F
licenseNot graded
qualityC
maintenanceEnables Claude Code to run and manage fal.ai queue jobs, including submitting generation requests, checking status, waiting for results, canceling jobs, and downloading finished media files to disk.
-
fal.ai MCP by usefulapi
by io.usefulapi
Server Details
Run fal.ai models, poll the inference queue and read model schemas.
The last two health checks of this connector failed. If this server requires authentication, missing or expired test credentials may be the cause. A test profile lets Glama authenticate for health checks and discover tools; it is separate from your personal connections.
If you are the author, claim ownership, then add or update a test profile under Admin → Test Profile.
- Status
- Unhealthy
- Uptime
- 0.0% over the last 24 hours
- Last Tested
- Transport
- Streamable HTTP
- URL
- Repository
- m190/usefulapi-mcp
- GitHub Stars
- 0
- ChatGPT
- –
- Claude
- –
TDQS
A3.9/5.0
Scored across 7 tools
Disambiguation4/5
Most tools target distinct operations in the queue lifecycle (submit, status, result, cancel, list, schema). The main overlap is falai_run_model, which bundles submit+poll+result, potentially competing with the submit_request/status/result trio, but its description clearly delineates it as a convenience wrapper so agents can tell it apart.
Naming Consistency5/5
All seven tools follow a uniform falai_ prefix with consistent snake_case verb_noun naming (cancel_request, get_model_schema, get_request_result, get_request_status, list_models, run_model, submit_request). No mixed conventions or ambiguous verbs.
Tool Count5/5
Seven tools is well-scoped for a queue-based inference API, covering discovery, submission, polling, retrieval, cancellation, and a convenience wrapper without redundancy or bloat.
Completeness4/5
The full async queue lifecycle (submit, status, result, cancel) plus model discovery and schema inspection is covered, and run_model offers a synchronous path. Minor gaps remain, such as model metadata retrieval beyond the schema or any file/asset handling, but core workflows are complete.
Related MCP Connectors
Run DeepInfra inference, list models and read account rate limits.
Run any Relay model (image, video, audio, LLM), poll tasks, upload files and search Relay's docs.
Generate images, videos and music with model discovery, cost estimates and asynchronous results.
Run AI models, create deployments, and manage predictions via cloud API
Related MCP Servers
- AlicenseAqualityDmaintenanceEnables MCP clients to run 600+ generative AI models from fal.ai, including image, video, audio, and text, with tools for synchronous and asynchronous execution, model catalog browsing, and schema inspection.81MIT
- AlicenseNot gradedqualityDmaintenanceA FastMCP server that exposes core fal.ai model API operations, enabling model catalogue browsing, search, schema retrieval, inference, queue management, and CDN uploads through natural language.4MIT
- AlicenseAqualityDmaintenanceEnables discovery, search, generation, and management of AI models via fal.ai, allowing Claude Desktop and other MCP clients to interact with fal.ai services.12551 npmMIT
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd
Glama MCP Gateway
Add one secure layer between your agents and this server.