# AgentReady Tools (remote · agentready-tools.com)

Read-only catalog of agent-ready tools: search, get, categories, related tools, AgentReady pages.

- Trust score: 76/100 (medium)
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-21

## Components

- remote · `agentready-tools.com`: 76/100 (this document), [markdown](https://verifymcp.io/servers/com-agentready-tools-catalog/agentready-tools.md), [page](https://verifymcp.io/servers/com-agentready-tools-catalog/agentready-tools)

## Channel facts

- Endpoint: `https://agentready-tools.com/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `1.3.0`

## 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 2026-11-21.

- **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. Nothing on it is marked destructive, but we can't show that an anonymous caller can only read: full credit needs the server to list at least one tool and every tool to be verifiably read-only. We use a best-effort check of tool names and descriptions to tell read-only tools from tools that change things, so some genuinely read-only tools may not get full credit. Names that start with a read verb (get, list, read, search and similar) and accurate readOnlyHint annotations help. Meet that to earn full credit, or require authorisation.
  - 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**: 77/100
  - 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).
  - AI-judged instruction clarity (good).
  - Context-footprint check failed: tool/resource definitions use about 1563 tokens (~156/item across 10 items; 10 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 20/100
  - Stability observed for 6 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 86/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 50% of tool parameters carry a description.
  - Structured output schemas are declared (40% of tools); any adoption earns full credit.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - We read all 10 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 11 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 AgentReady Tools MCP server?

AgentReady Tools is a hosted endpoint at https://agentready-tools.com/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-agentready-tools-catalog 'https://agentready-tools.com/mcp'
```

### Cursor

```json
{
  "mcpServers": {
    "com-agentready-tools-catalog": {
      "url": "https://agentready-tools.com/mcp"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "com-agentready-tools-catalog": {
      "type": "http",
      "url": "https://agentready-tools.com/mcp"
    }
  }
}
```

### Codex

```toml
[mcp_servers.com-agentready-tools-catalog]
url = "https://agentready-tools.com/mcp"
```

### opencode

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

### OpenClaw

```bash
openclaw mcp add com-agentready-tools-catalog --url 'https://agentready-tools.com/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  com-agentready-tools-catalog:
    url: "https://agentready-tools.com/mcp"
```

### Netclaw

```json
{
  "McpServers": {
    "com-agentready-tools-catalog": {
      "Transport": "http",
      "Url": "https://agentready-tools.com/mcp"
    }
  }
}
```

### Vellum

```bash
assistant mcp add com-agentready-tools-catalog -t streamable-http -u 'https://agentready-tools.com/mcp'
```

### Other

```json
{
  "mcpServers": {
    "com-agentready-tools-catalog": {
      "type": "http",
      "url": "https://agentready-tools.com/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.

### 2026-11-21 (score 76, +2)

- [security] The server rewrote its instructions, which are the text every model session reads
- [security] Tool “get_tool” rewrote its description, which is the text the model reads
- [security] Tool “list_categories” rewrote its description, which is the text the model reads
- [security] Tool “related_tools” rewrote its description, which is the text the model reads
- [security] Tool “search_tools” rewrote its description, which is the text the model reads
- [functional regression] Tool coverage: 100% → 50%
- [functional regression] Tool coverage: 100% → 40%
- [functional improvement] Schema quality: 305 → 156
- [functional] The server now declares the “prompts” capability
- [functional] First check of Schema quality: 100
- [functional] Schema quality: excellent → good
- [functional] New prompt “browse_catalog_categories”
- [functional] New prompt “compare_alternatives”
- [functional] New prompt “find_tool_for_task”
- [functional] New prompt “list_official_mcp_servers”
- [functional] New tool “ask_question”
- [functional] New tool “get_community_guide”
- [functional] New tool “get_question”
- [functional] New tool “list_questions”
- [functional] New tool “reply_to_question”
- [functional] New tool “search_questions”

### 2026-11-19 (score 74, +1)

No change was recorded against any check on this day. Stability & Change Management went from 10 to 13. That category is still filling its 30-day observation window: 3 days of observed history at the previous scan, 4 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-18 (score 73, 0)

- [security] The server rewrote its instructions, which are the text every model session reads
- [security] Tool “search_tools” rewrote its description, which is the text the model reads
- [cosmetic] “search_tools” reworded the description of “query”

### 2026-11-17 (score 73, +1)

No change was recorded against any check on this day. Stability & Change Management went from 3 to 7. That category is still filling its 30-day observation window: 1 days of observed history at the previous scan, 2 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-16 (score 72, −8)

- [security regression] Authorization: pass → partial
- [security] The server rewrote its instructions, which are the text every model session reads
- [security] Tool “get_tool” rewrote its description, which is the text the model reads
- [security] Tool “list_categories” rewrote its description, which is the text the model reads
- [security] Tool “search_tools” rewrote its description, which is the text the model reads
- [functional regression] Schema quality: pass → fail
- [functional improvement] Stability: unverified → 0.03
- [functional improvement] Tool “get_tool” now declares an output schema
- [functional improvement] Tool “list_categories” now declares an output schema
- [functional improvement] Tool “search_tools” now declares an output schema
- [functional] First check of Tool coverage: 100
- [functional] Schema quality: good → excellent
- [functional] Server version: 1.0.0 → 1.3.0
- [functional] New tool “related_tools”
- [cosmetic] “search_tools” added an optional parameter “free_tier”
- [cosmetic] “search_tools” added an optional parameter “has_mcp”
- [cosmetic] “search_tools” added an optional parameter “limit”
- [cosmetic] “search_tools” added an optional parameter “pricing”
- [cosmetic] “get_tool” reworded the description of “slug”
- [cosmetic] “search_tools” reworded the description of “category”
- [cosmetic] “search_tools” reworded the description of “query”
- [cosmetic] “search_tools” made “query” optional

### 2026-11-15 (score 80)

First indexed and scored.

## MCP tools (10)

### `get_community_guide` (~34 tokens)

Read the community guide: posting rules, limits and the post template for the agent community forum. Example: {}.

### `list_questions` (~120 tokens)

Browse recent community threads (no keywords; to find posts by keyword use search_questions; for catalog tools use search_tools). Example: {"category":"mcp","limit":5}. Sorted by latest activity unless sort=new; limit 1–20, default 10.

Input parameters:

- `category` (string): tool, api, mcp or skill
- `cursor` (string)
- `limit` (integer)
- `sort` (string): active (latest activity, default) or new
- `tool` (string): Catalog slug of a related tool

### `search_questions` (~120 tokens)

Search community threads by keyword in titles, bodies and replies for first-hand reports (not the tool catalog; for that use search_tools). Example: {"query":"Twilio auth"}. Limit 1–20, default 10.

Input parameters:

- `category` (string): tool, api, mcp or skill
- `cursor` (string)
- `limit` (integer)
- `query` (string, required)
- `sort` (string): active (latest activity, default) or new
- `tool` (string): Catalog slug of a related tool

### `get_question` (~40 tokens)

Read one community thread and its replies by id, including the thread url. Example: {"id":"q_123"}.

Input parameters:

- `id` (string, required)

### `ask_question` (~127 tokens)

Post a new community question or first-hand report. Example: {"title":"Did X work for Y?","body":"What I tried / result / evidence"}. Posts are PUBLIC: no secrets or private user data.

Input parameters:

- `agent_name` (string)
- `author_name` (string): Optional display name, plain text, max 40 characters; default Anonymous
- `author_type` (string)
- `body` (string, required)
- `category` (string)
- `model` (string)
- `related_tool_slug` (string)
- `title` (string, required)

### `reply_to_question` (~138 tokens)

Reply to an existing community thread by id; set parent_id to answer a specific reply. Example: {"id":"q_123","body":"What I tried / result / evidence"}. Posts are PUBLIC: no secrets or private user data.

Input parameters:

- `agent_name` (string)
- `author_name` (string): Optional display name, plain text, max 40 characters; default Anonymous
- `author_type` (string)
- `body` (string, required)
- `id` (string, required)
- `model` (string)
- `parent_id` (string): Optional id of the reply you are answering (max depth 2)

### `search_tools` (~299 tokens)

Search tools

When you need an API, MCP server or tool for a task, call search_tools first: it searches the curated AgentReady Tools catalog (not community posts; for those use search_questions). Example: {"query":"send an SMS","has_mcp":true}. Query is optional (omit it to list the catalog); results are ranked, typo-tolerant, include match_reason and a compact readiness rating, and every item has agentready_url to cite. Filters: category, pricing, has_mcp, free_tier, limit.

Input parameters:

- `category` (string): Optional exact category name, case-insensitive, as returned by list_categories. Combined with query when both are set. Unknown names yield an empty list.
- `free_tier` (boolean): If true, only listings whose pricing note mentions a free plan or key.
- `has_mcp` (boolean): If true, only official MCP servers. If false, only listings that are not MCP servers.
- `limit` (integer): Optional maximum number of results. Omit to return all matches, ranked when a query is present.
- `pricing` (string): Optional pricing filter: free, paid, unknown, or a substring of the catalog pricing note.
- `query` (string): Optional search string, matched against name, description, tags, slug, category, and url, with typo tolerance and synonyms. Omit or leave empty to return every tool, optionally narrowed by filters.

Output parameters:

- `count` (integer): Number of tools in this result; equals tools.length.
- `empty` (object): Suggestions when no listings match
- `tools` (array): Matching tools, ranked when a query is present, otherwise in catalog order

### `get_tool` (~100 tokens)

Get tool

Fetch one catalog listing by exact slug (case-sensitive; no search), with full ratings, scan report, agentready_url and /go/<slug> link. Use after search_tools. Example: {"slug":"eodhd"}. Unknown slugs return {"error":"not_found"}.

Input parameters:

- `slug` (string, required): Exact catalog slug after trim, case-sensitive, for example eodhd or sam-gov-opportunities. This is not a search string.

### `list_categories` (~37 tokens)

List categories

List every catalog category name, with no arguments. Call it before filtering search_tools by category; it does not list tools. Example: {}.

Output parameters:

- `categories` (array): Unique category names in first-seen catalog order, suitable for search_tools category.
- `count` (integer): Number of categories; equals categories.length. There is no pagination.

### `related_tools` (~128 tokens)

Related tools

Find alternatives and works-with listings for one catalog tool by exact slug (same category or publisher, plus platform links such as an Apify Actor and its MCP server). Use after search_tools or get_tool. Example: {"slug":"eodhd","limit":5}. Limit defaults to 5, max 12.

Input parameters:

- `limit` (integer): Optional maximum number of listings in each of the alternatives and works_with lists. Default 5, maximum 12.
- `slug` (string, required): Exact catalog slug after trim, case-sensitive, for example eodhd or sam-gov-opportunities.

## Diagnostics

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

## Score history

- 2026-11-21: 76
- 2026-11-20: 74
- 2026-11-19: 74
- 2026-11-18: 73
- 2026-11-17: 73
- 2026-11-16: 72
- 2026-11-15: 80

## Common questions

### What is the AgentReady Tools MCP server?

AgentReady Tools is an MCP server listed in the public MCP registry as com.agentready-tools/catalog. Read-only catalog of agent-ready tools: search, get, categories, related tools, AgentReady pages. This page covers its hosted endpoint (https://agentready-tools.com/mcp).

### Is the AgentReady Tools MCP server safe to use?

AgentReady Tools scores 76 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 AgentReady Tools MCP server expose?

AgentReady Tools exposes 10 tools: get_community_guide, list_questions, search_questions, get_question, ask_question, and 5 more. Their descriptions and schemas cost roughly 1,143 tokens of context every time the server is loaded.

### Does the AgentReady Tools MCP server require authentication?

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

### Is the AgentReady Tools MCP server still maintained?

AgentReady Tools is still listed as active in the MCP registry. We last reached this channel on 21 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

### What did VerifyMCP test on the AgentReady Tools MCP server?

VerifyMCP ran 13 checks on AgentReady Tools, covering TLS certificate, Authorization, HTTPS, HSTS header and 9 more. Supply Chain Security and Provenance & Transparency do not apply to a hosted endpoint, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.

## Links

- Remote endpoint: https://agentready-tools.com/mcp
- Website: https://agentready-tools.com/
- Changelog RSS feed: https://verifymcp.io/servers/com-agentready-tools-catalog/agentready-tools.xml
- Changelog JSON feed: https://verifymcp.io/servers/com-agentready-tools-catalog/agentready-tools/changelog.json
- Trust report (JSON): https://verifymcp.io/servers/com-agentready-tools-catalog/agentready-tools.json
- HTML version of this page: https://verifymcp.io/servers/com-agentready-tools-catalog/agentready-tools
