# fal.ai MCP by usefulapi (remote · falai.usefulapi.io)

Run fal.ai models, poll the inference queue and read model schemas.

- Trust score: 73/100 (medium)
- Change this week: +3
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-10-22

## Components

- remote · `falai.usefulapi.io`: 73/100 (this document), [markdown](https://verifymcp.io/servers/io-usefulapi-falai/falai.md), [page](https://verifymcp.io/servers/io-usefulapi-falai/falai)

## Channel facts

- Endpoint: `https://falai.usefulapi.io/mcp`
- Transports: `streamable-http`
- Auth: `required`
- Version: `1.16.4`

## 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 2026-10-22.

- **Endpoint Security**: 78/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - Authorisation is enforced on tool calls, advertised via RFC 9728 protected-resource metadata. Discovery is public, which costs nothing: no tool can be invoked without a token.
  - HTTPS enforcement could not be verified: the plaintext port redirected somewhere other than https, so enforcement is unproven.
  - HSTS check failed: the Strict-Transport-Security header is absent.
  - DNSSEC check failed: this domain isn't protected by DNSSEC.
  - The authorisation server offers only Dynamic Client Registration (RFC 7591), which MCP 2026-07-28 deprecated in favour of Client ID Metadata Documents.
- **Transport & Reachability**: 0/100
  - Transport check failed: declared streamable-http, but the endpoint redirected instead of responding directly.
- **Schema Quality & AI Usability**: 84/100
  - 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).
  - AI-judged instruction clarity (excellent).
  - Context-footprint check failed: tool/resource definitions use about 1040 tokens (~148/item across 7 items; 7 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 73/100
  - Stability observed for 22 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 7 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 8 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 60/100
  - Spec-recency check failed: implements MCP spec 2025-06-18; the latest is 2026-07-28.

## Install

### How do I install the fal.ai MCP by usefulapi server?

fal.ai MCP by usefulapi is a hosted endpoint at https://falai.usefulapi.io/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 io-usefulapi-falai 'https://falai.usefulapi.io/mcp'
```

### Cursor

```json
{
  "mcpServers": {
    "io-usefulapi-falai": {
      "url": "https://falai.usefulapi.io/mcp"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "io-usefulapi-falai": {
      "type": "http",
      "url": "https://falai.usefulapi.io/mcp"
    }
  }
}
```

### Codex

```toml
[mcp_servers.io-usefulapi-falai]
url = "https://falai.usefulapi.io/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "io-usefulapi-falai": {
      "type": "remote",
      "url": "https://falai.usefulapi.io/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add io-usefulapi-falai --url 'https://falai.usefulapi.io/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  io-usefulapi-falai:
    url: "https://falai.usefulapi.io/mcp"
```

### Netclaw

```json
{
  "McpServers": {
    "io-usefulapi-falai": {
      "Transport": "http",
      "Url": "https://falai.usefulapi.io/mcp"
    }
  }
}
```

### Vellum

```bash
assistant mcp add io-usefulapi-falai -t streamable-http -u 'https://falai.usefulapi.io/mcp'
```

### Other

```json
{
  "mcpServers": {
    "io-usefulapi-falai": {
      "type": "http",
      "url": "https://falai.usefulapi.io/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.

### 2026-10-22 (score 73, 0)

- [functional] Server version: 1.16.3 → 1.16.4

### 2026-10-21 (score 73, +1)

- [security] The server rewrote its instructions, which are the text every model session reads
- [functional] Server version: 1.14.0 → 1.16.3

### 2026-10-19 (score 72, +1)

No change was recorded against any check on this day. Stability & Change Management went from 60 to 63. That category is still filling its 30-day observation window: 18 days of observed history at the previous scan, 19 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-17 (score 71, +1)

No change was recorded against any check on this day. Stability & Change Management went from 53 to 57. That category is still filling its 30-day observation window: 16 days of observed history at the previous scan, 17 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-15 (score 70, +1)

No change was recorded against any check on this day. Stability & Change Management went from 47 to 50. That category is still filling its 30-day observation window: 14 days of observed history at the previous scan, 15 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-14 (score 69, +2)

- [security] The server rewrote its instructions, which are the text every model session reads
- [functional improvement] Schema quality: unverified → 100
- [functional] The server now declares the “prompts” capability
- [functional] New prompt “getting_started”
- [functional] Server version: 1.13.0 → 1.14.0

### 2026-10-12 (score 67, +1)

No change was recorded against any check on this day. Stability & Change Management went from 37 to 40. That category is still filling its 30-day observation window: 11 days of observed history at the previous scan, 12 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-10 (score 66, −13)

- [security regression] HTTPS: pass → unverified
- [security regression] Transport: pass → fail
- [security] The server rewrote its instructions, which are the text every model session reads
- [functional] Server version: 1.9.0 → 1.13.0

## MCP tools (7)

### `falai_list_models` (~84 tokens)

List models

List or search fal.ai models in the registry (paginated). fal.ai API: GET /models (query: keywords, page, total).

Input parameters:

- `keywords` (string): Optional search string to filter models by.
- `page` (integer): 1-based page number (default 1).
- `total` (integer): Page size (number of models per page).

### `falai_get_model_schema` (~94 tokens)

Get model schema

Get the OpenAPI 3 schema for a model — its input/output fields (components.schemas). Use this to learn what inputs a model accepts before submitting. fal.ai API: GET /openapi/queue/openapi.json?endpoint_id={model_id}.

Input parameters:

- `model_id` (string, required): The fal.ai model id, used raw as a path segment, e.g. 'fal-ai/flux/schnell'.

### `falai_get_request_status` (~118 tokens)

Get request status

Get the status of a queued request (IN_QUEUE | IN_PROGRESS | COMPLETED). fal.ai queue: GET {queue}/{model_id}/requests/{request_id}/status (optional logs=1).

Input parameters:

- `logs` (boolean): Include queue logs in the response (?logs=1).
- `model_id` (string, required): The fal.ai model id, used raw as a path segment, e.g. 'fal-ai/flux/schnell'.
- `request_id` (string, required): The queue request id returned when the request was submitted.

### `falai_get_request_result` (~88 tokens)

Get request result

Get the final output of a COMPLETED queued request. fal.ai queue: GET {queue}/{model_id}/requests/{request_id}.

Input parameters:

- `model_id` (string, required): The fal.ai model id, used raw as a path segment, e.g. 'fal-ai/flux/schnell'.
- `request_id` (string, required): The queue request id returned when the request was submitted.

### `falai_submit_request` (~146 tokens)

Submit request

Submit an inference request to the queue and return immediately (async — does NOT wait for completion). Returns { request_id, response_url, status_url, cancel_url, queue_position }. Consumes fal credits when the model runs. fal.ai queue: POST {queue}/{model_id} with body = the model input.

Input parameters:

- `input` (object, required): The model's input object — arbitrary params for that model, e.g. { "prompt": "a cat" }. Use falai_get_model_schema to learn the fields.
- `model_id` (string, required): The fal.ai model id, used raw as a path segment, e.g. 'fal-ai/flux/schnell'.

### `falai_run_model` (~200 tokens)

Run model (subscribe)

Convenience 'subscribe': submit a request, poll its status until COMPLETED, then return the result. Consumes fal credits. If it does not complete within the wait budget, returns a { status, request_id, status_url, note } object (NOT an error) so you can keep polling with falai_get_request_status / falai_get_request_result.

Input parameters:

- `input` (object, required): The model's input object — arbitrary params for that model, e.g. { "prompt": "a cat" }. Use falai_get_model_schema to learn the fields.
- `max_wait_seconds` (integer): Max seconds to wait for completion (default 60, capped at 300).
- `model_id` (string, required): The fal.ai model id, used raw as a path segment, e.g. 'fal-ai/flux/schnell'.
- `poll_interval_seconds` (integer): Seconds between status polls (default 3, min 1).

### `falai_cancel_request` (~107 tokens)

Cancel request

Request cancellation of a queued (not-yet-started) request. Returns 202 { status: 'CANCELLATION_REQUESTED' }. fal.ai queue: PUT {queue}/{model_id}/requests/{request_id}/cancel.

Input parameters:

- `model_id` (string, required): The fal.ai model id, used raw as a path segment, e.g. 'fal-ai/flux/schnell'.
- `request_id` (string, required): The queue request id returned when the request was submitted.

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/io-usefulapi-falai/falai#diagnostics

## Score history

- 2026-10-22: 73
- 2026-10-21: 73
- 2026-10-20: 72
- 2026-10-19: 72
- 2026-10-18: 71
- 2026-10-17: 71
- 2026-10-16: 70
- 2026-10-15: 70
- 2026-10-14: 69
- 2026-10-13: 67
- 2026-10-12: 67
- 2026-10-11: 66
- 2026-10-10: 66
- 2026-10-07: 79
- 2026-10-05: 79
- 2026-10-04: 79
- 2026-10-03: 78
- 2026-10-02: 78
- 2026-10-01: 77
- 2026-09-30: 72
- 2026-09-29: 18

## Common questions

### What is the fal.ai MCP by usefulapi server?

fal.ai MCP by usefulapi is listed in the public MCP registry as io.usefulapi/falai. Run fal.ai models, poll the inference queue and read model schemas. This page covers its hosted endpoint (https://falai.usefulapi.io/mcp).

### Is the fal.ai MCP by usefulapi server safe to use?

fal.ai MCP by usefulapi scores 73 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 fal.ai MCP by usefulapi server expose?

fal.ai MCP by usefulapi exposes 7 tools: falai_list_models, falai_get_model_schema, falai_get_request_status, falai_get_request_result, falai_submit_request, and 2 more. Their descriptions and schemas cost roughly 837 tokens of context every time the server is loaded.

### Does the fal.ai MCP by usefulapi server require authentication?

Yes. fal.ai MCP by usefulapi asked us for credentials when we connected, so you will need to authorise it in your MCP client before it can do anything.

### Is the fal.ai MCP by usefulapi server still maintained?

fal.ai MCP by usefulapi is still listed as active in the MCP registry. We last reached this channel on 22 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://falai.usefulapi.io/mcp
- Repository: https://github.com/m190/usefulapi-mcp
- Website: https://usefulapi.io/falai/
- Changelog RSS feed: https://verifymcp.io/servers/io-usefulapi-falai/falai.xml
- Changelog JSON feed: https://verifymcp.io/servers/io-usefulapi-falai/falai.json
- HTML version of this page: https://verifymcp.io/servers/io-usefulapi-falai/falai