TokenLab MCP Server
NPM · @TOKENLABAI/MCP-SERVER
TokenLab MCP server: generate images and video, call models. 32 default and 89 full-profile tools.
Available components
Last scanned (5 hours ago)
Scores higher than 69% of npm servers
Category AI and Machine Learning
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 → Why this is hard to score →
Supply Chain Security63
- No malware found by supply-chain analysis.Pass
- Known CVEs could not be checked: the version this server declares is not published in its registry.Unverified
- No install/post-install scripts declared.Pass
- Dependency health could not be checked: the version this server declares is not published in its registry.Unverified
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 0 days ago).Pass
- Disclosure check failed: no security disclosure policy was found in the source repository. See how to fix → Fail
Schema Quality & AI Usability67
- 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).Pass
- AI-judged instruction clarity (good).Pass
- Context-footprint check failed: tool/resource definitions use about 7380 tokens (~210/item across 35 items; 32 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 Management97
- Stability check failed: the tool surface changed between 0.6.26 and 0.6.44: 0 tool removals, 2 breaking changes, 0 additions. See how to fix → Fail
Tool Coverage91
- 97% of tools have a non-trivial description (not blank, and not just the tool's name).Partial
- 80% of tool parameters carry a description.Partial
Tool Safety100
- No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
- All 1 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation.Pass
- An AI judge read all 34 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
- Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass
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.
- 4 Nov 26 −11
- Known CVEs: pass → unverified ▼ security
- Stability: fail → unverified ▼ security
- Tool safety: pass → unverified ▼ security
- Dependency health: 0.85 → unverified ▼ functional
- Capabilities: pass → unverified ▼ functional
- Schema quality: 100 → unverified ▼ functional
- Tool coverage: 97 → unverified ▼ functional
- Package version: 0.6.41 → 0.6.44 functional
- Package version: 0.6.41 → 0.6.43 functional
- Package version: 0.6.41 → 0.6.42 functional
- 2 Nov 26 +11
- Known CVEs: unverified → pass ▲ security
- Dependency health: unverified → 0.85 ▲ functional
- 1 Nov 26 −11
- Stability: fail → unverified ▼ security
- Known CVEs: pass → unverified ▼ security
- Tool safety: pass → unverified ▼ security
- Schema quality: 100 → unverified ▼ functional
- Capabilities: pass → unverified ▼ functional
- Dependency health: 0.85 → unverified ▼ functional
- Tool coverage: 97 → unverified ▼ functional
- Package version: 0.6.39 → 0.6.41 functional
- Package version: 0.6.39 → 0.6.40 functional
- 29 Oct 26 +15
- Malware scan: unverified → pass ▲ security
- 28 Oct 26 −15
- Malware scan: pass → unverified ▼ security
- Package version: 0.6.38 → 0.6.39 functional
- 25 Oct 26 +26
- Malware scan: unverified → pass ▲ security
- Known CVEs: unverified → pass ▲ security
- Dependency health: unverified → 0.85 ▲ functional
- 24 Oct 26 −25
- Known CVEs: pass → unverified ▼ security
- Malware scan: pass → unverified ▼ security
- Dependency health: 0.85 → unverified ▼ functional
- Package version: 0.6.35 → 0.6.38 functional
- Package version: 0.6.35 → 0.6.37 functional
- 22 Oct 26 +24
- Malware scan: unverified → pass ▲ security
- Known CVEs: unverified → pass ▲ security
- Dependency health: unverified → 0.85 ▲ functional
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 4 Nov 2026 · Analysed npm/@tokenlabai/mcp-server@0.6.44
Provenance Verified
A signed build attestation was found and verified, binding this exact artifact to the source repository it claims to come from.
| Result | Verified |
|---|---|
| Ecosystem | npm |
| Reason | Verified |
| Discovered via | Registry attestation endpoint |
| 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/heads/main |
| Rekor log index | 3691786273 |
| Predicate type | SLSA build provenance https://slsa.dev/provenance/v1 |
| Subject digest | sha512:f6952107f324d2f68224dee9d81315a389ca9013267dd1c49c16749acc832b131f51e99a049553f82bc937eb9f9016e6f2ae223504ec45972db8ec685 |
Background: How many MCP packages publish verified provenance →
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. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →
cancel_task Cancel async task ~92
Cancels a queued asynchronous task when cancellation is supported for the selected task. Cancellation currently supports queued Seedance video tasks (`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.
| Name | Type | Req | Description |
|---|---|---|---|
| id | string | yes | Returned id/task_id or the ID in poll_url. |
No output schema declared.
No examples provided.
compare_models Compare TokenLab Models ~36
Compare public TokenLab model details and pricing for several model IDs.
| Name | Type | Req | Description |
|---|---|---|---|
| include_raw | boolean | – | – |
| models | array | yes | – |
No output schema declared.
No examples provided.
create_3d_model Create 3D model generation task ~199
Creates a 3D model generation task using Tripo3D. Returns a task ID for polling.
| Name | Type | Req | Description |
|---|---|---|---|
| Idempotency-Key | string | – | Optional key that makes a create request safe to retry. Send a new unique value, such as a UUID, fo… |
| X-TokenLab-Delivery-Policy | string | – | Per-request Delivery policy. Overrides the API key and Workspace defaults. Auto tries TokenLab Veri… |
| format | string | – | – |
| image | string | – | Base64 image for image-to-3D |
| image_url | string | – | – |
| model | string | – | 3D model ID. |
| prompt | string | – | 3D prompt; required only if get_model lists prompt. |
| quality | string | – | – |
| seed | integer | – | Repeatable generation seed where supported. |
| style | string | – | Model-specific style hint. |
| user | string | – | User ID. |
No output schema declared.
No examples provided.
create_anthropic_message Create message (Anthropic-compatible) ~280
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.
| Name | Type | Req | Description |
|---|---|---|---|
| Idempotency-Key | string | – | Optional key that stops a second run of the same request. Send a new unique value, such as a UUID, … |
| X-TokenLab-Delivery-Policy | string | – | Per-request Delivery policy. Overrides the API key and Workspace defaults. Auto tries TokenLab Veri… |
| max_tokens | integer | yes | Maximum number of tokens to generate |
| messages | array | yes | Messages in the conversation |
| metadata | object | – | Request metadata echoed into downstream logs or traces when supported. |
| model | string | yes | Model ID. |
| service_tier | string | – | Only auto and standard_only take effect. |
| stop_sequences | array | – | – |
| stream_options | object | – | Streaming options such as usage chunk inclusion. |
| system | string | – | System prompt |
| temperature | number | – | – |
| thinking | object | – | Thinking configuration for compatible Anthropic-style models. |
| tool_choice | object | – | Tool choice policy or explicit tool selection. |
| tools | array | – | Tool definitions available to the model. |
| top_k | integer | – | – |
| top_p | number | – | – |
No output schema declared.
No examples provided.
create_chat_completion Create chat completion ~550
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.
| Name | Type | Req | Description |
|---|---|---|---|
| Idempotency-Key | string | – | Optional key that stops a second run of the same request. Send a new unique value, such as a UUID, … |
| X-TokenLab-Delivery-Policy | string | – | Per-request Delivery policy. Overrides the API key and Workspace defaults. Auto tries TokenLab Veri… |
| anthropic_options | object | – | Options for Claude models. |
| audio | object | – | Audio output configuration when requesting audio modality. |
| extra | object | – | extra.prompt_caching/extra.prompt_caching_ttl alias anthropic_options. |
| frequency_penalty | number | – | Frequency penalty (-2 to 2) |
| function_call | – | – | Legacy function selection. |
| functions | array | – | Legacy function definitions. |
| logit_bias | object | – | Per-token logit bias map. |
| logprobs | boolean | – | Whether to return log probabilities for output tokens. |
| max_completion_tokens | integer | – | Maximum completion tokens for newer reasoning-enabled model families |
| max_tokens | integer | – | Maximum number of tokens to generate |
| messages | array | yes | A list of messages comprising the conversation |
| modalities | array | – | Requested output modalities such as text or audio. |
| model | string | yes | Model ID. |
| n | integer | – | Number of completions to generate |
| parallel_tool_calls | boolean | – | Whether the model may issue parallel tool calls. |
| prediction | object | – | Draft/speculative decoding hints. |
| presence_penalty | number | – | Presence penalty (-2 to 2) |
| reasoning_effort | string | – | Reasoning effort hint for compatible model families. |
| response_format | object | – | Response format specification |
| seed | integer | – | Seed for deterministic generation |
| service_tier | string|null | – | Standard tier pricing; auto/default forwarded; flex/priority/fast/ultrafast ignored. |
| stop | – | – | Stop sequences |
| temperature | number | – | Sampling temperature (0-2) |
| tool_choice | – | – | Controls which function is called |
| tools | array | – | List of tools the model may call |
| top_logprobs | integer | – | Top token count per position; requires logprobs. |
| top_p | number | – | Nucleus sampling probability |
| translation_options | object | – | Audio/video translation language settings. |
| user | string | – | User ID for abuse detection. |
No output schema declared.
No examples provided.
create_embedding Create embeddings ~103
Creates an embedding vector representing the input text.
| Name | Type | Req | Description |
|---|---|---|---|
| X-TokenLab-Delivery-Policy | string | – | Per-request Delivery policy. Overrides the API key and Workspace defaults. Auto tries TokenLab Veri… |
| dimensions | integer | – | Output vector dimensions |
| encoding_format | string | – | Output format |
| input | – | yes | Input text(s) or token array(s) to embed. |
| model | string | yes | Model ID. |
| user | string | – | User ID. |
No output schema declared.
No examples provided.
create_gemini_content Generate content (Gemini-compatible) ~223
Generates content using the Gemini GenerateContent request shape. The model details must advertise Gemini requests and the model must be available. ProtoJSON lowerCamelCase and original proto snake_case field names are preserved. Unknown fields are accepted on a best-effort basis; model-specific support is not guaranteed. **Authentication:** Use `?key=` query parameter, `x-goog-api-key` header, or `Authorization: Bearer` header.
| Name | Type | Req | Description |
|---|---|---|---|
| X-TokenLab-Delivery-Policy | string | – | Per-request Delivery policy. Overrides the API key and Workspace defaults. Auto tries TokenLab Veri… |
| cachedContent | string | – | Gemini cached content resource name for compatible models. |
| contents | array | yes | Conversation contents |
| generationConfig | object | – | – |
| model | string | yes | Gemini model ID. |
| safetySettings | array | – | – |
| systemInstruction | object | – | – |
| toolConfig | object | – | Gemini tool configuration such as functionCallingConfig. |
| tools | array | – | Gemini tools; allowed types/combinations depend on the selected service. |
No output schema declared.
No examples provided.
create_image Create image ~630
Creates an image given a prompt.
| Name | Type | Req | Description |
|---|---|---|---|
| Idempotency-Key | string | – | Optional key that makes an image request safe to retry if the request created a task. Send a new un… |
| X-TokenLab-Delivery-Policy | string | – | Per-request Delivery policy. Overrides the API key and Workspace defaults. Auto tries TokenLab Veri… |
| aspect_ratio | string | – | Aspect-ratio selector for compatible image model families. |
| async | boolean | – | Async task if the model supports it. |
| background | string | – | Background handling for compatible image flows. For gpt-image-2 generation and edits, accepted valu… |
| cfg_scale | number | – | Model-specific image CFG scale. See get_model. |
| compression | integer | – | Alias for output_compression when supported by the selected model |
| expand_prompt | boolean | – | Ask compatible models to expand or enhance the prompt. |
| guidance | number | – | Model-specific guidance value. See get_model. |
| guidance_scale | number | – | Model-specific guidance scale. See get_model. |
| height | integer | – | Model-specific output height in pixels. See get_model. |
| image_url | string | – | Single reference image URL for compatible image-to-image models. |
| image_urls | array | – | Reference image URLs for compatible image-to-image models. |
| mask_url | string | – | Optional mask URL for compatible image operations. |
| model | string | yes | Explicit image model ID. |
| moderation | string | – | Moderation strictness for compatible image models such as gpt-image-2 |
| n | integer | – | Number of images to generate |
| negative_prompt | string | – | Content to avoid for compatible image models. |
| operation | string | – | Public image operation family. Reference-image models use image-to-image with image_url, image_urls… |
| output_compression | integer | – | Output compression level from 0 to 100 for compressed formats |
| output_format | string | – | Output image format for compatible image models such as gpt-image-2 |
| prompt | string | – | Image prompt; required only if get_model lists prompt. |
| prompt_extend | boolean | – | z-image-turbo prompt expansion; default false; true uses expansion pricing. |
| quality | string | – | Model-specific image quality; check get_model for accepted values. |
| reference_image_urls | array | – | Alias used by compatible reference-image model families. |
| resolution | string | – | Resolution selector for compatible image model families. |
| response_format | string | – | How the images are returned. Omitted: when the model returns image bytes, each image is in data[].b… |
| seed | integer | – | Seed for deterministic-compatible image models. |
| size | string | – | Model-specific image size; check get_model for sizes and limits. |
| steps | integer | – | Model-specific inference step count. See get_model. |
| style | string | – | Optional model-specific style selector. Only send when the selected model documents support for thi… |
| user | string | – | End-user identifier |
| width | integer | – | Model-specific output width in pixels. See get_model. |
No output schema declared.
No examples provided.
create_image_file Create image ~453
Creates an image given a prompt.
| Name | Type | Req | Description |
|---|---|---|---|
| Idempotency-Key | string | – | Optional key that makes an image request safe to retry if the request created a task. Send a new un… |
| X-TokenLab-Delivery-Policy | string | – | Per-request Delivery policy. Overrides the API key and Workspace defaults. Auto tries TokenLab Veri… |
| aspect_ratio | string | – | – |
| async | boolean | – | Async task if the model supports it. |
| background | string | – | – |
| cfg_scale | number | – | Model-specific image CFG scale. See get_model. |
| compression | integer | – | – |
| expand_prompt | boolean | – | – |
| guidance | number | – | Model-specific guidance value. See get_model. |
| guidance_scale | number | – | Model-specific guidance scale. See get_model. |
| height | integer | – | Model-specific output height in pixels. See get_model. |
| image | string | – | Local reference image upload for compatible image-to-image models. Pass local file path. |
| image_urls | string | – | Comma-separated reference image URLs. |
| mask_url | string | – | – |
| model | string | yes | Explicit image model ID. |
| moderation | string | – | – |
| n | integer | – | – |
| negative_prompt | string | – | – |
| operation | string | – | – |
| output_compression | integer | – | – |
| output_format | string | – | – |
| prompt | string | – | Image prompt; required only if get_model lists prompt. |
| prompt_extend | boolean | – | z-image-turbo prompt expansion; default false; true uses expansion pricing. |
| quality | string | – | Model-specific image quality; check get_model for accepted values. |
| reference_image_urls | string | – | Comma-separated reference image URLs for compatible model families. |
| resolution | string | – | – |
| response_format | string | – | – |
| seed | integer | – | – |
| size | string | – | Model-specific image size; check get_model for sizes and limits. |
| steps | integer | – | Model-specific inference step count. See get_model. |
| style | string | – | – |
| user | string | – | – |
| width | integer | – | Model-specific output width in pixels. See get_model. |
No output schema declared.
No examples provided.
create_multimodal_embedding Create multimodal embeddings ~100
Creates embeddings for multimodal input items. Text input is generally available; image input may require feature enablement.
| Name | Type | Req | Description |
|---|---|---|---|
| X-TokenLab-Delivery-Policy | string | – | Per-request Delivery policy. Overrides the API key and Workspace defaults. Auto tries TokenLab Veri… |
| dimensions | integer | – | Optional embedding dimensionality when supported by the selected model |
| input | – | yes | – |
| model | string | yes | Multimodal embedding model ID. |
No output schema declared.
No examples provided.
create_music Create music generation task ~289
Creates a music generation task using Suno. Returns a task ID for polling.
| Name | Type | Req | Description |
|---|---|---|---|
| Idempotency-Key | string | – | Optional key that makes a create request safe to retry. Send a new unique value, such as a UUID, fo… |
| X-TokenLab-Delivery-Policy | string | – | Per-request Delivery policy. Overrides the API key and Workspace defaults. Auto tries TokenLab Veri… |
| action | string | – | – |
| audio_operation | string | – | upload-extend needs continue_at; add-instrumental needs audio_url/title/tags/negative_tags. |
| audio_url | string | – | Public audio URL; omitted audio_operation defaults to upload-cover. |
| continue_at | number | – | Continuation time in seconds; required for upload-extend. |
| continue_clip_id | string | – | Clip ID to continue when extending an existing generation. |
| make_instrumental | boolean | – | Generate instrumental output without vocals. |
| model | string | – | Music model ID. |
| mv | string | – | Suno model version; required for MUSIC/default action, omitted for lyrics-only. |
| negative_tags | string | – | Styles to avoid. Required when audio_operation is add-instrumental. |
| prompt | string | – | Prompt required for music/lyrics/upload-cover/upload-extend; omit for add-instrumental. |
| tags | string | – | – |
| title | string | – | Song title. |
No output schema declared.
No examples provided.
create_response Create response (OpenAI Responses API) ~381
Creates a response using the OpenAI Responses API request shape. The model details must advertise the Responses request format and the model must be available. Unknown fields are accepted on a best-effort basis; model-specific support is not guaranteed.
| Name | Type | Req | Description |
|---|---|---|---|
| Idempotency-Key | string | – | Optional key that stops a second run of the same request. Send a new unique value, such as a UUID, … |
| X-TokenLab-Delivery-Policy | string | – | Per-request Delivery policy. Overrides the API key and Workspace defaults. Auto tries TokenLab Veri… |
| background | boolean | – | Whether to run the response asynchronously. |
| include | array | – | Additional response sections to include when supported. |
| input | – | – | String or structured input items. |
| instructions | string | – | System instructions |
| max_output_tokens | integer | – | Maximum output tokens |
| metadata | object | – | Request metadata. |
| model | string | yes | Model to use |
| parallel_tool_calls | boolean | – | Whether the model may issue parallel tool calls. |
| previous_response_id | string | – | ID of a previous response to continue. |
| prompt | object | – | Reusable prompt template and variables. |
| reasoning | object | – | Reasoning configuration. |
| service_tier | string|null | – | Standard tier pricing; auto/default forwarded; flex/priority/fast/ultrafast ignored. |
| store | boolean | – | Whether the response is stored for later retrieval. |
| stream_options | object | – | Responses streaming options. |
| temperature | number | – | – |
| text | object | – | Text formatting options. |
| tool_choice | – | – | Tool choice policy or explicit tool selection. |
| tools | array | – | Tools; allowed types/combinations depend on the selected service. |
| top_p | number | – | Nucleus sampling probability. |
| truncation | string | – | Truncation strategy for long conversations. |
No output schema declared.
No examples provided.
create_speech Create speech ~215
Generates audio from the input text (Text-to-Speech).
| Name | Type | Req | Description |
|---|---|---|---|
| X-TokenLab-Delivery-Policy | string | – | Per-request Delivery policy. Overrides the API key and Workspace defaults. Auto tries TokenLab Veri… |
| input | string | yes | Text to synthesize. |
| instructions | string | – | Style instructions for supported OpenAI-compatible TTS models. |
| language_code | string | – | Language code for Gemini/xAI/compatible TTS. |
| model | string | yes | TTS model ID; no default. |
| prompt | string | – | Gemini TTS style prompt. |
| response_format | string | – | Audio format: mp3/opus/aac/flac/wav/pcm; model-specific support. |
| speed | number | – | Speech speed where supported. |
| stream_format | string | – | TokenLab delivery format. |
| temperature | number | – | Gemini TTS sampling temperature. |
| voice | – | – | Voice selector; some MiniMax models also accept voice_id. |
| voice_id | string | – | MiniMax voice selector. |
No output schema declared.
No examples provided.
create_video Create video generation task ~1,279
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.
| Name | Type | Req | Description |
|---|---|---|---|
| Idempotency-Key | string | – | Optional key that makes a create request safe to retry. Send a new unique value, such as a UUID, fo… |
| X-TokenLab-Delivery-Policy | string | – | Per-request Delivery policy. Overrides the API key and Workspace defaults. Auto tries TokenLab Veri… |
| aspect_ratio | string | – | Aspect ratio, for example 16:9; allowed values depend on the model (400 invalid_aspect_ratio). |
| audio | boolean | – | Audio selector accepted by a few models, such as the Vidu models and `wan-2.6`. It must match `outp… |
| audio_type | string | – | Audio control; support varies by model and operation. |
| audio_url | string | – | Public audio URL for a supported audio-input operation. |
| audio_urls | array | – | Compatibility array for audio-conditioned flows when multiple audio references are supported by the… |
| bgm | boolean | – | Audio control; support varies by model and operation. |
| camera_fixed | boolean | – | Optional fixed-camera selector for compatible video models. Seedance 2.0 and Seedance 2.5 do not su… |
| cfg_scale | number | – | Prompt adherence strength (0-20) for models that expose CFG-style control. |
| draft | boolean | – | Draft workflow flag. Accepted only by models whose details list this field. |
| draft_task_id | string | – | ID of an earlier draft task to turn into the final video. Accepted only by models whose details lis… |
| duration | integer | – | Duration in seconds; allowed values depend on the model (400 invalid_duration). Seedance also accep… |
| effect_type | string | – | Model-specific edit effect. |
| end_image | string | – | Last frame image for start-end-to-video. Send it with start_image. Accepts the same inputs as start… |
| execution_expires_after | integer | – | Optional execution expiry window in seconds for compatible video models. Seedance defaults to 17280… |
| extend_at | integer | – | Model-specific video extension offset. |
| extend_times | string | – | Model-specific extension multiplier/repeat count. |
| fps | integer | – | Frames per second |
| frames | integer | – | Frame count, for models that list this field. Seedance models do not accept it. |
| generate_audio | boolean | – | output_audio alias; all supplied audio toggles must match. |
| height | integer | – | Pixel height; pair with width. |
| image | string | – | Inline image as a data URL (for example, data:image/png;base64,...), up to 2,000,000 characters. Pr… |
| image_url | string | – | Publicly reachable image URL for image-to-video generation, up to 8,192 characters, or asset://asse… |
| image_urls | array | – | Image URLs for models that list this field. Seedance 2.5 accepts up to 30 image inputs in total acr… |
| kling_elements | array | – | Element references for image-conditioned requests on models that explicitly support this field. Def… |
| material_asset_id | string | – | TokenLab Seedance material asset ID returned by /v1/videos/assets or from a real-person group retur… |
| material_asset_ids | array | – | TokenLab Seedance material asset IDs returned by /v1/videos/assets. Accepted by the Seedance 2.0 mo… |
| model | string | – | Model ID. |
| motion_strength | number | – | Motion intensity (0-1) for models that expose it. |
| negative_prompt | string | – | What to avoid in the video |
| operation | string | – | Video operation; if omitted, inferred from inputs. Send explicitly. |
| outputAudio | boolean | – | output_audio alias; all supplied audio toggles must match. |
| output_audio | boolean | – | Audio-output selector for operations that declare it. Omission follows the model default; `false` r… |
| output_format | string | – | mp4, mov or webm, where the model lists it. |
| priority | integer | – | Task priority where supported; incompatible with service_tier=flex. |
| prompt | string | – | Video description |
| ratio | string | – | aspect_ratio alias; if both are sent, values must match. |
| reference_image_type | string | – | Image reference role: asset/style; alias: referenceImageType. |
| reference_images | array | – | Reference images for reference-to-video, as public image URLs or data URLs. The count limit depends… |
| resolution | string | – | Resolution, for example 720p; allowed values depend on the model (400 invalid_resolution). |
| return_last_frame | boolean | – | Return last frame where supported; Seedance default: false. |
| safety_identifier | string | – | Optional safety/user trace identifier for compatible video models. If omitted for Seedance, TokenLa… |
| seconds | integer | – | Alias of duration used by compatible request shapes. Seedance models also accept -1 to let the mode… |
| seed | integer | – | Seed for reproducibility, for models that list this field. Seedance 2.0 models accept -1 for a rand… |
| service_tier | string | – | Optional service tier for compatible video models. service_tier=default is accepted as a compatibil… |
| size | string | – | Model-specific video size tier. |
| start_image | string | – | First frame image. With end_image, the request is start-end-to-video. Without end_image, it is imag… |
| task_id | string | – | Continuation/extension/derivative task ID. |
| user | string | – | User ID. |
| video_url | string | – | Public video URL for video-to-video or motion control. |
| video_urls | array | – | Compatibility array for video-conditioned flows when multiple input videos are supported by the sel… |
| voice_id | string | – | Audio control; support varies by model and operation. |
| watermark | boolean | – | Watermark toggle where supported; Seedance default: false. |
| width | integer | – | Pixel width; pair with height. |
No output schema declared.
No examples provided.
delete_file Delete file ~91
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.
| Name | Type | Req | Description |
|---|---|---|---|
| anthropic-beta | string | – | Include files-api-2025-04-14 to use Anthropic Files API mode. |
| file_id | string | yes | File ID returned by the Files API. |
No output schema declared.
No examples provided.
edit_image Edit image ~478
Edits an image using multipart image uploads, JSON image URLs, or the official JSON images array for supported GPT Image models.
| Name | Type | Req | Description |
|---|---|---|---|
| Idempotency-Key | string | – | Optional key that makes an image request safe to retry if the request created a task. Send a new un… |
| X-TokenLab-Delivery-Policy | string | – | Per-request Delivery policy. Overrides the API key and Workspace defaults. Auto tries TokenLab Veri… |
| aspect_ratio | string | – | – |
| async | boolean | – | Async task if the model supports it. |
| background | string | – | – |
| cfg_scale | number | – | Model-specific image CFG scale. See get_model. |
| compression | integer | – | – |
| control_strength | number | – | Model-specific edit control strength. See get_model. |
| creativity | number | – | Model-specific image edit creativity. See get_model. |
| fidelity | number | – | Model-specific image edit fidelity. See get_model. |
| guidance | number | – | Model-specific guidance value. See get_model. |
| guidance_scale | number | – | Model-specific guidance scale. See get_model. |
| height | integer | – | Model-specific output height in pixels. See get_model. |
| image_url | string | – | Single source image URL. Kept for TokenLab compatibility; use images for the official JSON shape. |
| image_urls | array | – | Multiple source image URLs. GPT Image edits accept up to 16 source images; xAI Grok Imagine Image 2… |
| images | array | – | Official JSON image references for image edits. Provide exactly one of image_url or file_id for eac… |
| mask | object | – | Optional JSON mask reference for image edits. Provide exactly one of image_url or file_id. Multipar… |
| model | string | yes | Explicit image-edit model ID. |
| moderation | string | – | – |
| n | integer | – | – |
| output_compression | integer | – | – |
| output_format | string | – | – |
| prompt | string | – | – |
| quality | string | – | – |
| resolution | string | – | – |
| response_format | string | – | – |
| size | string | – | – |
| steps | integer | – | Model-specific inference step count. See get_model. |
| user | string | – | – |
| width | integer | – | Model-specific output width in pixels. See get_model. |
No output schema declared.
No examples provided.
edit_image_file Edit image ~403
Edits an image using multipart image uploads, JSON image URLs, or the official JSON images array for supported GPT Image models.
| Name | Type | Req | Description |
|---|---|---|---|
| Idempotency-Key | string | – | Optional key that makes an image request safe to retry if the request created a task. Send a new un… |
| X-TokenLab-Delivery-Policy | string | – | Per-request Delivery policy. Overrides the API key and Workspace defaults. Auto tries TokenLab Veri… |
| aspect_ratio | string | – | – |
| async | boolean | – | Async task if the model supports it. |
| background | string | – | – |
| cfg_scale | number | – | Model-specific image CFG scale. See get_model. |
| compression | integer | – | – |
| control_strength | number | – | Model-specific edit control strength. See get_model. |
| creativity | number | – | Model-specific image edit creativity. See get_model. |
| fidelity | number | – | Model-specific image edit fidelity. See get_model. |
| guidance | number | – | Model-specific guidance value. See get_model. |
| guidance_scale | number | – | Model-specific guidance scale. See get_model. |
| height | integer | – | Model-specific output height in pixels. See get_model. |
| image | – | – | Source image file(s). Repeat image for multiple source images. GPT Image edits accept up to 16 imag… |
| mask | string | – | Pass local file path. |
| model | string | yes | Explicit image-edit model ID. |
| moderation | string | – | – |
| n | integer | – | – |
| output_compression | integer | – | – |
| output_format | string | – | – |
| prompt | string | – | – |
| quality | string | – | – |
| resolution | string | – | – |
| response_format | string | – | – |
| size | string | – | – |
| steps | integer | – | Model-specific inference step count. See get_model. |
| user | string | – | – |
| width | integer | – | Model-specific output width in pixels. See get_model. |
No output schema declared.
No examples provided.
evaluate_decisions Evaluate decision questions ~110
Evaluate typed Noul probability, Choice, and Score questions against shared state using the native System One endpoint. Discover a decision model with list_models/get_model first. Returns synchronous structured decisions, not chat text. A decision does not authorize an external action.
| Name | Type | Req | Description |
|---|---|---|---|
| X-TokenLab-Delivery-Policy | string | – | Per-request Delivery policy. Overrides the API key and Workspace defaults. Auto tries TokenLab Veri… |
| model | string | yes | – |
| questions | object | yes | – |
| state | – | yes | – |
No output schema declared.
No examples provided.
get_api_overview Get TokenLab 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 Get model ~57
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.
| Name | Type | Req | Description |
|---|---|---|---|
| model | string | yes | The model ID |
No output schema declared.
No examples provided.
get_model_pricing Get model pricing ~47
Retrieves pricing-only detail for one model. No API key is needed. Use it to explain a price, not to build a request.
| Name | Type | Req | Description |
|---|---|---|---|
| model | string | yes | The model ID |
No output schema declared.
No examples provided.
get_pricing List model pricing ~47
Returns the public pricing surface for active models, with optional provider and tag filters.
| Name | Type | Req | Description |
|---|---|---|---|
| provider | string | – | Filter by provider ID. |
| tag | string | – | Filter by model tag. |
No output schema declared.
No examples provided.
get_task_status Get async task status ~73
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.
| Name | Type | Req | Description |
|---|---|---|---|
| id | string | yes | Returned id/task_id or the ID in poll_url. |
No output schema declared.
No examples provided.
list_files List files ~152
List files
| Name | Type | Req | Description |
|---|---|---|---|
| after | string | – | – |
| after_id | string | – | Anthropic Files cursor. Return files after this public file id. Requires the Anthropic Files beta h… |
| anthropic-beta | string | – | Include files-api-2025-04-14 to use Anthropic Files API mode. |
| before_id | string | – | Anthropic Files cursor. Return files before this public file id. Requires the Anthropic Files beta … |
| limit | integer | – | Files to return. |
| purpose | string | – | Optional file purpose filter. batch and batch_output cover Batch API files; user_data and vision co… |
| scope_id | string | – | Reserved scope cursor; returns an explicit unsupported error. |
No output schema declared.
No examples provided.
list_models List models ~147
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`.
| Name | Type | Req | Description |
|---|---|---|---|
| category | string | – | Filter by model category. |
| provider | string | – | Public provider filter (openai/anthropic/google/minimax). |
| recommended_for | string | – | Sort non-chat models for a task; include recommendation evidence. |
| tag | string | – | Filter by a public capability tag. |
| view | string | – | compact by default; full returns the complete OpenAI-compatible list. |
No output schema declared.
No examples provided.
rerank_documents Rerank documents ~108
Reranks documents by relevance to a query using semantic similarity.
| Name | Type | Req | Description |
|---|---|---|---|
| X-TokenLab-Delivery-Policy | string | – | Per-request Delivery policy. Overrides the API key and Workspace defaults. Auto tries TokenLab Veri… |
| documents | array | yes | Documents to rerank. |
| model | string | yes | Reranker model to use |
| query | string | yes | Search query. |
| return_documents | boolean | – | – |
| top_n | integer | – | Number of results to return |
No output schema declared.
No examples provided.
retrieve_file Retrieve file ~45
Retrieve file
| Name | Type | Req | Description |
|---|---|---|---|
| anthropic-beta | string | – | Include files-api-2025-04-14 to use Anthropic Files API mode. |
| file_id | string | yes | – |
No output schema declared.
No examples provided.
retrieve_file_content Retrieve file content ~21
Retrieve file content
| Name | Type | Req | Description |
|---|---|---|---|
| file_id | string | yes | – |
No output schema declared.
No examples provided.
transcribe_audio Create transcription ~150
Transcribes audio into text (Speech-to-Text).
| Name | Type | Req | Description |
|---|---|---|---|
| X-TokenLab-Delivery-Policy | string | – | Per-request Delivery policy. Overrides the API key and Workspace defaults. Auto tries TokenLab Veri… |
| file | string | yes | Audio file to transcribe Pass local file path. |
| language | string | – | ISO-639-1 language code |
| model | string | yes | Transcription model ID; no default. |
| prompt | string | – | Optional prompt text |
| response_format | string | – | Response format |
| temperature | number | – | Sampling temperature |
| timestamp_granularities | array | – | Timestamp granularity selection. Requires verbose_json output when requesting word-level timestamps. |
No output schema declared.
No examples provided.
translate_audio Translate audio ~90
Transcribes audio and translates the result to English.
| Name | Type | Req | Description |
|---|---|---|---|
| X-TokenLab-Delivery-Policy | string | – | Per-request Delivery policy. Overrides the API key and Workspace defaults. Auto tries TokenLab Veri… |
| file | string | yes | Pass local file path. |
| model | string | yes | – |
| prompt | string | – | – |
| response_format | string | – | – |
| temperature | number | – | – |
No output schema declared.
No examples provided.
translate_text Translate text ~84
Translates text into a target language using the current translation request format.
| Name | Type | Req | Description |
|---|---|---|---|
| X-TokenLab-Delivery-Policy | string | – | Per-request Delivery policy. Overrides the API key and Workspace defaults. Auto tries TokenLab Veri… |
| model | string | yes | – |
| source_language | string | – | – |
| target_language | string | yes | – |
| text | string | yes | – |
No output schema declared.
No examples provided.
upload_file Upload file ~166
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.
| Name | Type | Req | Description |
|---|---|---|---|
| anthropic-beta | string | – | Include files-api-2025-04-14 to use Anthropic Files API mode. |
| file | string | yes | The file: up to 200 MiB for batch, 50 MiB for images. Pass local file path. |
| model | string | – | Optional TokenLab extension for image file uploads. Defaults to gpt-image-2 and binds the returned … |
| purpose | string | – | Required in TokenLab/OpenAI-compatible mode: use batch for Batch API JSONL files, or user_data/visi… |
No output schema declared.
No examples provided.
How do I install the TokenLab MCP Server server?
TokenLab MCP Server runs locally as an npm package, launched with npx -y @tokenlabai/mcp-server. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.
npm · @tokenlabai/mcp-server
claude mcp add hedging8563-tokenlab -- npx -y @tokenlabai/mcp-server
What is the TokenLab MCP Server server?
TokenLab MCP Server is listed in the public MCP registry as io.github.hedging8563/tokenlab. TokenLab MCP server: generate images and video, call models. 32 default and 89 full-profile tools. This page covers its npm package (@tokenlabai/mcp-server).
Is the TokenLab MCP Server server safe to use?
TokenLab MCP Server scores 81 out of 100 on VerifyMCP. It declares no install or post-install scripts. Its build provenance is signed and verified. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.
What tools does the TokenLab MCP Server server expose?
TokenLab MCP Server exposes 32 tools: cancel_task, create_3d_model, create_anthropic_message, create_chat_completion, create_embedding, and 27 more. Their descriptions and schemas cost roughly 7,118 tokens of context every time the server is loaded.
Is the TokenLab MCP Server server still maintained?
TokenLab MCP Server is still listed as active in the MCP registry. We last reached this channel on 4 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.
What licence is the TokenLab MCP Server server under?
TokenLab MCP Server declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.