protogrid
Sign inAdd to your agent

Search / ai.abmeter/abmeter

ABMeter

R2· OAuth, once

Run A/B experiments through your AI assistant. SDKs for Ruby, Python, JS, Node, React Native, Go.

v0.2.0 · active · repository · website · descriptor JSON · versions

An agent can connect after a one-time OAuth consent by a human.Remote endpoint behind OAuth 2. Tokens stay with the agent; the registry only exposes the authorization metadata.
Quality83good
Trust96of 100
Uptime, 30 days96%
Latency p50801 ms

Connect

8 clients · secrets stay placeholders
{
  "mcpServers": {
    "abmeter": {
      "type": "http",
      "url": "https://mcp.abmeter.ai"
    }
  }
}
claude mcp add --transport http abmeter https://mcp.abmeter.ai
[mcp_servers.abmeter]
url = "https://mcp.abmeter.ai"

{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "abmeter": {
      "type": "remote",
      "url": "https://mcp.abmeter.ai",
      "enabled": true
    }
  }
}
{
  "mcpServers": {
    "abmeter": {
      "type": "http",
      "url": "https://mcp.abmeter.ai"
    }
  },
  "deeplink": "cursor://anysphere.cursor-deeplink/mcp/install?name=abmeter&config=eyJ0eXBlIjoiaHR0cCIsInVybCI6Imh0dHBzOi8vbWNwLmFibWV0ZXIuYWkifQ%3D%3D"
}
{
  "servers": {
    "abmeter": {
      "type": "http",
      "url": "https://mcp.abmeter.ai"
    }
  }
}
{
  "mcpServers": {
    "abmeter": {
      "httpUrl": "https://mcp.abmeter.ai"
    }
  }
}
extensions:
  "abmeter":
    enabled: true
    name: "abmeter"
    type: streamable_http
    uri: "https://mcp.abmeter.ai"
    timeout: 300

Quality 83 / 100good

protocoln/a · weight 25
  • n/a
    protocol.modern, protocol.stateless, protocol.transport, protocol.list_ttlno remote answered a protocol handshake (not probed yet, unreachable, or local-only)
authorization83 · weight 15
  • pass
    auth.prmProtected Resource Metadata (RFC 9728) published
  • pass
    auth.as_metadataauthorization server metadata reachable
  • warn
    auth.cimdonly Dynamic Client Registration, deprecated in 2026-07-28 in favour of CIMD
  • n/a
    auth.secret_in_urlno templated URL
tool hygienen/a · weight 30
  • n/a
    tools.descriptions, tools.description_length, tools.schemas, tools.annotations, tools.directory_hints, tools.token_cost, tools.api_dumptool list unknown (behind auth, not probed, or empty)
stabilityn/a · weight 15
  • n/a
    stability.changes, stability.rug_pulltool list unknown
dependenciesn/a · weight 15
  • n/a
    deps.known_vulns, deps.mcp_sdk_version, deps.resolvableno npm or PyPI package

Tool list unknown · checked 2026-10-20 13:49 UTC

Tool changes

No tool definition changes recorded. A server's first observation is its baseline; later probes record what changes.

Checks run on what our credential-free, read-only probes observe; tools are never called and no code audit is performed. How it is computed.

Trust 96 / 100

provenance100
liveness98
freshness85
hygiene100

+repository +namespace-matches-repo +dns-namespace +website +reachable +uptime-96% ~updated-52d-ago

Derived from observable signals (official registry feed and our own credential-free probes); no code audit performed. How it is computed.

Endpoints

remoteauthreachableuptime 30dp50protocollast ok
https://mcp.abmeter.ai streamable-httpoauth2 AS: https://abmeter.aiyes96%801 ms–2026-10-20

Tools (0)

No tools observed. Tools appear once a credential-free probe can list them.

Schemas: list_tools.

Similar MCP servers

  • Buoy-ggL0
    io.github.Buoy-gg/mcp

    Let AI agents read and drive a running React Native or Flutter app through Buoy's devtools.

  • IA-QA — 130+ QA & Dev Tools for AI AgentsR0quality 85
    io.github.JcJamet/ia-qa-toolbox

    130+ QA & dev tools for AI agents: prompt injection, RAG testing, VLM eval, guardrails. Free.

  • MidaR2quality 83
    so.mida/ab-testing

    Create, run and analyze A/B tests and personalizations on your site with Mida.

  • runvouchR1quality 82
    com.runvouch/runvouch

    Watchdog for unattended AI agents: alerts, evidence checks and a verifiable proof per run.

  • redlineL0
    io.github.gowtham0992/redline

    Run local prompt regression checks from prompt-response logs in AI coding assistants.

  • AitherOS ADKL0
    io.github.Aitherium/aither-adk

    Agent runtime with typed memory, knowledge and code graphs, plus file and web tools

Official server.json
{
  "name": "ai.abmeter/abmeter",
  "_meta": {
    "io.modelcontextprotocol.registry/publisher-provided": {
      "docs": "https://abmeter.ai/lab/quick-start",
      "connect": "https://abmeter.ai/lab/connect-mcp"
    }
  },
  "icons": [
    {
      "src": "https://abmeter.ai/abmeter-icon-192.png",
      "sizes": [
        "192x192"
      ],
      "mimeType": "image/png"
    },
    {
      "src": "https://abmeter.ai/favicon.svg",
      "sizes": [
        "any"
      ],
      "mimeType": "image/svg+xml"
    }
  ],
  "title": "ABMeter",
  "$schema": "https://static.modelcontextprotocol.io/schemas/2025-12-11/server.schema.json",
  "remotes": [
    {
      "url": "https://mcp.abmeter.ai",
      "type": "streamable-http"
    }
  ],
  "version": "0.2.0",
  "repository": {
    "url": "https://github.com/abmeter/abmeter",
    "source": "github"
  },
  "websiteUrl": "https://abmeter.ai",
  "description": "Run A/B experiments through your AI assistant. SDKs for Ruby, Python, JS, Node, React Native, Go."
}