FFHub MCP integration for AI agents.
Connect AI agents to FFHub through 3 structured actions, including get ffmpeg task, create ffmpeg task, and list ffmpeg tasks. Review authentication, inputs…
- ACTION CONTRACTS
- 3
- AUTHENTICATION
- API key
- SOURCE STATUS
- Provider-backed
CATALOG SOURCE REVIEWED AUGUST 23, 2026 / ACTION NAMES AND SCHEMAS DERIVED FROM WORKING MACHINES PROVIDER SOURCE
CAPABILITY PROFILE
What the FFHub integration exposes
The FFHub Agent App exposes 3 provider-backed actions for media and developer tools work. Its current contract lets an authorized agent get the current status, timing, error, and output files for one ffhub ffmpeg task, create a new ffhub ffmpeg transcoding task from a full ffmpeg command or argument-only command string, and list ffhub ffmpeg tasks with optional customer, status, limit, and offset filters. These operations are called through Working Machines as typed capabilities rather than through browser navigation or copied UI steps.
A connection uses API key. Before execution, the agent can inspect the selected action, its required fields, declared scopes, and expected output contract. Provider credentials remain inside the Working Machines runtime; the calling agent receives the capability and its structured result, not the underlying secret.
For reliable operation, start with the narrowest action that satisfies the task, resolve stable provider identifiers before changing state, and validate the returned object or status after execution. Availability still depends on the connected FFHub account, granted provider permissions, workspace policy, region, plan, and upstream API behavior.
VERIFIED ACTION SAMPLE
Real FFHub capabilities.
Showing 3 of 3 actions. Risk labels are conservative signals based on operation names, not substitutes for provider documentation or runtime policy.
get_ffmpeg_taskREADGet the current status, timing, error, and output files for one FFHub FFmpeg task.
INPUTS: taskId
create_ffmpeg_taskWRITECreate a new FFHub FFmpeg transcoding task from a full FFmpeg command or argument-only command string.
INPUTS: command / webhook / withMetadata
list_ffmpeg_tasksREADList FFHub FFmpeg tasks with optional customer, status, limit, and offset filters.
INPUTS: userId / status / limit / offset
INPUT CONTRACTS
Know what the action needs before it runs.
get_ffmpeg_task
taskIdREQUIRED- FFHub task ID to retrieve.
create_ffmpeg_task
commandREQUIRED- Full FFmpeg command or argument-only command string accepted by FFHub, including remote input URLs and output file names.
webhookOPTIONAL- Optional callback URL that receives the same payload as get_ffmpeg_task.
withMetadataOPTIONAL- Whether FFHub should collect ffprobe metadata for generated output files.
list_ffmpeg_tasks
userIdOPTIONAL- Optional FFHub customer identifier.
statusOPTIONAL- FFHub task status.
limitOPTIONAL- Maximum number of tasks to return, from 1 to 100.
offsetOPTIONAL- Number of tasks to skip before reading the current page.
PROVIDER-SPECIFIC WORKFLOWS
Jobs this Agent App can support
Inspect Get Ffmpeg Task
Get the current status, timing, error, and output files for one FFHub FFmpeg task. Use this as a bounded discovery step, retain the returned identifier, and avoid expanding the read beyond the task's stated scope.
get_ffmpeg_taskControl Create Ffmpeg Task
Create a new FFHub FFmpeg transcoding task from a full FFmpeg command or argument-only command string. Resolve the target first, present material changes for confirmation, and make retries idempotent where the provider supports it.
create_ffmpeg_taskVerify with List Ffmpeg Tasks
List FFHub FFmpeg tasks with optional customer, status, limit, and offset filters. Compare the returned provider state with the intended outcome and preserve stable IDs or canonical links in the run record.
list_ffmpeg_tasksSAFETY BOUNDARY
Operate FFHub with explicit limits
- Authorize FFHub with API key and grant only the provider access required by the selected actions.
- 1 action is change-capable by name. Confirm the target identity and material parameters before allowing a write.
- Do not infer permission from catalog visibility. Workspace policy, connection identity, and upstream authorization still govern execution.
- No provider scope string is declared on the sampled actions. Verify the connected account's actual permissions in FFHub rather than assuming unrestricted access.
- After a call, inspect the structured result and execution record before reporting that the FFHub task completed successfully.
CONNECTION MODEL
API key
FFHub API key sent with the Authorization Bearer header. Create and manage it in FFHub Settings > API Keys: https://ffhub.io/settings/apikeys
Working Machines stores provider credentials behind the execution boundary. An agent can use an authorized connection identity, but catalog discovery alone does not reveal OAuth tokens, API keys, or provider secrets.
- READ SIGNALS
- 2
- WRITE SIGNALS
- 1
- HIGH IMPACT
- 0
- REVIEW SIGNALS
- 0
EVIDENCE AND AVAILABILITY
Provider reference
Action names, input fields, authentication types, and counts on this page are generated from the Working Machines provider catalog. Provider behavior, quotas, object semantics, account eligibility, and regional availability remain governed by FFHub.