# ARBITER (remote · api.grip.fyi)

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

- Trust score: 68/100 (medium)
- Change this week: +4
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-09-28

## Components

- remote · `api.grip.fyi`: 68/100 (this document), [markdown](https://verifymcp.io/servers/fyi-grip-arbiter/api.md), [page](https://verifymcp.io/servers/fyi-grip-arbiter/api)

## Channel facts

- Endpoint: `https://api.grip.fyi/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `1.0.2`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-09-28.

- **Endpoint Security**: 46/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - Authorisation not fully verified: no authorisation is required to call this server, and 2 tool(s) never declared a destructiveHint. The MCP spec treats an absent hint as destructive by default, so we cannot call this surface safe.
  - HTTPS enforcement could not be verified: the plaintext port answered with HTTP 405, which proves neither a plaintext path nor enforcement.
  - HSTS check failed: the Strict-Transport-Security header is absent.
  - DNSSEC check failed: this domain isn't protected by DNSSEC.
- **Transport & Reachability**: 100/100
  - Verified streamable-http transport via a live MCP handshake.
- **Schema Quality & AI Usability**: 76/100
  - AI-judged instruction clarity (excellent).
  - Context-footprint check failed: tool/resource definitions use about 363 tokens (~181/item across 2 items; 2 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 53/100
  - Stability observed for 16 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 100/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 100% of tool parameters carry a description.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - We read all 2 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 2 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

## Install

### How do I install the ARBITER MCP server?

ARBITER is a hosted endpoint at https://api.grip.fyi/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

### Claude

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

### Cursor

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

### VS Code

```json
{
  "servers": {
    "fyi-grip-arbiter": {
      "type": "http",
      "url": "https://api.grip.fyi/mcp"
    }
  }
}
```

### Codex

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

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "fyi-grip-arbiter": {
      "type": "remote",
      "url": "https://api.grip.fyi/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add fyi-grip-arbiter --url 'https://api.grip.fyi/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  fyi-grip-arbiter:
    url: "https://api.grip.fyi/mcp"
```

### Netclaw

```json
{
  "McpServers": {
    "fyi-grip-arbiter": {
      "Transport": "http",
      "Url": "https://api.grip.fyi/mcp"
    }
  }
}
```

### Vellum

```bash
assistant mcp add fyi-grip-arbiter -t streamable-http -u 'https://api.grip.fyi/mcp'
```

### Other

```json
{
  "mcpServers": {
    "fyi-grip-arbiter": {
      "type": "http",
      "url": "https://api.grip.fyi/mcp"
    }
  }
}
```

The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-09-28 (score 68, +1)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-09-26 (score 67, +1)

- [functional improvement] Endpoint reachability: not serving MCP → reachable

### 2026-09-25 (score 66, +48)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-09-24 (score 18, −47)

- [security regression] Endpoint reachability: reachable → not serving MCP
- [security regression] Stability: 0.37 → unverified
- [security regression] Tool safety: pass → unverified
- [security regression] Transport: pass → fail
- [security] Authorization: Authorisation not fully verified: no authorisation is required to connect, but we couldn't read the whole tool list to see what that exposes.
- [functional regression] Capabilities: pass → unverified
- [functional regression] Tool coverage: 100 → unverified
- [functional] First check of Schema quality: unverified

### 2026-09-22 (score 65, +1)

No change was recorded against any check on this day. Stability & Change Management went from 30 to 33. That category is still filling its 30-day observation window: 9 days of observed history at the previous scan, 10 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-20 (score 64, +1)

No change was recorded against any check on this day. Stability & Change Management went from 23 to 27. That category is still filling its 30-day observation window: 7 days of observed history at the previous scan, 8 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-18 (score 63, +1)

No change was recorded against any check on this day. Stability & Change Management went from 17 to 20. That category is still filling its 30-day observation window: 5 days of observed history at the previous scan, 6 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-17 (score 62, +6)

- [security] Tool “arbiter_compare” rewrote its description, which is the text the model reads
- [security] Tool “arbiter_embed” rewrote its description, which is the text the model reads
- [functional improvement] Schema quality: 237 → 181
- [functional improvement] Tool coverage: 0% → 100%
- [functional] Schema quality: good → excellent
- [cosmetic] “arbiter_compare” reworded the description of “candidates”
- [cosmetic] “arbiter_compare” reworded the description of “query”
- [cosmetic] “arbiter_compare” reworded the description of “top_k”
- [cosmetic] “arbiter_embed” reworded the description of “texts”
- [cosmetic] “arbiter_compare” dropped the optional parameter “use_freq”
- [cosmetic] “arbiter_embed” dropped the optional parameter “use_freq”

## MCP tools (2)

### `arbiter_compare` (~215 tokens)

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.

Input parameters:

- `candidates` (array, required): Finite caller-supplied candidate field to order. ARBITER measures these candidates and does not generate them.
- `query` (string, required): Current state, context, intent, question, or perspective to measure against the candidate field.
- `top_k` (integer): Optional maximum number of highest-ranked candidates to return.

### `arbiter_embed` (~148 tokens)

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.

Input parameters:

- `texts` (array, required): One or more supplied text values to convert into deterministic persistent machine representations.

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/fyi-grip-arbiter/api#diagnostics

## Score history

- 2026-09-28: 68
- 2026-09-27: 67
- 2026-09-26: 67
- 2026-09-25: 66
- 2026-09-24: 18
- 2026-09-23: 65
- 2026-09-22: 65
- 2026-09-21: 64
- 2026-09-20: 64
- 2026-09-19: 63
- 2026-09-18: 63
- 2026-09-17: 62
- 2026-09-16: 56
- 2026-09-15: 56
- 2026-09-14: 55
- 2026-09-13: 55
- 2026-09-12: 54

## Common questions

### What is the ARBITER MCP server?

ARBITER is an MCP server listed in the public MCP registry as fyi.grip/arbiter. Decision arbitration, action routing, workflow control, deployment remediation, persistent memory. This page covers its hosted endpoint (https://api.grip.fyi/mcp).

### Is the ARBITER MCP server safe to use?

ARBITER scores 68 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

### What tools does the ARBITER MCP server expose?

ARBITER exposes 2 tools: arbiter_compare, arbiter_embed. Their descriptions and schemas cost roughly 363 tokens of context every time the server is loaded.

### Does the ARBITER MCP server require authentication?

No. We connected to ARBITER without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

### Is the ARBITER MCP server still maintained?

ARBITER is still listed as active in the MCP registry. We last reached this channel on 28 September 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

## Links

- Remote endpoint: https://api.grip.fyi/mcp
- Website: https://api.grip.fyi/
- Changelog RSS feed: https://verifymcp.io/servers/fyi-grip-arbiter/api.xml
- Changelog JSON feed: https://verifymcp.io/servers/fyi-grip-arbiter/api.json
- HTML version of this page: https://verifymcp.io/servers/fyi-grip-arbiter/api