# AI Arena Agent Tools (remote · mcp.ai-arena.ca)

Read-only US public-data screening tools with free Basic and Evidence tiers.

- Trust score: 75/100 (medium)
- Change this week: +3
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-09-20

## Components

- remote · `mcp.ai-arena.ca`: 75/100 (this document), [markdown](https://verifymcp.io/servers/ca-ai-arena-agent-tools/mcp.md), [page](https://verifymcp.io/servers/ca-ai-arena-agent-tools/mcp)

## Channel facts

- Endpoint: `https://mcp.ai-arena.ca/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `0.2.1`

## 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 2026-09-20.

- **Endpoint Security**: 80/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - No authorisation is required to call this server. Every tool declares its destructiveHint and none is destructive, so open access doesn't expose one.
  - HTTPS is enforced; there's no plaintext access path.
  - The HSTS (Strict-Transport-Security) header is present.
  - 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**: 72/100
  - AI-judged instruction clarity (good).
  - Tool/resource definitions use about 634 tokens (~48/item across 13 items; 13 tools + 0 resources), lean.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 30/100
  - Stability observed for 9 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 77/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 30% 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 13 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 14 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a current MCP spec version (2026-07-28).

## Install

### How do I install the AI Arena Agent Tools MCP server?

AI Arena Agent Tools is a hosted endpoint at https://mcp.ai-arena.ca/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 ca-ai-arena-agent-tools 'https://mcp.ai-arena.ca/mcp'
```

### Cursor

```json
{
  "mcpServers": {
    "ca-ai-arena-agent-tools": {
      "url": "https://mcp.ai-arena.ca/mcp"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "ca-ai-arena-agent-tools": {
      "type": "http",
      "url": "https://mcp.ai-arena.ca/mcp"
    }
  }
}
```

### Codex

```toml
[mcp_servers.ca-ai-arena-agent-tools]
url = "https://mcp.ai-arena.ca/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "ca-ai-arena-agent-tools": {
      "type": "remote",
      "url": "https://mcp.ai-arena.ca/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add ca-ai-arena-agent-tools --url 'https://mcp.ai-arena.ca/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  ca-ai-arena-agent-tools:
    url: "https://mcp.ai-arena.ca/mcp"
```

### Netclaw

```json
{
  "McpServers": {
    "ca-ai-arena-agent-tools": {
      "Transport": "http",
      "Url": "https://mcp.ai-arena.ca/mcp"
    }
  }
}
```

### Vellum

```bash
assistant mcp add ca-ai-arena-agent-tools -t streamable-http -u 'https://mcp.ai-arena.ca/mcp'
```

### Other

```json
{
  "mcpServers": {
    "ca-ai-arena-agent-tools": {
      "type": "http",
      "url": "https://mcp.ai-arena.ca/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.

### 2026-09-19 (score 75, +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.

### 2026-09-16 (score 74, +1)

No change was recorded against any check on this day. Stability & Change Management went from 13 to 17. That category is still filling its 30-day observation window: 4 days of observed history at the previous scan, 5 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-14 (score 73, +1)

No change was recorded against any check on this day. Stability & Change Management went from 7 to 10. That category is still filling its 30-day observation window: 2 days of observed history at the previous scan, 3 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-12 (score 72, +1)

- [functional improvement] Stability: unverified → 0.03
- [functional] Server version: 0.2.1 → 0.2.2

### 2026-09-11 (score 71)

First indexed and scored.

## MCP tools (13)

### `ai_arena_status` (~23 tokens)

AI Arena Service Status

Check AI Arena version, free-beta mode and available pricing tiers.

### `sec_recent_filings_basic` (~44 tokens)

SEC Recent Filings — Basic

FREE beta. Compact recent SEC filing metadata optimized for low-token agent screening.

Input parameters:

- `cik` (string, required): SEC Central Index Key.
- `limit` (integer)

### `sec_recent_filings_evidence` (~54 tokens)

SEC Recent Filings — Evidence

FREE beta. Recent SEC filings with accession data, filing URLs, retrieval provenance and larger limits. Intended future paid tier.

Input parameters:

- `cik` (string, required): SEC Central Index Key.
- `limit` (integer)

### `sec_action_radar_basic` (~49 tokens)

SEC Corporate Action Radar — Basic

FREE beta. Quickly flags recent filing forms associated with tenders, offerings, proxies and material events.

Input parameters:

- `cik` (string, required): SEC Central Index Key.
- `limit` (integer)

### `sec_action_radar_evidence` (~55 tokens)

SEC Corporate Action Radar — Evidence

FREE beta. Form-based corporate-action signals with confidence, accession numbers, direct filing URLs and provenance. Intended future paid tier.

Input parameters:

- `cik` (string, required): SEC Central Index Key.
- `limit` (integer)

### `sec_company_fact_search_basic` (~50 tokens)

SEC Company Facts Search — Basic

FREE beta. Search SEC XBRL facts and return compact latest observations.

Input parameters:

- `cik` (string, required)
- `concept` (string, required): Concept name or label fragment, e.g. revenue.

### `sec_company_fact_search_evidence` (~59 tokens)

SEC Company Facts Search — Evidence

FREE beta. SEC XBRL concept matches with descriptions, multiple observations and source provenance. Intended future paid tier.

Input parameters:

- `cik` (string, required)
- `concept` (string, required): Concept name or label fragment, e.g. revenue.

### `us_federal_award_basic` (~35 tokens)

US Federal Award — Basic

FREE beta. Compact USAspending federal-award summary by award ID.

Input parameters:

- `award_id` (string, required)

### `us_federal_award_evidence` (~48 tokens)

US Federal Award — Evidence

FREE beta. Richer USAspending award evidence and provenance while avoiding an unbounded raw passthrough. Intended future paid tier.

Input parameters:

- `award_id` (string, required)

### `us_recipient_search_basic` (~41 tokens)

US Federal Recipient Search — Basic

FREE beta. Search USAspending recipient names/UEIs with compact results.

Input parameters:

- `limit` (integer)
- `query` (string, required)

### `us_recipient_search_evidence` (~43 tokens)

US Federal Recipient Search — Evidence

FREE beta. Larger recipient result set with authoritative API provenance. Intended future paid tier.

Input parameters:

- `limit` (integer)
- `query` (string, required)

### `tender_preflight_basic` (~45 tokens)

Tender Preflight — Basic

FREE beta. Deterministic screening for set-aside, NAICS, PSC, security-clearance and date signals in supplied tender text.

Input parameters:

- `text` (string, required)

### `tender_preflight_evidence` (~39 tokens)

Tender Preflight — Evidence

FREE beta. Deterministic tender screening plus explicit evidence categories and interpretation notes. Intended future paid tier.

Input parameters:

- `text` (string, required)

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/ca-ai-arena-agent-tools/mcp#diagnostics

## Score history

- 2026-09-20: 75
- 2026-09-19: 75
- 2026-09-18: 74
- 2026-09-17: 74
- 2026-09-16: 74
- 2026-09-15: 73
- 2026-09-14: 73
- 2026-09-13: 72
- 2026-09-12: 72
- 2026-09-11: 71

## Common questions

### What is the AI Arena Agent Tools MCP server?

AI Arena Agent Tools is an MCP server listed in the public MCP registry as ca.ai-arena/agent-tools. Read-only US public-data screening tools with free Basic and Evidence tiers. This page covers its hosted endpoint (https://mcp.ai-arena.ca/mcp).

### Is the AI Arena Agent Tools MCP server safe to use?

AI Arena Agent Tools scores 75 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 AI Arena Agent Tools MCP server expose?

AI Arena Agent Tools exposes 13 tools: ai_arena_status, sec_recent_filings_basic, sec_recent_filings_evidence, sec_action_radar_basic, sec_action_radar_evidence, and 8 more. Their descriptions and schemas cost roughly 585 tokens of context every time the server is loaded.

### Does the AI Arena Agent Tools MCP server require authentication?

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

### Is the AI Arena Agent Tools MCP server still maintained?

AI Arena Agent Tools is still listed as active in the MCP registry. We last reached this channel on 20 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://mcp.ai-arena.ca/mcp
- Website: https://api.ai-arena.ca/v1/agent-catalog
- Changelog RSS feed: https://verifymcp.io/servers/ca-ai-arena-agent-tools/mcp.xml
- Changelog JSON feed: https://verifymcp.io/servers/ca-ai-arena-agent-tools/mcp.json
- HTML version of this page: https://verifymcp.io/servers/ca-ai-arena-agent-tools/mcp