A
licenseA
qualityB
maintenanceEnables coding agents to compact conversation contexts verbatim, make fast decisions through choice, boolean, and rubric scoring, and enforce command safety guardrails.
6
MIT
ARBITER
by fyi.grip
Server Details
Deterministic contextual decision arbitration and action routing for autonomous software. Takes current state, context, or intent plus caller-supplied candidate actions, state transitions, routes, refusals, escalations, tools, or models and returns a deterministic ordered candidate field. Also provides persistent machine representations for memory, retrieval, indexing, and downstream coherence measurement.
Ownership verified
- Status
- Healthy
- Uptime
- 95.0% over the last 24 hours
- Last Tested
- Transport
- Streamable HTTP · MCP 2025-11-25
- URL
- ChatGPT
- –
- Claude
- –
TDQS
A4.4/5.0
Scored across 2 tools
Disambiguation5/5
arbiter_compare orders an explicit candidate set against a query, while arbiter_embed produces vector representations for supplied text. Their descriptions clearly distinguish ranking from representation and explicitly cross-reference when to use each, leaving no ambiguity.
Naming Consistency5/5
Both tools follow the arbiter_<verb> pattern using lowercase snake_case and a consistent vendor prefix. compare and embed are parallel action verbs, making the naming fully predictable.
Tool Count3/5
Two tools is on the thin side per calibration and exposes only a pair of operations. For a narrow paid API this is defensible, but it is borderline rather than a full toolset.
Completeness5/5
The server's apparent domain is exactly two stateless ARBITER operations, compare and embed. Both operations are covered and the descriptions explicitly state what each tool does not do, so there are no obvious missing capabilities.
Available Tools
2 toolsarbiter_compareAInspect
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.
Inputs: query (required), candidates (required), top_k.
arbiter_embedAInspect
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.
Inputs: texts (required).
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Related MCP Connectors
Deterministic decision layer for autonomous agents: reproducible PROCEED/REVIEW/SKIP verdicts.
Deterministic reasoning stack for AI agents: simulate, decide & compute, plus cross-domain tools.
Governed decision engine: yes/no, score, choice and rank answers about cases, from past outcomes.
Typed AI decisions for agents: classify, route, screen evidence, score and batch-label text.
Related MCP Servers
- AlicenseNot gradedqualityBmaintenanceEnables MCP-compatible agents to arbitrate typed state-action schemas, dispatch routine actions deterministically, and apply pre-escalation filters that reduce unnecessary frontier LLM calls. It supports low-latency, schema-enforced routing with safety guardrails and local-first memory retention.7MIT
- AlicenseAqualityCmaintenanceEnables agents to resolve ambiguous decisions by returning calibrated probabilities for each candidate action, along with a gate that signals whether to act on the top option or escalate, all via a cheap local or remote backend.5MIT
- FlicenseAqualityCmaintenanceEnables AI agents to hand high-level objectives to a decision-making core that autonomously reasons, plans, enforces deterministic policy, executes capabilities, evaluates outcomes, and persists semantic memory over stdio or Streamable HTTP.6-
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd
Glama MCP Gateway
Add one secure layer between your agents and this server.