API Tools

whatcanido.dev

Enables searching for providers and invoking their actions through a unified API.

1 endpoint10 known toolsFirst detected July 25, 2026Last detected July 25, 2026

ENDPOINT 1

https://whatcanido.dev/api/mcp

No auth detected

MCP server metadata

Name: whatcanido
Version: 0.1.0

Capabilities

tools

Server instructions

Whatcanido action grammar gateway. Suggested call order: (1) find_providers(action_type, query?) to locate providers; (2) get_provider_actions(provider_id) to read the canonical input schema; (3) submit_action(provider_id, action_type, inputs) to perform the action; (4) get_action_status(request_id) to check progress. Provider IDs are '<product>:<slug>'; request IDs are '<product>:<kind>:<id>'. Missing required fields come back in 'missing_fields' so you can ask the user without retrying blindly.

Known tools 10

find_providers

Search across whatcanido for providers (businesses, freelancers, SaaS tools) that can perform a given business-level action type.

Inferred read-only

get_provider_actions

Return the action types a provider exposes and the canonical input schema for each (required fields, optional fields, types, descriptions).

Inferred read-only

submit_action

Invoke an action on a specific provider.

Inferred read-only

get_action_status

Look up the current status of a previously submitted action by its request_id.

Inferred read-only

discover_capabilities

Search the whatcanido capability registry by free-text intent.

Inferred read-only

get_capability_spec

Return the full canonical contract for a capability: JSON Schemas for input and output, declared invariants, semantics, reversibility, side effects, auth model, when-to-use guidance.

Inferred read-only

plan_capabilities

Given a user intent, return a typed plan: an ordered list of capability calls that together accomplish the goal, with the highest-reputation provider per step.

Inferred read-only

reverse_search_capabilities

Given a JSON payload (something you found in user context, a webhook body, an export, a clipboard paste), return the capabilities whose input or output schema overlaps with the payload's shape.

Inferred read-only

list_available_capabilities

Return a compact roster of every capability with at least one enabled provider, grouped by category, with the best current conformance per capability.

Inferred read-only

invoke_capability

Execute a capability call against a chosen provider with typed inputs.

Potential side effects

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.whatcanido]
url = "https://whatcanido.dev/api/mcp"
enabled = true

Claude Code

.mcp.json

{
  "mcpServers": {
    "whatcanido": {
      "type": "http",
      "url": "https://whatcanido.dev/api/mcp"
    }
  }
}

Claude Desktop

Settings → Connectors → Add custom connector

Name: whatcanido
Remote MCP URL: https://whatcanido.dev/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": {
    "whatcanido": {
      "url": "https://whatcanido.dev/api/mcp"
    }
  }
}

Visual Studio Code

.vscode/mcp.json

Add to Visual Studio Code

{
  "servers": {
    "whatcanido": {
      "type": "http",
      "url": "https://whatcanido.dev/api/mcp"
    }
  }
}

Generic MCP

Client-specific MCP configuration

{
  "name": "whatcanido",
  "transport": "streamable-http",
  "url": "https://whatcanido.dev/api/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.