Which products your agent can use for a task, ranked from our drives (the MCP tool find_tools_for_task): for each, the closest task in its capability map and what happened when our agent tried it, the agent level, whether our agent got in on its own, where it stopped, the work done, the drive date, origin (with disclosure when the owner paid) and the page. Strong matches first, then the ones our agent did, then level and work done. Or by capability instead of task (GET /api/capabilities lists them), by its id or name; the answer names it and lists every product whose latest drive has a task of it, with what our agent got there (task.result), the product's own tasks behind it (tasks) and the evidence (the page section that shows it), done first, then level. Send task or capability. 120 requests per 10 minutes per IP
Request
- Base URL: https://agentdrives.com
- URL: https://agentdrives.com/api/find-tools
- Auth: none required
Query parameters
What your agent should get done, in plain words, e.g. 'send an invoice'. Send this or capability
A capability instead of task: its id (cap_ and 8 characters, from GET /api/capabilities) or its name, e.g. 'Send a transactional email'. Words that fit several answer 400 ambiguous_capability with the list (choose)
A category id or name
true: only products our agent signed up for and got a key on its own
Agent level, the only rank: 0 Read-only (Agents can read about it, but there is nothing to use); 1 Needs a person (Agents can't get in on their own); 2 Gets in (An agent gets in on its own but does less than half the core work); 3 Does the work (An agent gets in on its own and does half the core work or more); 4 Runs on its own (An agent does the core work and can stop paying on its own); 5 Autonomous (All of that, and it pays on its own for the work)
Response
The ranked products (with capability: the capability, how many products have it, and the products)
Changes
No recorded changes to this operation across all 5 revisions of this API.