ARBITER MCP Server

by grip Your server? Claim it

answering

ARBITER is answering right now. Last checked 11 min ago. It exposes 2 tools.

Decision arbitration, action routing, workflow control, deployment remediation, persistent memory.

Uptime history 6 days of history · worst day 71%

6 days agonow

100.0%

Uptime 24h

91 of 91 checks

Tools

read from the server

951 ms

Response time

average over 24h

open, no key

Access

streamable-http

What changed 8

Every tool that appeared, vanished or quietly changed what it asks for. Recorded since 17 September 2026. No other catalogue keeps this.

17 Sep 2 tool descriptions were rewritten arbiter_compare, arbiter_embed

17 Sep 2 tools changed the parameters they ask for arbiter_compare, arbiter_embed

16 Sep 2 tool descriptions were rewritten arbiter_compare, arbiter_embed

16 Sep 2 tools changed the parameters they ask for arbiter_compare, arbiter_embed

ARBITER does not always answer

Over the last week it answered 95.1% of our checks. We check every 15 minutes, so you hear about the next outage within the hour — not from your users.

Connect this server

Endpoint below is the one we actually reach during checks — not the one copied from a README. Last verified 11 min ago.

Claude Code Claude Desktop Codex Cursor VS Code

run in your terminal

claude mcp add arbiter --transport http https://api.grip.fyi/mcp

~/Library/Application Support/Claude/claude_desktop_config.json

{
  "mcpServers": {
    "arbiter": {
      "url": "https://api.grip.fyi/mcp"
    }
  }
}

~/.codex/config.toml

[mcp_servers.arbiter]
url = "https://api.grip.fyi/mcp"

.cursor/mcp.json

{
  "mcpServers": {
    "arbiter": {
      "url": "https://api.grip.fyi/mcp"
    }
  }
}

.vscode/mcp.json

{
  "mcpServers": {
    "arbiter": {
      "url": "https://api.grip.fyi/mcp"
    }
  }
}

Available tools 2

Read directly from the server with tools/list, grouped by what they act on. If a tool disappears, we record the date.

arbiter

arbiter_compare

Paid ARBITER finite-candidate measurement for contextual choice. Use when a caller already has an explicit candidate field and needs it ordered against a query, current state, intent, context, question, or perspective. query is the situation to measure. candidates is the finite caller-supplied field to order. top_k optionally limits returned results. Returns MCP text content containing the JSON result from POST /v1/compare with the supplied candidates ordered by measured coherence. Does not generate candidates or execute the selected action. Deterministic for identical inputs and engine state. Price: $0.01 USDC on Base per call. MCP identity: fyi.grip/arbiter.

arbiter_embed

Paid ARBITER deterministic persistent machine representation. Use when a caller needs representations of supplied text for storage, indexing, retrieval, clustering, reuse, or later comparison. Use arbiter_compare instead when an explicit finite candidate field needs ordering now. texts is one or more supplied strings. Returns MCP text content containing the JSON result from POST /v1/embed. Does not store, retrieve, update, delete, or rank records. Deterministic for identical inputs and engine state. Price: $0.01 USDC on Base per call. MCP identity: fyi.grip/arbiter.

Endpoints

URL	Transport	State	Latency	Checked
https://api.grip.fyi/mcp	streamable-http	answering	701 ms	11 min ago

Alternatives to ARBITER

same job, measured the same way

Perceptdot Vercel

by perceptdot

AI agent vision for Vercel deployments — with ROI measurement. perceptdot.com

29 installs/wk local only

Clize

by clize

Real-world actions for AI coding agents: domains, email, deploys, payments, media, and SEO/GEO.

2 251 installs/wk local only

Control Plane

by cpln

Control Plane (controlplane.com): deploy and operate workloads across AWS, GCP, Azure, and more.

answering

Prefect MCP Server

by prefecthq

MCP server for Prefect. Monitor and debug workflows, deployments, and automations.

2 259 installs/wk local only

memex

by ayushagrawal288

Persistent memory for AI agents — semantic + recency search, ONNX embeddings, Docker Compose.

local only

Cloudwright

by xmpuspus

Cloud architecture and migration planning with costs, controls, evidence, and deployable IaC.

197 installs/wk local only

RokuMCP

by jack1590

MCP server for Roku device automation — deploy, ECP control, screenshots, and debug console

103 installs/wk local only

Perceptdot

by soondoobu1111-star

B2A2H platform — tracks GA4, Vercel deployments, GitHub workflows with AI-powered ROI analytics.

1 tools answering

ARBITER — questions

Answers built from our own checks of this server.

What can ARBITER do?

It exposes 2 tools, read directly from the server on our last check. Among them: arbiter_compare, arbiter_embed. The full list with descriptions is on this page — we take it from the server itself via tools/list, not from a README. How MCP servers expose tools in the first place →

Is ARBITER working right now?

We send a real MCP handshake every 15 minutes. Over the last 24 hours 91 of 91 checks got a reply (100.0%), average response time 951 ms. The bar chart above shows every period we have measured.

How do I connect ARBITER?

Copy the ready config from this page — we generate it for Claude Code, Claude Desktop, Codex, Cursor and VS Code, each with the file path that client actually reads. It is a remote server, so there is nothing to install — the client connects to the address.

Does ARBITER need an API key?

No. ARBITER completed a full MCP handshake with us as an anonymous client and listed its tools without asking for anything. All 2 of them are readable on this page. This is what we observed, not what the docs claim.

How fast is ARBITER?

It answers our handshake in 951 ms on average, which is faster than 10% of all working MCP servers we measure. That is on the slow side — worth knowing if the tool sits inside an interactive loop. The comparison comes from our own checks across the whole registry, every 15 minutes.