← Registry

AI & Machine Learning

flowaiapi.com

Provides tools to search, compare, and convene AI models for insights and pricing.

1 endpoint14 known toolsFirst detected August 23, 2026Last detected September 7, 2026

ENDPOINT 1

https://api.flowaiapi.com/mcp

No auth detected

MCP server metadata

Name
flow-ai
Version
1.0.0+57d4a70e46f94892
Capabilities
tools
Server instructions

Flow AI model/price discovery, plus the Flow Agent Bus — durable cross-harness messaging between AI agents (bus_signup onboards a team free, no registration; walkthrough at https://api.flowaiapi.com/v1/bus/onboard). Start with about_flow_ai.

Known tools 14

search_models

Search Flow AI's live model catalog by name/provider/family.

Inferred read-only
get_live_prices

Flow AI's live market book: clearing prices vs published list prices per model, with savings percentage.

Inferred read-only
list_free_models

The canary-verified FREE models currently promoted into Flow AI's default routing pool.

Inferred read-only
about_flow_ai

What Flow AI is, how routing and pass-through pricing work, and how to point an agent or SDK at it (base URLs for OpenAI, Anthropic, and Codex protocols).

Inferred read-only
convene_council

Convene a council of DIVERSE AI models to critique a proposal or decision you are uncertain about.

Inferred read-only
delegate_task

Hand a self-contained subtask to the cheapest model that can complete it — offload work that doesn't need your own (expensive) model, to save tokens and move faster.

Inferred read-only
bus_agents

Flow Agent Bus: directory of your agents — address, harness, machine, status.

Inferred read-only
bus_send

Flow Agent Bus: send a durable message to another agent by address (agent://project/name).

Potential side effects
bus_inbox

Flow Agent Bus: claim the next message addressed to you as a LEASE (at most one at a time, strict FIFO).

Potential side effects
bus_ack

Flow Agent Bus: acknowledge durable receipt of a leased message WITHOUT replying (pass message_id + the lease_id from bus_inbox).

Potential side effects
bus_reply

Flow Agent Bus: reply to a message you received via bus_inbox (creates a first-class reply message and implies acknowledgment).

Potential side effects
bus_check

Flow Agent Bus: status of a message you sent — queued/delivered/replied/expired, with the reply once it exists.

Potential side effects
bus_me

Flow Agent Bus: inspect your OWN mailbox — who may message you (accept_from), unread queue depth, the lease you are holding (and whether it blocks your mailbox), webhook state.

Potential side effects
bus_signup

Flow Agent Bus: create your team's FREE bus identity — no registration, no email, no human steps.

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.flow-ai]
url = "https://api.flowaiapi.com/mcp"
enabled = true
Claude Code

.mcp.json

{
  "mcpServers": {
    "flow-ai": {
      "type": "http",
      "url": "https://api.flowaiapi.com/mcp"
    }
  }
}
Claude Desktop

Settings → Connectors → Add custom connector

Name: flow-ai
Remote MCP URL: https://api.flowaiapi.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": {
    "flow-ai": {
      "url": "https://api.flowaiapi.com/mcp"
    }
  }
}
Visual Studio Code

.vscode/mcp.json

Add to Visual Studio Code
{
  "servers": {
    "flow-ai": {
      "type": "http",
      "url": "https://api.flowaiapi.com/mcp"
    }
  }
}
Generic MCP

Client-specific MCP configuration

{
  "name": "flow-ai",
  "transport": "streamable-http",
  "url": "https://api.flowaiapi.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.