Skip to content
verify mcp Beta VerifyMCP is currently in beta. If you notice any issues, email [email protected] and we’ll put it right.

TokenLab MCP Server

NPM · @TOKENLABAI/MCP-SERVER · SCANNED AUG 3

TokenLab MCP server: 31 default and 80 full-profile tools for models, media, tasks, and files.

+45 this week 76 Trust /100
Trust breakdown (6 categories)

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. How we score →

Supply Chain Security86
  • No malware found by supply-chain analysis.Pass
  • Only part of the dependency tree could be resolved (94 of 98), so this covers what we could see, not the whole tree.Partial
  • No install/post-install scripts declared.Pass
  • Only part of the dependency tree could be resolved (94 of 98), so this covers what we could see, not the whole tree. View diagnostics → Partial
Provenance & Transparency97
  • Source repository is publicly reachable at the declared URL. View diagnostics → Pass
  • Cryptographically verified build provenance (signed, bound to hedging8563/tokenlab-mcp-server). View diagnostics → Pass
  • Clear OSI-approved license (MIT).Pass
  • Actively maintained (last published 8 days ago).Pass
  • Disclosure check failed: no security disclosure policy was found in the source repository. See how to fix → Fail
Schema Quality & AI Usability64
  • 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).Pass
  • AI-judged instruction clarity (fair).Partial
  • Context-footprint check failed: tool/resource definitions use about 7208 tokens (~212/item across 34 items; 31 tools + 3 resources), over budget; trim descriptions and params. See how to fix → Fail
  • Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management27
  • Stability observed for 8 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage89
  • 97% of tools have a non-trivial description (not blank, and not just the tool's name).Partial
  • 73% of tool parameters carry a description.Partial
Capabilities100
  • Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass
Install

Add this component to your MCP client. Where a client-specific snippet is available, pick your client below and copy it straight into your config; otherwise use the connection detail shown.

npm · @tokenlabai/mcp-server

# add to Claude Code
claude mcp add hedging8563-tokenlab -- npx -y @tokenlabai/mcp-server
# add to Codex CLI
codex mcp add hedging8563-tokenlab -- npx -y @tokenlabai/mcp-server
// opencode.json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "hedging8563-tokenlab": {
      "type": "local",
      "command": [
        "npx",
        "-y",
        "@tokenlabai/mcp-server"
      ],
      "enabled": true
    }
  }
}
# add to OpenClaw
openclaw mcp add hedging8563-tokenlab --command npx --arg -y --arg @tokenlabai/mcp-server
# ~/.hermes/config.yaml
mcp_servers:
  hedging8563-tokenlab:
    command: "npx"
    args: ["-y", "@tokenlabai/mcp-server"]
// mcp.json
{
  "mcpServers": {
    "hedging8563-tokenlab": {
      "command": "npx",
      "args": [
        "-y",
        "@tokenlabai/mcp-server"
      ]
    }
  }
}
Changelog

Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.

  • 3 Aug 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 23 to 27. That category is still filling its 30-day observation window: 7 days of observed history at the previous scan, 8 at this one. The score rises as the window fills, whether or not the server changes.

  • 2 Aug 26 +19
    • Known CVEs: partial → unverified security
    • Malware scan: unverified → pass security
    • Stability: Stability not yet verified: we do not have a sandbox capture of the MCP schema this version of the package serves yet. security
    • Security disclosure: fail → unverified functional
    • Capabilities: pass → unverified functional
    • Schema quality: 100 → unverified functional
    • Tool coverage: 97 → unverified functional
    • Schema quality: unverified → fair functional
    • Stability: unverified → 0.23 functional
  • 1 Aug 26 +51
    • Install scripts: unverified → pass security
    • Provenance: unverified → pass security
    • Known CVEs: unverified → partial security
    • Stability: Stability not yet verified: not enough scan history yet (needs a 30-day window). security
    • The attested source repository moved: hedging8563/tokenlab-mcp-server security
    • License: unverified → pass functional
    • Schema quality: unverified → 100 functional
    • Dependency health: unverified → partial functional
    • Maintenance: unverified → pass functional
    • MCP protocol: unverified → pass functional
    • Tool coverage: unverified → 97 functional
    • Licence: MIT functional
  • 31 Jul 26 −26
    • We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
  • 27 Jul 26 31

    First indexed and scored.

Diagnostics

Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.

Captured 3 Aug 2026 · Analysed npm/@tokenlabai/[email protected]

Provenance verified

Ecosystem: npm · Outcome: verified

Reason: verified

Source repo:
hedging8563/tokenlab-mcp-server
Certificate issuer:
https://token.actions.githubusercontent.com
Certificate SAN:
https://github.com/hedging8563/tokenlab-mcp-server/.github/workflows/publish-npm.yml@refs/tags/v0.6.17
Rekor log index:
2248401442
Predicate type:
https://slsa.dev/provenance/v1
Subject digest:
sha512:69e490b48753cbb860644a9588ebc3f61296723c0475c77f3bd026cd769e540556a3661449bc9536ba90da94162d8f87daa5258e1aadd6d44c5494a50
Discovery method:
attestation_endpoint
Dependencies 94 packages

94 packages in the resolved dependency tree · 94 deprecated · 29 stale.

The dependency tree was only partially resolved, so these counts may be incomplete.

MCP tools — 31 exposed · ~7,009 tokens

The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability.

Tool Tokens
cancel_task ~114

Cancel async task Cancels a queued asynchronous task when cancellation is supported for the selected task. Cancellation currently supports queued Seedance video tasks (`seedance-1.5-pro`, `seedance-2.0`, and `seedance-2.0-fast`) while they are still waiting to run. Tasks that are already processing, completed, failed, expired, or unsupported are not cancelled.

NameTypeReqDescription
idstringyesThe async task ID returned by `id` / `task_id`, or embedded in `poll_url`

No output schema declared.

No examples provided.

compare_models ~36

Compare public TokenLab model details and pricing for several model IDs.

NameTypeReqDescription
include_rawboolean
modelsarrayyes

No output schema declared.

No examples provided.

create_3d_model ~134

Create 3D model generation task Creates a 3D model generation task using Tripo3D. Returns a task ID for polling.

NameTypeReqDescription
formatstring
imagestringBase64 image for image-to-3D
image_urlstring
modelstring
promptstringyes3D model description
qualitystring
seedintegerSeed for deterministic-compatible providers.
stylestringStyle hint for compatible 3D model families.
userstringEnd-user identifier.

No output schema declared.

No examples provided.

create_anthropic_message ~232

Create message (Anthropic-compatible) Creates a model response using Anthropic's native request format. Supports Claude models with vision and streaming. **Authentication:** Use `x-api-key` header or `Authorization: Bearer` header.

NameTypeReqDescription
max_tokensintegeryesMaximum number of tokens to generate
messagesarrayyesMessages in the conversation
metadataobjectRequest metadata echoed into downstream logs or traces when supported.
modelstringyesModel to use (e.g., claude-sonnet-4-6)
service_tierstringService tier hint for compatible providers.
stop_sequencesarray
stream_optionsobjectStreaming options such as usage chunk inclusion.
systemstringSystem prompt
temperaturenumber
thinkingobjectThinking configuration for compatible Anthropic-style models.
tool_choiceTool choice policy or explicit tool selection.
toolsarrayTool definitions available to the model.
top_kinteger
top_pnumber

No output schema declared.

No examples provided.

create_chat_completion ~516

Create an OpenAI-compatible chat completion. For inline image_url data URLs, declare the byte-accurate image MIME type. The MCP boundary corrects recognized PNG, JPEG, WebP, and GIF payloads declared as application/octet-stream and rejects unrecognized generic binary image payloads before sending a billable request.

NameTypeReqDescription
audioobjectAudio output configuration when requesting audio modality.
frequency_penaltynumberFrequency penalty (-2 to 2)
function_callDeprecated function-call selection retained by the official Chat Completions contract.
functionsarrayDeprecated function definitions retained by the official Chat Completions contract.
logit_biasobjectPer-token logit bias map.
logprobsbooleanWhether to return log probabilities for output tokens.
max_completion_tokensintegerMaximum completion tokens for newer reasoning-enabled model families
max_tokensintegerMaximum number of tokens to generate
messagesarrayyesA list of messages comprising the conversation
modalitiesarrayRequested output modalities such as text or audio.
modelstringyesID of the model to use (e.g., gpt-5.4, claude-sonnet-4-6)
nintegerNumber of completions to generate
parallel_tool_callsbooleanWhether the model may issue parallel tool calls.
predictionobjectPrediction hints for providers that support draft or speculative decoding.
presence_penaltynumberPresence penalty (-2 to 2)
reasoning_effortstringReasoning effort hint for compatible model families.
response_formatobjectResponse format specification
seedintegerSeed for deterministic generation
service_tierstring|nullService tier hint for compatible providers.
stopStop sequences
stream_optionsobjectStreaming options such as usage chunk inclusion.
temperaturenumberSampling temperature (0-2)
tool_choiceControls which function is called
toolsarrayList of tools the model may call
top_logprobsintegerNumber of most likely tokens to return at each position when logprobs is enabled.
top_pnumberNucleus sampling probability
translation_optionsobjectLanguage settings for models that translate audio or video through Chat Completions.
userstringEnd-user identifier for abuse detection

No output schema declared.

No examples provided.

create_embedding ~78

Create embeddings Creates an embedding vector representing the input text.

NameTypeReqDescription
dimensionsintegerOutput vector dimensions
encoding_formatstringOutput format
inputyesInput text(s) or token array(s) to embed.
modelstringyesID of the model to use
userstringEnd-user identifier

No output schema declared.

No examples provided.

create_gemini_content ~295

Generate content (Gemini-compatible) Generates content using the native Gemini GenerateContent shape. This route is exposed only when the model details advertise Gemini requests and a same-protocol route is currently available. ProtoJSON lowerCamelCase and original proto snake_case field names are preserved. Unknown fields are forwarded best-effort and support is determined by the selected provider. **Authentication:** Use `?key=` query parameter, `x-goog-api-key` header, or `Authorization: Bearer` header.

NameTypeReqDescription
cachedContentstringGemini cached content resource name for compatible models.
cached_contentstringOriginal proto field-name spelling of cachedContent.
contentsarrayyesConversation contents
generationConfigobject
generation_configobjectOriginal proto field-name spelling of generationConfig.
modelstringyesModel name (e.g., gemini-2.5-pro)
safetySettingsarray
safety_settingsarrayOriginal proto field-name spelling of safetySettings.
systemInstructionobject
system_instructionobjectOriginal proto field-name spelling of systemInstruction.
toolConfigobjectGemini tool configuration such as functionCallingConfig.
tool_configobjectOriginal proto field-name spelling of toolConfig.
toolsarrayGemini tools. Tool types and combinations are interpreted by the selected service.

No output schema declared.

No examples provided.

create_image ~565

Create image Creates an image given a prompt.

NameTypeReqDescription
aspect_ratiostringAspect-ratio selector for compatible image model families.
asyncbooleanReturn a task before the final image is ready when the selected model supports public async execution.
backgroundstringBackground handling for compatible image flows. For gpt-image-2 generation and edits, accepted values are auto and opaque; transparent is not supported. Other models may support different values.
compressionintegerAlias for output_compression when supported by the selected model
expand_promptbooleanAsk compatible models to expand or enhance the prompt.
image_urlstringSingle reference image URL for compatible image-to-image models.
image_urlsarrayReference image URLs for compatible image-to-image models.
mask_urlstringOptional mask URL for compatible image operations.
modelstringyesModel to use. Send this explicitly; query GET /v1/models?recommended_for=image for current recommendations.
moderationstringModeration strictness for compatible image models such as gpt-image-2
nintegerNumber of images to generate
negative_promptstringContent to avoid for compatible image models.
operationstringPublic image operation family. Reference-image models use image-to-image with image_url, image_urls, or reference_image_urls.
output_compressionintegerOutput compression level from 0 to 100 for compressed formats
output_formatstringOutput image format for compatible image models such as gpt-image-2
promptstringyesImage description
qualitystringImage quality. Defaults and accepted values are model-specific. For gpt-image-2, omit this field or use auto for automatic quality, or send low, medium, or high. Other image families may use provider…
reference_image_urlsarrayAlias used by compatible reference-image model families.
resolutionstringResolution selector for compatible image model families.
response_formatstringResponse format
seedintegerSeed for deterministic-compatible image models.
sizestringImage size. Defaults are model-specific. For gpt-image-2, omit this field or use auto for automatic sizing, or send WIDTHxHEIGHT; custom dimensions must both be multiples of 16, longest edge <= 3840p…
stylestringOptional model-specific style selector. Only send when the selected model documents support for this parameter.
userstringEnd-user identifier

No output schema declared.

No examples provided.

create_image_file ~237

Create image Creates an image given a prompt.

NameTypeReqDescription
aspect_ratiostring
asyncboolean
backgroundstring
compressioninteger
expand_promptboolean
imagestringLocal reference image upload for compatible image-to-image models. Pass local file path.
image_urlsstringComma-separated reference image URLs.
mask_urlstring
modelstringyesModel to use. Send this explicitly.
moderationstring
ninteger
negative_promptstring
operationstring
output_compressioninteger
output_formatstring
promptstringyesImage description
qualitystring
reference_image_urlsstringComma-separated reference image URLs for compatible model families.
resolutionstring
response_formatstring
seedinteger
sizestring
stylestring
userstring

No output schema declared.

No examples provided.

create_multimodal_embedding ~73

Create multimodal embeddings Creates embeddings for multimodal input items. Text input is generally available; image input may require feature enablement.

NameTypeReqDescription
dimensionsintegerOptional embedding dimensionality when supported by the selected model
inputyes
modelstringyesModel to use for multimodal embeddings

No output schema declared.

No examples provided.

create_music ~253

Create music generation task Creates a music generation task using Suno. Returns a task ID for polling.

NameTypeReqDescription
actionstring
audio_operationstringUploaded-audio mode. upload-extend requires continue_at; add-instrumental requires audio_url, title, tags, and negative_tags.
audio_urlstringPublicly reachable reference or uploaded audio URL. Defaults to upload-cover when audio_operation is omitted.
continue_atnumberTimestamp in seconds for continuation flows. Required when audio_operation is upload-extend.
continue_clip_idstringClip ID to continue when extending an existing generation.
make_instrumentalbooleanGenerate instrumental output without vocals.
modelstring
mvstringOfficial Suno model version. Required when creating music (action omitted or MUSIC); omit for lyrics-only requests.
negative_tagsstringStyles to avoid. Required when audio_operation is add-instrumental.
promptstringMusic description. Required for music, lyrics, upload-cover, and upload-extend requests; omit for add-instrumental.
tagsstring
titlestring

No output schema declared.

No examples provided.

create_response ~339

Create response (OpenAI Responses API) Creates a response using the native OpenAI Responses API shape. The model details must advertise the Responses request format and a same-protocol route must be currently available; model names and providers do not imply availability. Unknown request fields are forwarded on a best-effort basis and remain subject to the selected provider's support.

NameTypeReqDescription
backgroundbooleanWhether to run the response asynchronously.
includearrayAdditional response sections to include when supported.
inputInput content as a string or structured item array.
instructionsstringSystem instructions
max_output_tokensintegerMaximum output tokens
metadataobjectRequest metadata.
modelstringyesModel to use
parallel_tool_callsbooleanWhether the model may issue parallel tool calls.
previous_response_idstringID of a previous response to continue.
promptobjectReference to a reusable prompt template and variables.
reasoningobjectReasoning configuration.
service_tierstring|nullService tier hint for compatible providers.
storebooleanWhether the response is stored for later retrieval.
stream_optionsobjectResponses streaming options.
temperaturenumber
textobjectText formatting options.
tool_choiceTool choice policy or explicit tool selection.
toolsarrayTools available to the model. Tool types and combinations are validated by the selected service.
top_pnumberNucleus sampling probability.
truncationstringTruncation strategy for long conversations.

No output schema declared.

No examples provided.

create_speech ~267

Create speech Generates audio from the input text (Text-to-Speech).

NameTypeReqDescription
inputstringyesText to synthesize.
instructionsstringOptional style or delivery instructions for OpenAI-compatible TTS models that support them.
language_codestringOptional language code for Gemini, xAI, and compatible TTS routes.
modelstringTTS model. Query GET /v1/models?recommended_for=tts for the current shortlist.
promptstringOptional speaking style prompt for Gemini TTS models.
response_formatstringAudio format. Common values include mp3, opus, aac, flac, wav, and pcm. Supported values vary by model family.
speednumberSpeech speed for model families that support it.
stream_formatstringTokenLab delivery format. stream_format=sse is not supported for tts-1 or tts-1-hd.
temperaturenumberSampling temperature for Gemini-compatible TTS routes.
voiceVoice selector for OpenAI-compatible, Gemini, xAI, and MiniMax-compatible routes. Some MiniMax routes also accept voice_id.
voice_idstringProvider-native voice selector for MiniMax-compatible speech models.

No output schema declared.

No examples provided.

create_video ~1,991

Create video generation task Creates an asynchronous video generation task. The response returns a canonical task ID and usually a preferred `poll_url`; clients should poll `poll_url` first, or use `/v1/tasks/{id}` as the fixed status endpoint.

NameTypeReqDescription
aspect_ratiostringCanonical video aspect ratio. Seedance defaults to adaptive when omitted. The ratio alias is accepted for compatibility.
audio_urlstringPublicly reachable audio URL for model-specific audio-conditioned video flows.
audio_urlsarrayCompatibility array for audio-conditioned flows when multiple audio references are supported by the routed model family. TokenLab currently accepts up to 3 reference audios.
camera_fixedbooleanOptional fixed-camera selector for compatible video models. Seedance 2.0 models do not support this field.
cfg_scalenumberPrompt adherence strength (0-20) for models that expose CFG-style control.
draftbooleanSeedance 1.5 Pro draft workflow flag. Only supported by draft-capable Seedance routes; draft=true creates a low-cost draft task.
draft_task_idstringSeedance 1.5 Pro draft promotion task ID. Provide this instead of draft=true to create the final video from a previous draft task.
durationintegerVideo duration in seconds. Seedance models also accept -1 to let the model choose within its supported duration range; TokenLab estimates billing conservatively for that mode.
effect_typestringModel-specific effect selector for specialized editing flows.
end_imagestringLast frame image input for start-end-to-video flows. Seedance accepts a public image reference or asset://asset-YYYYMMDDHHMMSS-xxxxx for an ACTIVE TokenLab material owned by the requesting organizati…
execution_expires_afterintegerOptional execution expiry window in seconds for compatible video models. Seedance defaults to 172800 seconds when omitted.
extend_atintegerModel-specific extension start offset used by some video-extension flows.
extend_timesstringModel-specific extension multiplier or repeat count used by some video-extension flows.
fpsintegerFrames per second
framesintegerOptional frame count for compatible video models. Seedance 2.0 models and Seedance 1.5 Pro do not support this field.
generate_audiobooleanCompatibility alias for output_audio. If more than one audio toggle is provided, all values must match.
imagestringInline image as a data URL (for example, data:image/png;base64,...). Prefer image_url for broader production compatibility. When the selected Seedance model can use the TokenLab material library, Tok…
image_urlstringPublicly reachable image URL for image-to-video generation, or asset://asset-YYYYMMDDHHMMSS-xxxxx for an ACTIVE TokenLab Seedance material used as the first frame. Preferred over inline base64 in pro…
image_urlsarrayImage URL array for compatible image-conditioned video flows. This endpoint currently allows up to 9 entries. When the selected Seedance model can use the TokenLab material library, TokenLab prepares…
kling_elementsarrayKling 3.0 element references for kling-3.0-video image-conditioned requests. Define 1-3 elements and reference them in the prompt with @name. Each element requires 2-4 image URLs in element_input_url…
material_asset_idstringTokenLab Seedance material asset ID returned by /v1/videos/assets, by automatic image preparation, or from a real-person group returned by GetVisualValidateResult. Use it after the asset is ACTIVE wi…
material_asset_idsarrayTokenLab Seedance material asset IDs returned by /v1/videos/assets or by automatic image preparation. They share the Seedance image-reference limit; the selected model must be able to use the TokenLa…
modelstringModel to use (e.g., veo3.1, kling-v1)
motion_strengthnumberMotion intensity (0-1) for models that expose it.
negative_promptstringWhat to avoid in the video
operationstringRequested video operation. If omitted, TokenLab infers the operation from the provided inputs. Explicit operation is recommended for production reliability.
outputAudiobooleanCompatibility alias for output_audio. If both are provided, they must match.
output_audiobooleanCanonical model-dependent audio output toggle. Veo 3 and Seedance requests default to true when omitted. Kling 3.0 Video accepts this selector for non-element-reference requests and maps it to the co…
priorityintegerOptional task priority for compatible video models. Do not combine priority with service_tier=flex.
promptstringVideo description
ratiostringCompatibility alias for aspect_ratio. If both ratio and aspect_ratio are provided, they must match.
reference_image_typestringOptional reference image role for models that distinguish between asset and style references. The camelCase alias referenceImageType is accepted for compatibility.
reference_imagesarrayCanonical public reference-image field for reference-to-video conditioning. This endpoint currently allows up to 9 URLs, compatible data URLs, or for Seedance, asset://asset-YYYYMMDDHHMMSS-xxxxx URIs…
resolutionstringVideo resolution. Seedance defaults to 720p when omitted; available values are model-dependent.
return_last_framebooleanReturn the last generated frame when the selected model supports it. Seedance defaults to false when omitted.
safety_identifierstringOptional safety/user trace identifier for compatible video models. If omitted for Seedance, TokenLab uses user when provided.
secondsintegerAlias of duration used by compatible request shapes. Seedance models also accept -1 to let the model choose within its supported duration range; duration and seconds must match when both are provided.
seedintegerSeed for reproducibility. Seedance uses -1 for random seed when omitted.
service_tierstringOptional service tier for compatible video models. service_tier=default is accepted as a no-op for Seedance 2.0 models; service_tier=flex is rejected where the selected model does not support it.
sizestringModel-specific size tier for compatible video models.
start_imagestringFirst frame image input for start-end-to-video flows. Seedance accepts a public image reference or asset://asset-YYYYMMDDHHMMSS-xxxxx for an ACTIVE TokenLab material owned by the requesting organizat…
task_idstringTask identifier used by some continuation, extension, or derivative flows.
userstringEnd-user identifier
video_urlstringPublicly reachable video URL for video-to-video style flows and motion-control models.
video_urlsarrayCompatibility array for video-conditioned flows when multiple input videos are supported by the routed model family. TokenLab currently accepts up to 3 reference videos.
watermarkbooleanOptional watermark toggle for models that expose it. Seedance defaults to false when omitted.

No output schema declared.

No examples provided.

delete_file ~93

Delete file Deletes a batch file or a bound image/reference file. When the request includes anthropic-beta: files-api-2025-04-14, the route uses Anthropic Files API mode for the bound workspace.

NameTypeReqDescription
anthropic-betastringInclude files-api-2025-04-14 to use Anthropic Files API mode.
file_idstringyesFile ID returned by the Files API.

No output schema declared.

No examples provided.

edit_image ~324

Edit image Edits an image using multipart image uploads, JSON image URLs, or the official JSON images array for supported GPT Image models.

NameTypeReqDescription
aspect_ratiostring
asyncbooleanReturn a task before the edited image is ready for models that support public async execution.
backgroundstring
compressioninteger
image_urlstringSingle source image URL. Kept for TokenLab compatibility; use images for the official JSON shape.
image_urlsarrayMultiple source image URLs. GPT Image edits accept up to 16 source images; xAI Grok Imagine edit models accept at most 3 source images.
imagesarrayOfficial JSON image references for image edits. Provide exactly one of image_url or file_id for each item. GPT Image edits accept up to 16 source images; xAI Grok Imagine edit models accept at most 3…
maskobjectOptional JSON mask reference for image edits. Provide exactly one of image_url or file_id. Multipart requests can also send mask as a file part.
modelstringyesModel to use for image edits. Send this explicitly.
moderationstring
ninteger
output_compressioninteger
output_formatstring
promptstringyes
qualitystring
resolutionstring
response_formatstring
sizestring
userstring

No output schema declared.

No examples provided.

edit_image_file ~267

Edit image Edits an image using multipart image uploads, JSON image URLs, or the official JSON images array for supported GPT Image models.

NameTypeReqDescription
aspect_ratiostring
asyncboolean
backgroundstring
compressioninteger
imageSource image file(s). Repeat image for multiple source images. GPT Image edits accept up to 16 images; xAI Grok Imagine edit models accept at most 3 source images. Pass local file paths.
image[]arrayAlternative repeated multipart field name for multiple source images. The same model-specific limits apply: GPT Image up to 16, xAI Grok Imagine up to 3. Pass local file paths.
maskstringPass local file path.
modelstringyesModel to use for image edits. Send this explicitly, for example gpt-image-2.
moderationstring
ninteger
output_compressioninteger
output_formatstring
promptstringyes
qualitystring
resolutionstring
response_formatstring
sizestring
userstring

No output schema declared.

No examples provided.

get_api_overview ~19

Fetch TokenLab's agent-readable API overview.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

get_model ~59

Get model Retrieves current model details, including supported operations, request parameters, request endpoints, selector limits, and pricing when available. Non-chat integrations should read these current model-specific request details before creating a request.

NameTypeReqDescription
modelstringyesThe model ID

No output schema declared.

No examples provided.

get_model_pricing ~45

Get model pricing Retrieves pricing-only detail for one model. Use this endpoint for price explanation, not for non-chat request construction.

NameTypeReqDescription
modelstringyesThe model ID

No output schema declared.

No examples provided.

get_pricing ~50

List model pricing Returns the public pricing surface for active models, with optional provider and tag filters.

NameTypeReqDescription
providerstringFilter by provider ID.
tagstringFilter by model tag.

No output schema declared.

No examples provided.

get_task_status ~87

Get async task status Retrieves the status and result of an asynchronous generation task. Prefer the `poll_url` returned by the create response; `/v1/tasks/{id}` is the canonical fixed status endpoint for video, music, and 3D jobs.

NameTypeReqDescription
idstringyesThe async task ID returned by `id` / `task_id`, or embedded in `poll_url`

No output schema declared.

No examples provided.

list_files ~199

List files

NameTypeReqDescription
afterstring
after_idstringAnthropic Files cursor. Return files after this public file id. Requires the Anthropic Files beta header and cannot be combined with before_id.
anthropic-betastringInclude files-api-2025-04-14 to use Anthropic Files API mode.
before_idstringAnthropic Files cursor. Return files before this public file id. Requires the Anthropic Files beta header and cannot be combined with after_id.
limitinteger
purposestringOptional file purpose filter. batch and batch_output cover Batch API files; user_data and vision cover TokenLab image/reference file bindings. Anthropic Files API mode is selected by Anthropic header…
scope_idstringReserved Anthropic Files scope cursor. TokenLab currently returns an explicit unsupported error rather than silently ignoring this value.

No output schema declared.

No examples provided.

list_models ~170

List models Lists the currently available models. Use `view=compact` for model selection and `view=full` for the existing OpenAI-compatible discovery shape. Native API calls default to `full`; integrations may choose `compact` as their default. Non-chat recommendations are available through `recommended_for`.

NameTypeReqDescription
categorystringFilter by model category.
providerstringFilter by public model provider, for example openai, anthropic, google, or minimax.
recommended_forstringSort supported non-chat models for a task category and include recommendation evidence.
tagstringFilter by a public capability tag.
viewstringCompact model-selection output is the MCP default. Set view to full only when the complete OpenAI-compatible list shape is required.

No output schema declared.

No examples provided.

rerank_documents ~82

Rerank documents Reranks documents by relevance to a query using semantic similarity.

NameTypeReqDescription
documentsarrayyesDocuments to rerank
modelstringyesReranker model to use
querystringyesQuery to rank against
return_documentsboolean
top_nintegerNumber of results to return

No output schema declared.

No examples provided.

retrieve_file ~45

Retrieve file

NameTypeReqDescription
anthropic-betastringInclude files-api-2025-04-14 to use Anthropic Files API mode.
file_idstringyes

No output schema declared.

No examples provided.

retrieve_file_content ~21

Retrieve file content

NameTypeReqDescription
file_idstringyes

No output schema declared.

No examples provided.

transcribe_audio ~121

Create transcription Transcribes audio into text (Speech-to-Text).

NameTypeReqDescription
filestringyesAudio file to transcribe Pass local file path.
languagestringISO-639-1 language code
modelstringyesModel to use (whisper-1)
promptstringOptional prompt text
response_formatstringResponse format
temperaturenumberSampling temperature
timestamp_granularitiesarrayTimestamp granularity selection. Requires verbose_json output when requesting word-level timestamps.

No output schema declared.

No examples provided.

translate_audio ~60

Translate audio Transcribes audio and translates the result to English.

NameTypeReqDescription
filestringyesPass local file path.
modelstring
promptstring
response_formatstring
temperaturenumber

No output schema declared.

No examples provided.

translate_text ~69

Translate text Translates text into a target language using the current translation request format.

NameTypeReqDescription
mime_typestring
modelstringyes
source_languagestring
target_languagestringyes
textstringyes
userstring

No output schema declared.

No examples provided.

upload_file ~168

Upload file Uploads a TokenLab/OpenAI-compatible batch or image file. With anthropic-beta: files-api-2025-04-14, uploads an Anthropic Files resource without a purpose field and returns Anthropic file metadata.

NameTypeReqDescription
anthropic-betastringInclude files-api-2025-04-14 to use Anthropic Files API mode.
filestringyesPass local file path.
modelstringOptional TokenLab extension for image file uploads. Defaults to gpt-image-2 and binds the returned file_id to the selected image-edit configuration.
purposestringRequired in TokenLab/OpenAI-compatible mode: use batch for Batch API JSONL files, or user_data/vision for image edits. Omit in Anthropic Files mode.

No output schema declared.

No examples provided.