# AgentoolRank (remote · agentoolrank.com)

Search and compare open-source AI agent tools ranked by live GitHub activity, and list new ones.

- Trust score: 64/100 (medium)
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-10-04

## Components

- remote · `agentoolrank.com`: 64/100 (this document), [markdown](https://verifymcp.io/servers/com-agentoolrank-agent-tools/api-mcp.md), [page](https://verifymcp.io/servers/com-agentoolrank-agent-tools/api-mcp)

## Channel facts

- Endpoint: `https://agentoolrank.com/api/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 2026-10-04.

- **Endpoint Security**: 63/100
  - 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 6 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 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**: 66/100
  - AI-judged instruction clarity (good).
  - Context-footprint check failed: tool/resource definitions use about 724 tokens (~120/item across 6 items; 6 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 13/100
  - Stability observed for 4 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 89/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 67% 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 6 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 7 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 60/100
  - Spec-recency check failed: implements MCP spec 2025-06-18; the latest is 2026-07-28.

## Install

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

AgentoolRank is a hosted endpoint at https://agentoolrank.com/api/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 com-agentoolrank-agent-tools 'https://agentoolrank.com/api/mcp'
```

### Cursor

```json
{
  "mcpServers": {
    "com-agentoolrank-agent-tools": {
      "url": "https://agentoolrank.com/api/mcp"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "com-agentoolrank-agent-tools": {
      "type": "http",
      "url": "https://agentoolrank.com/api/mcp"
    }
  }
}
```

### Codex

```toml
[mcp_servers.com-agentoolrank-agent-tools]
url = "https://agentoolrank.com/api/mcp"
```

### opencode

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

### OpenClaw

```bash
openclaw mcp add com-agentoolrank-agent-tools --url 'https://agentoolrank.com/api/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  com-agentoolrank-agent-tools:
    url: "https://agentoolrank.com/api/mcp"
```

### Netclaw

```json
{
  "McpServers": {
    "com-agentoolrank-agent-tools": {
      "Transport": "http",
      "Url": "https://agentoolrank.com/api/mcp"
    }
  }
}
```

### Vellum

```bash
assistant mcp add com-agentoolrank-agent-tools -t streamable-http -u 'https://agentoolrank.com/api/mcp'
```

### Other

```json
{
  "mcpServers": {
    "com-agentoolrank-agent-tools": {
      "type": "http",
      "url": "https://agentoolrank.com/api/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.

### 2026-10-04 (score 64, 0)

- [security] The server rewrote its instructions, which are the text every model session reads
- [security] Tool “recommend_directories” rewrote its description, which is the text the model reads
- [functional regression] Schema quality: pass → fail

### 2026-10-03 (score 64, 0)

- [security] The server rewrote its instructions, which are the text every model session reads
- [functional regression] Schema quality: 97 → 113
- [functional] New tool “recommend_directories”

### 2026-10-02 (score 64, +1)

- [security] Tool “submit_tool” rewrote its description, which is the text the model reads

### 2026-10-01 (score 63, 0)

- [functional improvement] Stability: unverified → 0.03

### 2026-09-30 (score 63)

First indexed and scored.

## MCP tools (6)

### `search_tools` (~94 tokens)

Search open-source AI agent tools (frameworks, coding agents, memory, RAG, observability, MCP servers...) ranked by GitHub activity. Returns stars, 30-day star growth, capabilities and alternatives.

Input parameters:

- `limit` (number): Max results (1-20, default 10)
- `query` (string, required): What you need, e.g. 'multi-agent framework in TypeScript' or 'RAG'

### `get_tool` (~40 tokens)

Get details for one tool by slug (from search_tools): GitHub stats, capabilities, best-for, limitations, alternatives.

Input parameters:

- `slug` (string, required)

### `get_alternatives` (~36 tokens)

List open-source alternatives to a tool, with GitHub stats for each, to compare options.

Input parameters:

- `slug` (string, required)

### `submit_tool` (~228 tokens)

List an AI agent tool (framework, coding agent, MCP server, memory/RAG, evals, browser agent...) on AgentoolRank for free. The free listing is queued; the response lists every paid option (price, days to go live, checkout_url for your human to pay) and recommends the cheapest one that fits max_budget_usd / deadline_days. Returns submission_id + status_token for get_submission_status, and message_for_human: a summary to forward to your human.

Input parameters:

- `deadline_days` (number): Optional: must be live within this many days
- `email` (string, required): Maker's email, used only to say when the listing is live
- `github_url` (string): https://github.com/owner/repo if open source
- `max_budget_usd` (number): Optional: the most your human will pay
- `name` (string, required)
- `tagline` (string, required): One sentence, max 160 chars
- `url` (string, required): Product website (https://...)
- `want_featured` (boolean): Optional: wants homepage placement

### `get_submission_status` (~44 tokens)

Check review status of a submission (pending/approved/rejected, queue position, listing URL).

Input parameters:

- `status_token` (string, required)
- `submission_id` (number, required)

### `recommend_directories` (~183 tokens)

Which launch directories should a product be submitted to? Returns sites our own products actually went through, each tagged auto / manual (needs one human step) with free-tier conditions, measured link type, login, human-only steps, form tips and the success signal to look for, plus one checklist of the human steps. Free: top 10. With a Submit Kit key ($29 one-time): up to 30 sites for the product type plus a "don't submit" list with reasons. No automated submission, no captcha bypass, no traffic or ranking promised.

Input parameters:

- `key` (string): Submit Kit key for the full list (optional)
- `languages` (array): Directory languages to include, default ['en'] (also: zh, fr)
- `open_source` (boolean): Include directories that only list open-source projects
- `product_type` (string, required)

## Diagnostics

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

## Score history

- 2026-10-04: 64
- 2026-10-03: 64
- 2026-10-02: 64
- 2026-10-01: 63
- 2026-09-30: 63

## Common questions

### What is the AgentoolRank MCP server?

AgentoolRank is an MCP server listed in the public MCP registry as com.agentoolrank/agent-tools. Search and compare open-source AI agent tools ranked by live GitHub activity, and list new ones. This page covers its hosted endpoint (https://agentoolrank.com/api/mcp).

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

AgentoolRank scores 64 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 AgentoolRank MCP server expose?

AgentoolRank exposes 6 tools: search_tools, get_tool, get_alternatives, submit_tool, get_submission_status, recommend_directories. Their descriptions and schemas cost roughly 625 tokens of context every time the server is loaded.

### Does the AgentoolRank MCP server require authentication?

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

### Is the AgentoolRank MCP server still maintained?

AgentoolRank is still listed as active in the MCP registry. We last reached this channel on 4 October 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://agentoolrank.com/api/mcp
- Repository: https://github.com/agent-gigmole/agentoolrank-mcp
- Website: https://agentoolrank.com/agents
- Changelog RSS feed: https://verifymcp.io/servers/com-agentoolrank-agent-tools/api-mcp.xml
- Changelog JSON feed: https://verifymcp.io/servers/com-agentoolrank-agent-tools/api-mcp.json
- HTML version of this page: https://verifymcp.io/servers/com-agentoolrank-agent-tools/api-mcp