APIXO
Server Details
Discover AI models and their input schemas, generate images, videos, music and speech, create or clone voices, and check generation status through APIXO. Public tool discovery is available without sign-in. Account-specific and generation operations require authentication; generation uses APIXO credits. Website: https://apixo.ai
- Status
- Healthy
- Uptime
- 100.0% over the last 24 hours
- Last Tested
- Transport
- Streamable HTTP · MCP 2025-11-25
- URL
- ChatGPT
- –
- Claude
- –
TDQS
Scored across 14 tools
All seven generation tools (generate_task, generate_image, generate_video, generate_music, generate_speech, clone_voice, design_voice) carry word-for-word identical descriptions, so the only signal separating them is the name. generate_task in particular is a generic catch-all that overlaps every media-specific shortcut, and clone_voice vs design_voice are indistinguishable from the text alone.
Every tool follows a strict snake_case verb_noun pattern (generate_image, get_model_schema, list_models, upload_reference), with verbs drawn from a small consistent set: generate/get/list/clone/design/upload. No style mixing.
14 tools is a sensible scope for a media-generation platform covering discovery, schema, pricing, upload, generation, and status. The count is slightly inflated by having both a generic generate_task and five type-specific shortcuts that do the same job with the same description.
Core lifecycle is covered (discover models, read schema, upload, generate, poll status), but sessions and versioning are referenced in descriptions with no tools to list, resume, or manage them. There is also no task listing/history, cancellation, or voice-library browsing, leaving agents at dead ends for anything beyond create-and-poll.
Available Tools
14 toolsclone_voiceclone voiceCDestructiveInspect
Create one independent billable Studio task. For user-attached or local media in a host with native APIXO attachments, use reference_files with file_bindings. ChatGPT and native Codex connectors use this route. Pass the host-provided attachment or the absolute local path when the connector accepts paths. If the native attachment fails, ask the user to reattach it or supply a usable URL. Do not rehost a failed native attachment without an explicit user request. Put existing media URLs supplied or selected by the user in input. Choose the attachment route by capability. Use reference_files when the client provides native APIXO attachments, including ChatGPT and compatible Codex connectors. Otherwise, for user-selected files accessible to the client, automatically use upload_reference and the APIXO uploader when the client can run Node.js 22+ and reach APIXO. This applies to Claude Code, Cursor, Grok Bot, WorkBuddy, and other clients that meet those conditions. A request to use the selected files in APIXO is sufficient to start the upload; honor the client's execution permissions. Read the model schema and identify each destination URL field before uploading. Submit only confirmed URLs in the user's order. If file access or execution is unavailable, explain the limitation and ask for a usable direct link. Keep upload grants out of replies and show reference URLs only on request. Read list_models.defaults for the default model of this tool, then get_model_schema for the complete schema. generate_task requires model; shortcuts may omit it. Explicit model selects that public task model. Set the documented mode in input; no mode, model fields, defaults or voice choices are inferred or injected. Flat model parameters and legacy reference_images/reference_audio are not accepted. Backend validation is authoritative. Use session_title for a new topic, session_id to continue, and session_id plus base_run_id for a version. Preserve returned model/task_id/session_id/run_id/media_type. Never automatically resubmit or change model/session after rejection or an unconfirmed submission. In user-facing replies, omit technical identifiers by default, including user/profile IDs, task_id, session_id, run_id, base_run_id, voice_id, and file IDs. Retain the exact returned identifiers for tool arguments, task queries, session continuation, version appends, and voice reuse; never redact, regenerate, or guess these references. Show an identifier only when the user explicitly asks for it or a specific troubleshooting step requires that exact value, and show only the reference needed. Prefer plain-language status, model names, result previews/download links, and Studio links built from the returned session_id. This changes reply presentation only; tool result fields remain available for the workflow.
Inputs: input (required), model, session_id, base_run_id, +3 more. Returns: error, model, state, run_id, +10 more
design_voicedesign voiceBDestructiveInspect
Create one independent billable Studio task. For user-attached or local media in a host with native APIXO attachments, use reference_files with file_bindings. ChatGPT and native Codex connectors use this route. Pass the host-provided attachment or the absolute local path when the connector accepts paths. If the native attachment fails, ask the user to reattach it or supply a usable URL. Do not rehost a failed native attachment without an explicit user request. Put existing media URLs supplied or selected by the user in input. Choose the attachment route by capability. Use reference_files when the client provides native APIXO attachments, including ChatGPT and compatible Codex connectors. Otherwise, for user-selected files accessible to the client, automatically use upload_reference and the APIXO uploader when the client can run Node.js 22+ and reach APIXO. This applies to Claude Code, Cursor, Grok Bot, WorkBuddy, and other clients that meet those conditions. A request to use the selected files in APIXO is sufficient to start the upload; honor the client's execution permissions. Read the model schema and identify each destination URL field before uploading. Submit only confirmed URLs in the user's order. If file access or execution is unavailable, explain the limitation and ask for a usable direct link. Keep upload grants out of replies and show reference URLs only on request. Read list_models.defaults for the default model of this tool, then get_model_schema for the complete schema. generate_task requires model; shortcuts may omit it. Explicit model selects that public task model. Set the documented mode in input; no mode, model fields, defaults or voice choices are inferred or injected. Flat model parameters and legacy reference_images/reference_audio are not accepted. Backend validation is authoritative. Use session_title for a new topic, session_id to continue, and session_id plus base_run_id for a version. Preserve returned model/task_id/session_id/run_id/media_type. Never automatically resubmit or change model/session after rejection or an unconfirmed submission. In user-facing replies, omit technical identifiers by default, including user/profile IDs, task_id, session_id, run_id, base_run_id, voice_id, and file IDs. Retain the exact returned identifiers for tool arguments, task queries, session continuation, version appends, and voice reuse; never redact, regenerate, or guess these references. Show an identifier only when the user explicitly asks for it or a specific troubleshooting step requires that exact value, and show only the reference needed. Prefer plain-language status, model names, result previews/download links, and Studio links built from the returned session_id. This changes reply presentation only; tool result fields remain available for the workflow.
Inputs: input (required), model, session_id, base_run_id, +3 more. Returns: error, model, state, run_id, +10 more
generate_imagegenerate imageBDestructiveInspect
Create one independent billable Studio task. For user-attached or local media in a host with native APIXO attachments, use reference_files with file_bindings. ChatGPT and native Codex connectors use this route. Pass the host-provided attachment or the absolute local path when the connector accepts paths. If the native attachment fails, ask the user to reattach it or supply a usable URL. Do not rehost a failed native attachment without an explicit user request. Put existing media URLs supplied or selected by the user in input. Choose the attachment route by capability. Use reference_files when the client provides native APIXO attachments, including ChatGPT and compatible Codex connectors. Otherwise, for user-selected files accessible to the client, automatically use upload_reference and the APIXO uploader when the client can run Node.js 22+ and reach APIXO. This applies to Claude Code, Cursor, Grok Bot, WorkBuddy, and other clients that meet those conditions. A request to use the selected files in APIXO is sufficient to start the upload; honor the client's execution permissions. Read the model schema and identify each destination URL field before uploading. Submit only confirmed URLs in the user's order. If file access or execution is unavailable, explain the limitation and ask for a usable direct link. Keep upload grants out of replies and show reference URLs only on request. Read list_models.defaults for the default model of this tool, then get_model_schema for the complete schema. generate_task requires model; shortcuts may omit it. Explicit model selects that public task model. Set the documented mode in input; no mode, model fields, defaults or voice choices are inferred or injected. Flat model parameters and legacy reference_images/reference_audio are not accepted. Backend validation is authoritative. Use session_title for a new topic, session_id to continue, and session_id plus base_run_id for a version. Preserve returned model/task_id/session_id/run_id/media_type. Never automatically resubmit or change model/session after rejection or an unconfirmed submission. In user-facing replies, omit technical identifiers by default, including user/profile IDs, task_id, session_id, run_id, base_run_id, voice_id, and file IDs. Retain the exact returned identifiers for tool arguments, task queries, session continuation, version appends, and voice reuse; never redact, regenerate, or guess these references. Show an identifier only when the user explicitly asks for it or a specific troubleshooting step requires that exact value, and show only the reference needed. Prefer plain-language status, model names, result previews/download links, and Studio links built from the returned session_id. This changes reply presentation only; tool result fields remain available for the workflow.
Inputs: input (required), model, session_id, base_run_id, +3 more. Returns: error, model, state, run_id, +10 more
generate_musicgenerate musicBDestructiveInspect
Create one independent billable Studio task. For user-attached or local media in a host with native APIXO attachments, use reference_files with file_bindings. ChatGPT and native Codex connectors use this route. Pass the host-provided attachment or the absolute local path when the connector accepts paths. If the native attachment fails, ask the user to reattach it or supply a usable URL. Do not rehost a failed native attachment without an explicit user request. Put existing media URLs supplied or selected by the user in input. Choose the attachment route by capability. Use reference_files when the client provides native APIXO attachments, including ChatGPT and compatible Codex connectors. Otherwise, for user-selected files accessible to the client, automatically use upload_reference and the APIXO uploader when the client can run Node.js 22+ and reach APIXO. This applies to Claude Code, Cursor, Grok Bot, WorkBuddy, and other clients that meet those conditions. A request to use the selected files in APIXO is sufficient to start the upload; honor the client's execution permissions. Read the model schema and identify each destination URL field before uploading. Submit only confirmed URLs in the user's order. If file access or execution is unavailable, explain the limitation and ask for a usable direct link. Keep upload grants out of replies and show reference URLs only on request. Read list_models.defaults for the default model of this tool, then get_model_schema for the complete schema. generate_task requires model; shortcuts may omit it. Explicit model selects that public task model. Set the documented mode in input; no mode, model fields, defaults or voice choices are inferred or injected. Flat model parameters and legacy reference_images/reference_audio are not accepted. Backend validation is authoritative. Use session_title for a new topic, session_id to continue, and session_id plus base_run_id for a version. Preserve returned model/task_id/session_id/run_id/media_type. Never automatically resubmit or change model/session after rejection or an unconfirmed submission. In user-facing replies, omit technical identifiers by default, including user/profile IDs, task_id, session_id, run_id, base_run_id, voice_id, and file IDs. Retain the exact returned identifiers for tool arguments, task queries, session continuation, version appends, and voice reuse; never redact, regenerate, or guess these references. Show an identifier only when the user explicitly asks for it or a specific troubleshooting step requires that exact value, and show only the reference needed. Prefer plain-language status, model names, result previews/download links, and Studio links built from the returned session_id. This changes reply presentation only; tool result fields remain available for the workflow.
Inputs: input (required), model, session_id, base_run_id, +3 more. Returns: error, model, state, run_id, +10 more
generate_speechgenerate speechADestructiveInspect
Create one independent billable Studio task. For user-attached or local media in a host with native APIXO attachments, use reference_files with file_bindings. ChatGPT and native Codex connectors use this route. Pass the host-provided attachment or the absolute local path when the connector accepts paths. If the native attachment fails, ask the user to reattach it or supply a usable URL. Do not rehost a failed native attachment without an explicit user request. Put existing media URLs supplied or selected by the user in input. Choose the attachment route by capability. Use reference_files when the client provides native APIXO attachments, including ChatGPT and compatible Codex connectors. Otherwise, for user-selected files accessible to the client, automatically use upload_reference and the APIXO uploader when the client can run Node.js 22+ and reach APIXO. This applies to Claude Code, Cursor, Grok Bot, WorkBuddy, and other clients that meet those conditions. A request to use the selected files in APIXO is sufficient to start the upload; honor the client's execution permissions. Read the model schema and identify each destination URL field before uploading. Submit only confirmed URLs in the user's order. If file access or execution is unavailable, explain the limitation and ask for a usable direct link. Keep upload grants out of replies and show reference URLs only on request. Read list_models.defaults for the default model of this tool, then get_model_schema for the complete schema. generate_task requires model; shortcuts may omit it. Explicit model selects that public task model. Set the documented mode in input; no mode, model fields, defaults or voice choices are inferred or injected. Flat model parameters and legacy reference_images/reference_audio are not accepted. Backend validation is authoritative. Use session_title for a new topic, session_id to continue, and session_id plus base_run_id for a version. Preserve returned model/task_id/session_id/run_id/media_type. Never automatically resubmit or change model/session after rejection or an unconfirmed submission. In user-facing replies, omit technical identifiers by default, including user/profile IDs, task_id, session_id, run_id, base_run_id, voice_id, and file IDs. Retain the exact returned identifiers for tool arguments, task queries, session continuation, version appends, and voice reuse; never redact, regenerate, or guess these references. Show an identifier only when the user explicitly asks for it or a specific troubleshooting step requires that exact value, and show only the reference needed. Prefer plain-language status, model names, result previews/download links, and Studio links built from the returned session_id. This changes reply presentation only; tool result fields remain available for the workflow.
Inputs: input (required), model, session_id, base_run_id, +3 more. Returns: error, model, state, run_id, +10 more
generate_taskgenerate taskADestructiveInspect
Create one independent billable Studio task. For user-attached or local media in a host with native APIXO attachments, use reference_files with file_bindings. ChatGPT and native Codex connectors use this route. Pass the host-provided attachment or the absolute local path when the connector accepts paths. If the native attachment fails, ask the user to reattach it or supply a usable URL. Do not rehost a failed native attachment without an explicit user request. Put existing media URLs supplied or selected by the user in input. Choose the attachment route by capability. Use reference_files when the client provides native APIXO attachments, including ChatGPT and compatible Codex connectors. Otherwise, for user-selected files accessible to the client, automatically use upload_reference and the APIXO uploader when the client can run Node.js 22+ and reach APIXO. This applies to Claude Code, Cursor, Grok Bot, WorkBuddy, and other clients that meet those conditions. A request to use the selected files in APIXO is sufficient to start the upload; honor the client's execution permissions. Read the model schema and identify each destination URL field before uploading. Submit only confirmed URLs in the user's order. If file access or execution is unavailable, explain the limitation and ask for a usable direct link. Keep upload grants out of replies and show reference URLs only on request. Read list_models.defaults for the default model of this tool, then get_model_schema for the complete schema. generate_task requires model; shortcuts may omit it. Explicit model selects that public task model. Set the documented mode in input; no mode, model fields, defaults or voice choices are inferred or injected. Flat model parameters and legacy reference_images/reference_audio are not accepted. Backend validation is authoritative. Use session_title for a new topic, session_id to continue, and session_id plus base_run_id for a version. Preserve returned model/task_id/session_id/run_id/media_type. Never automatically resubmit or change model/session after rejection or an unconfirmed submission. In user-facing replies, omit technical identifiers by default, including user/profile IDs, task_id, session_id, run_id, base_run_id, voice_id, and file IDs. Retain the exact returned identifiers for tool arguments, task queries, session continuation, version appends, and voice reuse; never redact, regenerate, or guess these references. Show an identifier only when the user explicitly asks for it or a specific troubleshooting step requires that exact value, and show only the reference needed. Prefer plain-language status, model names, result previews/download links, and Studio links built from the returned session_id. This changes reply presentation only; tool result fields remain available for the workflow.
Inputs: input (required), model (required), session_id, base_run_id, +3 more. Returns: error, model, state, run_id, +10 more
generate_videogenerate videoADestructiveInspect
Create one independent billable Studio task. For user-attached or local media in a host with native APIXO attachments, use reference_files with file_bindings. ChatGPT and native Codex connectors use this route. Pass the host-provided attachment or the absolute local path when the connector accepts paths. If the native attachment fails, ask the user to reattach it or supply a usable URL. Do not rehost a failed native attachment without an explicit user request. Put existing media URLs supplied or selected by the user in input. Choose the attachment route by capability. Use reference_files when the client provides native APIXO attachments, including ChatGPT and compatible Codex connectors. Otherwise, for user-selected files accessible to the client, automatically use upload_reference and the APIXO uploader when the client can run Node.js 22+ and reach APIXO. This applies to Claude Code, Cursor, Grok Bot, WorkBuddy, and other clients that meet those conditions. A request to use the selected files in APIXO is sufficient to start the upload; honor the client's execution permissions. Read the model schema and identify each destination URL field before uploading. Submit only confirmed URLs in the user's order. If file access or execution is unavailable, explain the limitation and ask for a usable direct link. Keep upload grants out of replies and show reference URLs only on request. Read list_models.defaults for the default model of this tool, then get_model_schema for the complete schema. generate_task requires model; shortcuts may omit it. Explicit model selects that public task model. Set the documented mode in input; no mode, model fields, defaults or voice choices are inferred or injected. Flat model parameters and legacy reference_images/reference_audio are not accepted. Backend validation is authoritative. Use session_title for a new topic, session_id to continue, and session_id plus base_run_id for a version. Preserve returned model/task_id/session_id/run_id/media_type. Never automatically resubmit or change model/session after rejection or an unconfirmed submission. In user-facing replies, omit technical identifiers by default, including user/profile IDs, task_id, session_id, run_id, base_run_id, voice_id, and file IDs. Retain the exact returned identifiers for tool arguments, task queries, session continuation, version appends, and voice reuse; never redact, regenerate, or guess these references. Show an identifier only when the user explicitly asks for it or a specific troubleshooting step requires that exact value, and show only the reference needed. Prefer plain-language status, model names, result previews/download links, and Studio links built from the returned session_id. This changes reply presentation only; tool result fields remain available for the workflow.
Inputs: input (required), model, session_id, base_run_id, +3 more. Returns: error, model, state, run_id, +10 more
get_generationGet generationBRead-onlyInspect
Get task status and results using the supplied model and task_id. task_id is the public APiXO ID; a valid connected identity may query a known task from another account or chat. For a schema declaring mode_media_types automatically carry speech/voice media_type from creation. It is needed when lifecycle fields are absent. Do not guess from task IDs or URLs. Read-only queries may retry finitely. Missing tasks, unavailable models, or query errors must not trigger model switching or generation resubmission. Missing session/Run references, progress, and completion times are not inferred. In user-facing replies, omit technical identifiers by default, including user/profile IDs, task_id, session_id, run_id, base_run_id, voice_id, and file IDs. Retain the exact returned identifiers for tool arguments, task queries, session continuation, version appends, and voice reuse; never redact, regenerate, or guess these references. Show an identifier only when the user explicitly asks for it or a specific troubleshooting step requires that exact value, and show only the reference needed. Prefer plain-language status, model names, result previews/download links, and Studio links built from the returned session_id. This changes reply presentation only; tool result fields remain available for the workflow.
Inputs: model (required), task_id (required), media_type. Returns: error, model, state, run_id, +10 more
get_integration_guideGet the APIXO project integration guideARead-onlyIdempotentInspect
Read the REST generation flow, the verified local project setup command, and the API Keys dashboard link. Free public guidance for coding agents. This tool does not create, list, reveal, or modify keys.
Inputs: no named parameters.
get_model_pricingGet APIXO model pricesARead-onlyIdempotentInspect
Read prices for the connected APIXO account. Pass a canonical public model ID, or omit model to read all published, currently available models, including LLM prices. Returns specifications, base and final unit prices, billing units and the applied discount type. Read-only and free; any valid MCP login is sufficient. Prices are reference unit rates, not a generation quote. A task-model fixed unit price already includes the applicable account pricing; never apply a discount again. LLM rates follow the applicable token-billing discounts. PER_1M_TOKENS means per million tokens. Some models have multiple billable components or quantity limits; preserve the specification and billing unit. Pricing does not establish that this plugin can generate with a model; use list_models/get_model_schema for execution support.
Inputs: model. Returns: prices
get_model_schemaGet APIXO AI model input schemaARead-onlyIdempotentInspect
Read the complete published task model schema by canonical ID or exact slug. The schema field preserves all descriptions, examples, nested structures, constraints and AI guidance without filtering or normalization. APiXO uses custom request_schema.input.properties arrays, not standard JSON Schema. Follow schema for model parameters; the backend validates them. execution only describes transport/result adaptation and explicit attachment fields, not field or mode permissions. Result codecs and attachment paths come from schema.mcp, never model ID eligibility lists. New result formats require a supported decoder. Free, no account needed.
Inputs: model (required). Returns: model, format, schema, execution, +3 more
get_profileGet APIXO profileARead-onlyInspect
Return the APIXO profile connected to this OAuth session. Normally summarize the connected account using its display name; include its email only when relevant to the user's request. Do not print the profile ID by default. In user-facing replies, omit technical identifiers by default, including user/profile IDs, task_id, session_id, run_id, base_run_id, voice_id, and file IDs. Retain the exact returned identifiers for tool arguments, task queries, session continuation, version appends, and voice reuse; never redact, regenerate, or guess these references. Show an identifier only when the user explicitly asks for it or a specific troubleshooting step requires that exact value, and show only the reference needed. Prefer plain-language status, model names, result previews/download links, and Studio links built from the returned session_id. This changes reply presentation only; tool result fields remain available for the workflow.
Inputs: no named parameters. Returns: id, name, email
list_modelsList APIXO AI modelsARead-onlyIdempotentInspect
Read the current public task_api index and its default tool-to-model bindings. No model defaults are built into the plugin. LLM gateways are excluded. Modes and attachment_fields/result_codec load on schema lookup. Candidate eligibility does not prove successful real generation. Free public discovery; unavailable upstream returns an error.
Inputs: category, media_type. Returns: models, defaults
upload_referenceAuthorize a local reference uploadAIdempotentInspect
Get a free, short-lived upload grant for one local file using the existing APIXO MCP login. Choose the attachment route by capability. Use reference_files when the client provides native APIXO attachments, including ChatGPT and compatible Codex connectors. Otherwise, for user-selected files accessible to the client, automatically use upload_reference and the APIXO uploader when the client can run Node.js 22+ and reach APIXO. This applies to Claude Code, Cursor, Grok Bot, WorkBuddy, and other clients that meet those conditions. A request to use the selected files in APIXO is sufficient to start the upload; honor the client's execution permissions. Read the model schema and identify each destination URL field before uploading. Submit only confirmed URLs in the user's order. If file access or execution is unavailable, explain the limitation and ask for a usable direct link. Keep upload grants out of replies and show reference URLs only on request. Fetch the APIXO uploader from https://mcp.apixo.ai/tools/apixo-upload-reference.v1.mjs and save it locally as apixo-upload-reference.v1.mjs. Run node apixo-upload-reference.v1.mjs inspect with Node.js 22 or later to get the four tool arguments without sending the file. Pass the returned upload_id and grant as JSON on standard input to node apixo-upload-reference.v1.mjs upload . Keep the grant out of user-facing replies and the uploader's command-line arguments. Use the helper's confirmed url for generation. Upload links are public until temporary storage cleanup. If any required upload fails, stop before paid generation and report the issue.
Inputs: file_name (required), request_id (required), size_bytes (required), content_type (required). Returns: grant, upload_id, helper_url, upload_url, +1 more
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Related MCP Servers
- AlicenseNot gradedqualityCmaintenanceRemote MCP server that lets AI assistants read tracked competitive intelligence — competitor news, reviews, website changes, social posts and ads — and act on it by managing projects, competitors, battle cards, reports and canvases. Every answer carries a source and a date, and write actions only publish when explicitly shared.MIT
- AlicenseCqualityCmaintenanceCompetitor Monitor AI - MCP server providing AI-powered tools and automation by MEOK AI Labs112 npm37 PyPIMIT
- AlicenseAqualityDmaintenanceEnables brand visibility monitoring across major AI platforms like ChatGPT, Claude, Gemini, and Perplexity. It allows users to track visibility scores, analyze competitor data, and receive actionable insights to improve AI-generated brand recommendations.1611 npm1MIT

industrylens-mcpofficial
AlicenseNot gradedqualityCmaintenanceBrowse IndustryLens's published competitive-intelligence reports and head-to-head competitor comparisons from any AI agent — real, source-backed data.MIT
Glama MCP Gateway
Add one secure layer between your agents and this server.