Myagi - Open Agent Registry MCP server
online · 100% uptimebot.myagi/openagent-registry·v0.1.0Score any website's AI-agent readiness. Open Agent Registry scanner + platform tools.
0 stars
Reviews
Write oneNobody has reviewed Myagi - Open Agent Registry yet.
If you have run it, two minutes of your experience saves the next person an afternoon.
Myagi - Open Agent Registry tools (3, 1 write)
write = sends, deletes, buys or postsquery_platformFreeReturns structured information about the Myagi platform: current phase, milestones, conceptual model, and public roadmap.
registry_lookupFreeLook up a domain's agent-readiness score in the Open Agent Registry. Proxies to /open-agent-registry/api/scan. Returns the full Profile (signals, score, label, approval_path).
submit_inquirywrite actionFreeSubmit a contact inquiry on behalf of the calling agent's operator. Forwards to contact@myagi.bot. Returns an inquiry ID on success.
Public scan report
scanner v0.1.9 · 2026-09-27 · same rubric, same numbers if you re-run it
- –Code scanremote-only server, no package to scann/a
- Live reliabilityremote reachable in 736ms20/20
- Tool poisoning3 tool descriptions checked15/15
- Auth qualityopen endpoint exposes 1 write-action tools with no auth3/15
- Maintenancelast push 6 days ago15/15
- Maintainer identitynamespace and repository owner differ; GitHub account older than a year; website matches verified namespace8/10
Findings (1)
- highWrite-action tools reachable without authentication
auth.open-write
How Myagi - Open Agent Registry compares
Against every graded AI and agents MCP server, from our own scans and uptime checks. Updated after each scan run.
- Safety score
- 81/100
- higher than 63% of 4,460 AI and agents servers
- Tools
- 3
- the typical AI and agents server has 6
- Tools that change things
- 33%
- typical: 0%. Fewer write tools means less an agent can break
- Uptime
- 100%
- of our recent checks; the typical remote AI and agents server answers 100%
- Response time
- 766 ms
- faster than 15% of 2,331 AI and agents servers
What its tools let an agent do: 2 read · 1 change
Install Myagi - Open Agent Registry in Claude Code, Cursor or VS Code
claude mcp add --transport http openagent-registry https://myagi.bot/api/mcp
What the publisher says
From the Myagi - Open Agent Registry repository's README, as published. We do not edit it. Read it on GitHub
OpenAgent Registry
The open registry, scanner, and leaderboard for agent-ready websites and services.
OpenAgent Registry (OAR) does three things in one place:
- Scans any URL for the full stack of agent-access signals - llms.txt, agents.txt / agents.json, AGENTS.md, .well-known/agent-card.json, robots.txt + Content Signals, OpenAPI, OAuth discovery, RSL licensing, MCP/A2A registry presence - and aggregates upstream registries instead of re-doing their work.
- Scores each site against a transparent, public rubric and ranks it within its industry category.
- Tells you what to do about it - a concrete approval-path checklist with deep links to the actual developer applications, OAuth signups, partner programs, and standards-adoption steps. Lead with the checklist; the score is supporting evidence.
Sources of authoritative scoring credit (registries / standards bodies):
- Official MCP Registry - the MCP working group's catalog of MCP servers (+25 if your domain ships one)
- Standards: llms.txt, agents.txt / agents.json, A2A Protocol, Web Bot Auth, RSL
Community resources used for domain discovery only (no score credit; we use these to know which sites to scan):
- thedaviddias/llms-txt-hub - one maintainer's community list of sites publishing llms.txt
- Agent Friendly Directory - sklivvz's curated agent-usable services
- A2A Registry - community directory of A2A agents
- LLMTEXT - llms.txt validation toolkit
What OAR adds that none of the above does today:
- Comparative leaderboards by industry category (rentals, shopping, content, social, developer)
- Approval-path generator - concrete next steps, not just "you have OAuth"
- Aggregation across the full stack in one report
- Change monitoring over time
- A public, free API so agents (including your own) can query it before calling external services
Status
Pre-alpha but live. Public deploy: https://openagent-registry.vercel.app.
After the v0.1 import, the registry tracks 1,400+ services across 6 industry categories, sourced from the original seed plus an import of llms-txt-hub. Every service has a live score, a label, and a generated approval-path checklist. Looking for contributors - especially for approval-path data per service (the moat).
Stack
- Next.js 15 (App Router) + TypeScript + Tailwind CSS
- No backend service in v0 - Next.js API routes do the scanning
- Local JSON cache for MVP; Postgres or Vercel KV for production scale
- Deploys natively to Vercel
Quickstart
pnpm install
pnpm devThen open .
How scoring works
See docs/rubric.md. Every signal is weighted, every weight is published, every score is reproducible from the JSON profile. No black-box scoring.
The current rubric (summary):
Shortened. The full README is on GitHub.
Nothing above is checked by us. What we check is on the safety report.
Myagi - Open Agent Registry: common questions
- Is Myagi - Open Agent Registry MCP server safe?
- Mostly: it is graded B (81/100). Read the Myagi - Open Agent Registry safety report
- How do I install Myagi - Open Agent Registry?
- It runs remotely at myagi.bot. Add it to Claude Code, Cursor, VS Code or Claude Desktop with the snippets above, or call it through the mcp.market gateway without installing anything.
- Does Myagi - Open Agent Registry need an API key?
- Not as far as the registry entry and our scan can tell: no credentials are declared or required.
- Is Myagi - Open Agent Registry maintained?
- The last commit was 44 days ago (2026-09-21). The latest release is v0.1.0.
- Is Myagi - Open Agent Registry up?
- 100% of our last 28 checks got an answer. We check remote servers about four times a day.
- What can I use instead of Myagi - Open Agent Registry?
- Servers from other publishers that do the same job: Agent Security Scanner MCP server.
- How does Myagi - Open Agent Registry compare with other AI and agents MCP servers?
- safety score 81/100 (higher than 63% of 4,460 AI and agents servers); tools 3 (the typical AI and agents server has 6); tools that change things 33% (typical: 0%. Fewer write tools means less an agent can break). Full comparison.
Alternatives to Myagi - Open Agent Registry
Same job from other publishers: the closest match first, then the best rated.
- Agent Security ScannerSecurity layer for AI agents: blocks prompt injection, detects fake packages, scans vulnerabilities.not reviewedEstablishedC