ARBITER MCP Server

by grip Your server? Claim it

answering

ARBITER is answering right now. Last checked 7 min ago. It exposes 2 tools.

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

Uptime history 51 days of history · worst day 65%

51 days agonow

98.9%

Uptime 24h

90 of 91 checks

Tools

read from the server

1217 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 missed one check this week

Everything else answered, so this is steady rather than shaky. We check every 15 minutes, which is how a one-off gets told apart from the start of a pattern, and how you hear about the next one within the hour instead of 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 7 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

Settings → Connectors → Add custom connector, then paste this address

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

{
  "servers": {
    "arbiter": {
      "type": "http",
      "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	790 ms	7 min ago

Alternatives to ARBITER

same job, measured the same way

GraphyLoop

by chadixearth

Workflow planner, wave dispatcher, persistent swarm memory, and deploy preflight for AI agents.

935 installs/wk local only

Perceptdot Vercel

by perceptdot

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

42 installs/wk local only

Whenever

by whenever

Write, validate, deploy and run TypeScript workflow automations on Whenever from your coding agent.

answering

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.

1 700 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.

179 installs/wk local only

Groundwork

by nickjlamb

Deployment-readiness checks for document-QA and extraction AI: grounding, extraction, CI gate.

50 installs/wk local only

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 90 of 91 checks got a reply (98.9%), average response time 1217 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 in the form 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 1217 ms on average, which is faster than 3% 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.