# AgentDrives (remote · agentdrives.com)

Can an AI agent use this software? Levels from real agent test drives: sign-up, keys, use, pay.

- Trust score: 67/100 (medium)
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-10-18

## Components

- remote · `agentdrives.com`: 59/100, [markdown](https://verifymcp.io/servers/com-agentdrives-directory/agentdrives.md), [page](https://verifymcp.io/servers/com-agentdrives-directory/agentdrives)
- remote · `agentdrives.com`: 67/100 (this document), [markdown](https://verifymcp.io/servers/com-agentdrives-directory/api-mcp.md), [page](https://verifymcp.io/servers/com-agentdrives-directory/api-mcp)

## Channel facts

- Endpoint: `https://agentdrives.com/api/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `1.4.0`

## 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 2026-10-18.

- **Endpoint Security**: 69/100
  - 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 check failed: the endpoint is reachable over plaintext HTTP.
  - 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**: 56/100
  - AI-judged instruction clarity (good).
  - Context-footprint check failed: tool/resource definitions use about 1743 tokens (~435/item across 4 items; 4 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 7/100
  - Stability observed for 2 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 4 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 5 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 AgentDrives MCP server?

AgentDrives is a hosted endpoint at https://agentdrives.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-agentdrives-directory 'https://agentdrives.com/api/mcp'
```

### Cursor

```json
{
  "mcpServers": {
    "com-agentdrives-directory": {
      "url": "https://agentdrives.com/api/mcp"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "com-agentdrives-directory": {
      "type": "http",
      "url": "https://agentdrives.com/api/mcp"
    }
  }
}
```

### Codex

```toml
[mcp_servers.com-agentdrives-directory]
url = "https://agentdrives.com/api/mcp"
```

### opencode

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

### OpenClaw

```bash
openclaw mcp add com-agentdrives-directory --url 'https://agentdrives.com/api/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  com-agentdrives-directory:
    url: "https://agentdrives.com/api/mcp"
```

### Netclaw

```json
{
  "McpServers": {
    "com-agentdrives-directory": {
      "Transport": "http",
      "Url": "https://agentdrives.com/api/mcp"
    }
  }
}
```

### Vellum

```bash
assistant mcp add com-agentdrives-directory -t streamable-http -u 'https://agentdrives.com/api/mcp'
```

### Other

```json
{
  "mcpServers": {
    "com-agentdrives-directory": {
      "type": "http",
      "url": "https://agentdrives.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.

### 2026-10-18 (score 67, +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.

### 2026-10-17 (score 66, 0)

- [security] Tool “search_tools” rewrote its description, which is the text the model reads
- [security] Tool “find_tools_for_task” rewrote its description, which is the text the model 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
- [functional improvement] Stability: unverified → 0.03
- [functional] Schema quality: excellent → good
- [cosmetic] “find_tools_for_task” reworded the description of “task”

### 2026-10-16 (score 66)

First indexed and scored.

## MCP tools (4)

### `find_tools_for_task` (~409 tokens)

Find tools for a task

Ranks the products AgentDrives has test-driven for a task given in plain words (e.g. 'send an invoice', 'scrape a web page', 'add a contact to a CRM'). Each result: the agent level (0-5: 0 Read-only, 1 Needs a person, 2 Gets in, 3 Does the work, 4 Runs on its own, 5 Autonomous); gets_in_alone (our agent signed up and got a key without a person); task: the closest task in the product's capability map and what happened when our agent tried it (result: done, partial, plan_gated, failed, blocked, not_tried, unknown; via: the route, e.g. api, mcp, cli, browser); match (strong or partial); can_do (up to three things our agent did there); stop (where it stopped, and why); work_done (share of the core tasks done, 0-100); the drive date; origin (editorial, or owner with disclosure "Owner-paid drive"); and the page URL. Order: strong matches first, then the ones where our agent did the task, then level, then work done. self_signup: true keeps only products our agent got into on its own. Up to limit results (default 10, at most 25); nothing matches: an empty list. get_tool returns one product in full.

Input parameters:

- `category` (string): Only this category: an id or name from list_categories (e.g. 'invoicing')
- `limit` (integer): the most results to return
- `min_level` (integer): only products at this agent level or higher (0-5)
- `self_signup` (boolean): true: only products our agent signed up for and got a key on its own
- `task` (string, required): The task in plain words, e.g. 'send an invoice' or 'create a contact'

### `search_tools` (~688 tokens)

Search the directory

Searches AgentDrives' tested products by name, domain or what they do, and returns each one's agent level and evidence. Filters: category, minimum agent level (0-5: 0 Read-only, 1 Needs a person, 2 Gets in, 3 Does the work, 4 Runs on its own, 5 Autonomous), how an agent gets in (access: pay per call, no key, a key by API, its own sign-up…), agent-native payment (proven, or the rails it offers) and whether an agent leaves on its own. Returns the level and its name, how an agent gets in (access) and the five outcomes (find, access, use, pay, leave: each yes, part, no, unreached or na), the part scores (holds_up, docs_match, setup: 0-100, null = not measured), where it stopped, the agent-native ways to pay it offers (pays_with) and whether our side proved a payment (paid), the bot check that stopped our agent on a way in (it may have got in another way) and its wall_type (network: It judged where our agent connects from and its browser, not a person. An agent that works on its own from a data center doesn't get through unless the owner lets signed agents in. How agents in a person's own browser fare isn't measured yet. challenge: It asks every visitor to prove they are human. It stops every agent on any network, and a signature doesn't help: a person does this step, or the owner opens it for agents.), who paid for the drive (origin: editorial, or owner with disclosure "Owner-paid drive") and the page URL. Sorted by level, then work done, then minutes to the first call. Up to limit results (default 25, at most 100); none match: an empty list. get_tool returns one product's full result by a slug from here; list_categories gives the category ids.

Input parameters:

- `access` (string): only products an agent gets into this way: keyless (no key needed), local (runs locally), try_first (try first, claim later), pay_per_call, key_by_api, mcp_signin, email_signup, browser_signup, by_na…
- `agent_can_buy` (boolean): only products an agent paid through an agent-native rail, proven from our side
- `agent_can_leave` (boolean): only products an agent leaves on its own
- `category` (string): A category id or name from list_categories (e.g. 'crm'); an unknown one is an error that says so
- `limit` (integer): the most results to return
- `min_level` (integer): only products at this agent level or higher (0-5)
- `pays_with` (string): only products that offer this agent-native way to pay (seen or paid), e.g. x402, mpp, l402, stripe-projects, acp, ucp, ap2, mcp-payment
- `query` (string): Name, domain or what the tool does, e.g. 'invoicing', 'stripe.com' or 'postgres'; every word must match (the same search as the directory page)

### `get_tool` (~474 tokens)

Get one tool's drive result

Returns one product's full test-drive result: how far an agent gets with it and where it stops (search_tools gives the slug; an unknown slug is an error that says how to find one): the agent level, the five outcomes (find, access, use, pay, leave, by any way in the product offers; stages: the four that decide the level, under their older keys), how an agent gets in (access, with the core tasks done on each way), the part scores, the nine checkpoints in the order of the agent's eight steps (Find: none, it is the Agent-ready setup; Learn: docs; Sign up: sign-up, verify; Get a key: key, first call; Do the work: first action; Pay: pay; Cancel: cancel; Leave: delete), what an agent can and cannot do, tips for agents, pay_options (the ways to pay it offers an agent, the payment our side proved with its transaction, and what the owner could add), the bot check that stopped our agent on a way in, even where it got in another way (agent_check: vendor, step, type network or challenge, the owner's fix), after_wall: what the agent did on its own once a person cleared one step at the door (never part of the level), works_assisted (the core tasks done once a person set up the account; null: not measured yet), robots (a robots.txt rule on the way in: named, the product's wall, or star, a rule for crawlers; held: the level is from the last drive past it), same_level_drives of drives, the level history with why each move happened (product, rules, noise), rules_date: the date of the rules the level was set by. From the rules of 12 Oct 2026 on: routes (every way in it offers and what happened on each, tried agent-native first), checkout (how far the walk to the last click went and what the checkout showed), docs (its docs read and judged) and claims (the documented ways to do the core work, tried once each: held, broken, worked but undocumented).

Input parameters:

- `slug` (string, required): The product's directory slug, from search_tools (e.g. 'attio')

### `list_categories` (~47 tokens)

List categories

Lists every category in the directory: its id (for search_tools' category filter), its name, the number of products driven in it and the best agent level in it (0-5).

## Diagnostics

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

## Score history

- 2026-10-18: 67
- 2026-10-17: 66
- 2026-10-16: 66

## Common questions

### What is the AgentDrives MCP server?

AgentDrives is an MCP server listed in the public MCP registry as com.agentdrives/directory. Can an AI agent use this software? Levels from real agent test drives: sign-up, keys, use, pay. This page covers its hosted endpoint (https://agentdrives.com/api/mcp).

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

AgentDrives scores 67 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 AgentDrives MCP server expose?

AgentDrives exposes 4 tools: find_tools_for_task, search_tools, get_tool, list_categories. Their descriptions and schemas cost roughly 1,618 tokens of context every time the server is loaded.

### Does the AgentDrives MCP server require authentication?

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

### Is the AgentDrives MCP server still maintained?

AgentDrives is still listed as active in the MCP registry. We last reached this channel on 18 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://agentdrives.com/api/mcp
- Website: https://agentdrives.com/data
- Changelog RSS feed: https://verifymcp.io/servers/com-agentdrives-directory/api-mcp.xml
- Changelog JSON feed: https://verifymcp.io/servers/com-agentdrives-directory/api-mcp.json
- HTML version of this page: https://verifymcp.io/servers/com-agentdrives-directory/api-mcp