AI & Machine Learning

agentdrives.com

Provides an AI-agent-accessible directory and test-drive results for software tools, enabling agents to discover, evaluate, and sign up for tools they can use.

x402 supported2 endpoints29 known toolsFirst detected October 16, 2026Last detected October 16, 2026

ENDPOINT 1

https://agentdrives.com/api/mcp

No auth detected

MCP server metadata

Name: agentdrives-directory-public
Version: 1.4.0

Capabilities

tools

Server instructions

Look up whether an AI agent can really use a software product, based on AgentDrives's real test drives. Read-only and without an account. find_tools_for_task answers "which tool can my agent use to do X?" from what our agent did in each product; search_tools shortlists products by what they do, category, minimum level (0-5) or whether an agent can pay or leave on its own; get_tool gives one product's full result (where the agent stopped, what it can and can't do, tips); list_categories gives the category ids and the best level in each.

Known tools 4

find_tools_for_task

Which software can your agent use for a job, from AgentDrives's test drives: say the task in plain words (e.

Inferred read-only

search_tools

Find software an AI agent can really use, from AgentDrives's directory of products test-driven by an AI agent: use it before you pick a tool for a task or ask a person to sign up for one.

Inferred read-only

get_tool

One product's full test-drive result, for when you need to know exactly 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 networ

Potential side effects

list_categories

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).

Inferred read-only

CONNECT WITH APPROVAL

Client installation

Review this server and its permissions before adding it. Secret placeholders must be set locally.

Codex

~/.codex/config.toml

[mcp_servers.agentdrives-directory-public]
url = "https://agentdrives.com/api/mcp"
enabled = true

Claude Code

.mcp.json

{
  "mcpServers": {
    "agentdrives-directory-public": {
      "type": "http",
      "url": "https://agentdrives.com/api/mcp"
    }
  }
}

Claude Desktop

Settings → Connectors → Add custom connector

Name: agentdrives-directory-public
Remote MCP URL: https://agentdrives.com/api/mcp

Add this remote URL as a custom connector in Claude Desktop. Availability depends on the user plan and workspace policy.

Cursor

.cursor/mcp.json

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

Visual Studio Code

.vscode/mcp.json

Add to Visual Studio Code

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

Generic MCP

Client-specific MCP configuration

{
  "name": "agentdrives-directory-public",
  "transport": "streamable-http",
  "url": "https://agentdrives.com/api/mcp"
}

MCP Inspector

Run the official MCP Inspector locally and enter the indexed Streamable HTTP endpoint.

ENDPOINT 2

https://agentdrives.com/mcp

No auth detected

MCP server metadata

Name: agentdrives-directory
Version: 1.4.0

Capabilities

tools

Server instructions

Look up whether an AI agent can really use a software product, based on AgentDrives's real test drives. Without a key: find_tools_for_task, search_tools, get_tool, list_categories, support_ask and sign_up (an account of your own and its key, no person needed). With an API key from https://agentdrives.com/app/keys or sign_up (as x-api-key or Authorization: Bearer): claim your product's domain, order a drive, pay for it over HTTP 402 (pay_order) and follow your orders. Paid calls with no rate limit: top_up buys credit, balance shows it.

Known tools 25

find_tools_for_task

Which software can your agent use for a job, from AgentDrives's test drives: say the task in plain words (e.

Inferred read-only

search_tools

Find software an AI agent can really use, from AgentDrives's directory of products test-driven by an AI agent: use it before you pick a tool for a task or ask a person to sign up for one.

Inferred read-only

get_tool

Potential side effects

list_categories

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).

Inferred read-only

sign_up

No key needed: an account for you, the agent, with no person, no email address and no CAPTCHA, and its API key at once (api_key, shown once: send it as the x-api-key header, here or to the HTTP API).

Potential side effects

whoami

Your account, claimed domains and orders.

Inferred read-only

claim_domain

Step 1 of 3 (claim, verify, order): add your product's domain.

Inferred read-only

send_claim_code

Step 2 (mail route): mail a 6-digit code to an address at the claimed domain.

Inferred read-only

verify_claim

Step 2 of 3: verify a claim.

Inferred read-only

drive_stop

Stop our drives of your own product (a verified claim), or let them start again: stop true or false.

Inferred read-only

followup_drive

The second drive that comes with an Audit, within 30 days of its report.

Inferred read-only

order

Step 3 of 3: order for your product (prices before tax; every detail and limit: https://agentdrives.

Inferred read-only

pay_order

How to pay a Drive (ordered as product drive) that waits for payment, as an agent, over HTTP 402: the payment URL, the price and the protocols on now (protocols; MPP: a card through a Stripe Shared Payment Token, or USDC on Tempo or Base; x402: USDC on Base).

Potential side effects

top_up

How to buy prepaid credit for paid calls: POST /api/paid/find-tools with your key then takes $0.

Potential side effects

balance

Your prepaid credit for paid calls (top_up): the balance, the calls it pays, when it expires, each top-up with its receipt, and the history (calls by day, refunds, expiry).

Inferred read-only

my_orders

Your orders and their status (requested, paid, queued, running, done, past_due when a renewal failed, cancelled), followup_available and followups_left, the upgrades open to each (to, price_cents, until), and a free check's check_state (failed: it didn't finish, order it again; late: it waits longer than usual).

Inferred read-only

withdraw_order

Withdraw an order that has not been paid yet.

Inferred read-only

pay_code

Let our agent buy your plan, on an order you placed (a Drive, an Audit, a Monthly drive or a checkout test): add or replace a one-use code, a test-mode login or a seat on our test account, until a drive has it; remove: true deletes it.

Potential side effects

pay_check

Test your checkout: Add a code and our agent buys your plan with it.

Inferred read-only

cancel_monthly

Cancel the Monthly drive: one product (order_id) or all of them.

Inferred read-only

switch_monthly

Switch the Monthly drive for one product between monthly ($29) and yearly ($290).

Inferred read-only

suggest_product

Suggest a product for our agent to drive and list (free, anyone, any product).

Inferred read-only

support_ask

Ask our support a question about AgentDrives: prices, plans, levels, the method, orders, the API and MCP.

Inferred read-only

dispute_result

Dispute the published result of your own product (an API key with a verified claim on its domain; else 403 claim_not_verified).

Inferred read-only

case_status

A support case's state: open, waiting (an answer is on its way), answered (with the answer) or closed; the next step; a dispute's re-drive (queued, running, done).

Inferred read-only

CONNECT WITH APPROVAL

Client installation

Review this server and its permissions before adding it. Secret placeholders must be set locally.

Codex

~/.codex/config.toml

[mcp_servers.agentdrives-directory]
url = "https://agentdrives.com/mcp"
enabled = true

Claude Code

.mcp.json

{
  "mcpServers": {
    "agentdrives-directory": {
      "type": "http",
      "url": "https://agentdrives.com/mcp"
    }
  }
}

Claude Desktop

Settings → Connectors → Add custom connector

Name: agentdrives-directory
Remote MCP URL: https://agentdrives.com/mcp

Add this remote URL as a custom connector in Claude Desktop. Availability depends on the user plan and workspace policy.

Cursor

.cursor/mcp.json

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

Visual Studio Code

.vscode/mcp.json

Add to Visual Studio Code

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

Generic MCP

Client-specific MCP configuration

{
  "name": "agentdrives-directory",
  "transport": "streamable-http",
  "url": "https://agentdrives.com/mcp"
}

MCP Inspector

Run the official MCP Inspector locally and enter the indexed Streamable HTTP endpoint.

TRUST AND VERIFICATION EVIDENCE

Loading Trust v2 evidence…

Checking the associated registrable domain. The BuiltWith key remains server-side.

Indexed

Evidence is source-attributed and does not guarantee that a third-party server is safe. Risk labels are conservative metadata heuristics.