from

(and LOGIAGENTPRIVATE_KEY for signed mode) — see the Agent Approval quickstart.

  • logi-approval: LOGIAGENTTOKEN, LOGIAGENTPUBLIC_ID

Other agent clients (Cursor, Codex, Copilot, …)

The skills follow the open Agent Skills format — copy any plugins/*/skills// directory into your client's skills directory. Add the MCP servers with your client's MCP configuration using the same npx commands found in each plugin's .mcp.json.

Single-file skill install without the plugin system:

curl -fsSL https://docs.1pass.dev/skills/logi-rp-integrate/SKILL.md \
  -o ~/.claude/skills/logi-rp-integrate/SKILL.md --create-dirs

Docs

  • Integration guides: https://docs.1pass.dev
  • LLM-readable docs: https://docs.1pass.dev/llms.txt

License

MIT

Nothing above is checked by us. What we check is on the safety report.

Logi Approval: common questions

Is Logi Approval MCP server safe?
Mostly: it is graded B (75/100). Read the Logi Approval safety report
How do I install Logi Approval?
It runs on your machine. Copy the Claude Code, Cursor, VS Code or Claude Desktop config from the install section.
Does Logi Approval need an API key?
Yes. The registry entry asks for LOGI_AGENT_TOKEN, LOGI_AGENT_PRIVATE_KEY.
Is Logi Approval maintained?
The last commit was 89 days ago (2026-08-07). The latest release is v0.1.2.
What can I use instead of Logi Approval?
Servers from other publishers that do the same job: Decionis MCP server, Emilia Protocol MCP server and CHAP Coordinator MCP server.
How does Logi Approval compare with other AI and agents MCP servers?
safety score 75/100 (higher than 45% 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 Logi Approval

Same job from other publishers: the closest match first, then the best rated.

  • Decionis
    Authorize consequential AI agent actions before execution
    More from decionis.com →
    A
  • Emilia Protocol
    Exact-action approval for consequential agent actions: request, track, and verify signed receipts.
    B
  • CHAP Coordinator
    Auditable records of human decisions over AI agent work. Approvals, edits, overrides, escalations.
    A
  • HOL Guard
    Local-first AI agent security evidence and approval workflows through HOL Guard's stdio MCP server.
    A
  • Agent-Native Chat
    Minimal chat-first app with durable threads, actions, and the app-agent loop
    A