OOMOL Fusion API MCP integration for AI agents.
Connect AI agents to OOMOL Fusion API through 87 structured actions, including jina reader read, file upload abort multipart upload, fal remove background re…
- ACTION CONTRACTS
- 87
- 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 OOMOL Fusion API integration exposes
The OOMOL Fusion API Agent App exposes 87 provider-backed actions for ai and developer tools work. Its current contract lets an authorized agent read and extract url content, abort multipart upload, and image with background removed. 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 OOMOL Fusion API account, granted provider permissions, workspace policy, region, plan, and upstream API behavior.
VERIFIED ACTION SAMPLE
Real OOMOL Fusion API capabilities.
Showing 12 of 87 actions. Risk labels are conservative signals based on operation names, not substitutes for provider documentation or runtime policy.
jina_reader_readREADRead and extract URL content
INPUTS: URL / format / engine / jsonResponse / timeout
file_upload_abort_multipart_uploadWRITEAbort multipart upload
INPUTS: uploadID / key
fal_remove_background_resultHIGH IMPACTImage with background removed
INPUTS: sessionID
cosyvoice_tts_generateREVIEWGenerate speech audio with CosyVoice TTS.
INPUTS: model / text / voice / format / sampleRate
cphone_nano_banana_resultREVIEWGet cphone-nano-banana task result
INPUTS: sessionID
cphone_nano_banana_stateREVIEWGet cphone-nano-banana task state
INPUTS: sessionID
cphone_nano_banana_submitREVIEWEdit images with Nano Banana
INPUTS: prompt / model / aspectRatio / imageURLs / imageSize
deepseek_ocr_recognizeREVIEWRecognize text from a single image.
INPUTS: imageURL / prompt / oomolApiKey
doubao_stt_resultREVIEWGet doubao-stt task result
INPUTS: sessionID
doubao_stt_stateREVIEWGet doubao-stt task state
INPUTS: sessionID
doubao_stt_submitREVIEWConvert speech to text with Doubao
INPUTS: audioURL / format
doubao_text_to_image_seedream_generateREVIEWGenerate images from text with Doubao Seedream
INPUTS: prompt / image / size / multiple / maxCount
INPUT CONTRACTS
Know what the action needs before it runs.
jina_reader_read
URLREQUIRED- Webpage URL whose content should be fetched
formatOPTIONAL- Output content format
engineOPTIONAL- Rendering engine type: direct for static fetching and browser for dynamic rendering
jsonResponseOPTIONAL- Whether to return the result in JSON format
timeoutOPTIONAL- Page load wait timeout in seconds
file_upload_abort_multipart_upload
uploadIDREQUIRED- Multipart upload ID to abort
keyREQUIRED- Storage path of the S3 object
fal_remove_background_result
sessionIDREQUIRED- Session ID
cosyvoice_tts_generate
modelOPTIONAL- Speech synthesis model. Different models support different voices.
textREQUIRED- Text content to synthesize into speech. SSML and LaTeX are supported.
voiceREQUIRED- Voice name, cloned voice ID, or voice design name compatible with the selected model.
formatOPTIONAL- Audio encoding format.
sampleRateOPTIONAL- Audio sample rate in Hz.
PROVIDER-SPECIFIC WORKFLOWS
Jobs this Agent App can support
Inspect Jina Reader Read
Read and extract URL content Use this as a bounded discovery step, retain the returned identifier, and avoid expanding the read beyond the task's stated scope.
jina_reader_readControl File Upload Abort Multipart Upload
Abort multipart upload Resolve the target first, present material changes for confirmation, and make retries idempotent where the provider supports it.
file_upload_abort_multipart_uploadVerify with File Upload Abort Multipart Upload
Abort multipart upload Compare the returned provider state with the intended outcome and preserve stable IDs or canonical links in the run record.
file_upload_abort_multipart_uploadSAFETY BOUNDARY
Operate OOMOL Fusion API with explicit limits
- Authorize OOMOL Fusion API with API key and grant only the provider access required by the selected actions.
- 14 actions are change-capable by name. Confirm the target identity and material parameters before allowing a write.
- Treat `fal_remove_background_result`, `fal_remove_background_state`, and `fal_remove_background_submit` as high-impact operations and require an explicit approval boundary.
- No provider scope string is declared on the sampled actions. Verify the connected account's actual permissions in OOMOL Fusion API rather than assuming unrestricted access.
- After a call, inspect the structured result and execution record before reporting that the OOMOL Fusion API task completed successfully.
CONNECTION MODEL
API key
OOMOL API key sent with the Authorization Bearer header to https://fusion-api.oomol.com. Create or manage keys from the OOMOL console API keys page.
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
- 4
- WRITE SIGNALS
- 10
- HIGH IMPACT
- 4
- REVIEW SIGNALS
- 69
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 OOMOL Fusion API.