WaveSpeed
NPM · @WAVESPEED/MCP · 2 COMPONENTS
Run any model on the live WaveSpeed catalog: image, video, audio, 3D.
Available components
Last scanned (3 hours ago)
Scores higher than 93% 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 Security81
- No malware found by supply-chain analysis.Pass
- CVE check failed: a known high-severity CVE affects zod 3.25.76, a direct dependency. A fixed version is available. View diagnostics → Fail
- No install/post-install scripts declared.Pass
- 30 of 94 dependencies flagged as unhealthy. View diagnostics → Partial
Provenance & Transparency97
- Source repository is publicly reachable at the declared URL. View diagnostics → Pass
- Cryptographically verified build provenance (signed, bound to WaveSpeedAI/mcp-server). View diagnostics → Pass
- Clear OSI-approved license (MIT).Pass
- Actively maintained (last published 1 days ago).Pass
- Disclosure check failed: no security disclosure policy was found in the source repository. See how to fix → Fail
Schema Quality & AI Usability76
- 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 3568 tokens (~209/item across 17 items; 16 tools + 1 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 Management100
- No destabilizing schema changes in the last 30 days.Pass
Tool Coverage98
- 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
- 95% 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 18 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
- Supports UI / widget rendering.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 +20
- Known CVEs: unverified → fail ▼ security
- Malware scan: unverified → pass ▲ security
- Dependency health: unverified → 0.86 ▲ functional
- 3 Nov 26 −20
- Known CVEs: fail → unverified ▼ security
- Malware scan: pass → unverified ▼ security
- Dependency health: 0.86 → unverified ▼ functional
- Package version: 1.2.4 → 1.2.7 functional
- Package version: 1.2.4 → 1.2.6 functional
- 1 Nov 26 0
- Stability: pass → unverified ▼ security
- Tool safety: pass → unverified ▼ security
- Capabilities: pass → unverified ▼ functional
- Tool coverage: 100 → unverified ▼ functional
- Schema quality: 100 → unverified ▼ functional
- Package version: 1.2.2 → 1.2.4 functional
- Package version: 1.2.2 → 1.2.3 functional
- 29 Oct 26 +2
- Stability: pass → unverified ▼ security
- Tool safety: pass → unverified ▼ security
- Capabilities: pass → unverified ▼ functional
- Tool coverage: 100 → unverified ▼ functional
- First check of Schema quality: 100 functional
- First check of Capabilities: pass functional
- First check of Schema quality: unverified functional
- Package version: 1.1.3 → 1.2.2 functional
- 28 Oct 26 +15
- Malware scan: unverified → pass ▲ security
- 27 Oct 26 +6
- Known CVEs: unverified → fail ▼ security
- Dependency health: unverified → 0.86 ▲ functional
- Package version: 1.1.0 → 1.1.3 functional
- Package version: 1.1.0 → 1.1.2 functional
- Package version: 1.1.0 → 1.1.1 functional
- 26 Oct 26 −23
- Known CVEs: fail → unverified ▼ security
- Malware scan: pass → unverified ▼ security
- Dependency health: 0.86 → unverified ▼ functional
- Schema quality: pass → fail ▼ functional
- Tool coverage: 87% → 93% ▲ functional
- Package version: 1.0.18 → 1.1.0 functional
- 24 Oct 26 −5
- CVE-2023-54404 affects this package: high ▼ security
- Known CVEs: pass → fail ▼ security
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 5 Nov 2026 · Analysed npm/@wavespeed/mcp@1.2.7
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 | WaveSpeedAI/mcp-server |
| Certificate issuer | https://token.actions.githubusercontent.com |
| Certificate SAN | https://github.com/WaveSpeedAI/mcp-server/.github/workflows/npm-publish.yml@refs/heads/main |
| Rekor log index | 3677477809 |
| Predicate type | SLSA build provenance https://slsa.dev/provenance/v1 |
| Subject digest | sha512:278d2b434906a2448ce653c7630e263ef8f4d57f39dbf79947ce87a0eb507eb98535251da468ddaaef04d7e4c24cea34a8ab3142682fd7b6a47dee7fe |
Background: How many MCP packages publish verified provenance →
Vulnerabilities 1 finding
| ID | CVE | Severity | Vector | Fix available |
|---|---|---|---|---|
| GHSA-mrhx-c7xc-m3w5 | CVE-2023-54404 | high | CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H | yes |
Background: What a vulnerability scan can and cannot prove →
Dependencies 94 packages
| Packages resolved | 94 |
|---|---|
| Stale | 30 |
| Tree resolution | Complete |
Background: SBOMs and build attestations, explained →
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 →
delete_predictions ~142
Delete finished predictions from this account's run history, up to 100 at a time. This is a soft delete: each record stays, with status "deleted" and without its outputs, and list_predictions and get_prediction still return it that way; the output links are revoked (best effort). This tool cannot undo it. Runs that are still going are left alone, and only the key's own organization's records are deleted. Ask the user first, and pass confirm: true only after they agreed to delete these ids.
| Name | Type | Req | Description |
|---|---|---|---|
| confirm | boolean | yes | Must be true: the user has agreed to delete these predictions |
| ids | array | yes | Prediction ids to delete |
No output schema declared.
No examples provided.
edit_image ~336
Change existing images with the same models as the WaveSpeed /chat page: edits, restyles, backgrounds, adding or removing things, combining several images. In the prompt, name input media as @image 1, @image 2, @video 1, @audio 1 (counted in the order the lists are given); they are renamed to what the model expects.
| Name | Type | Req | Description |
|---|---|---|---|
| aspect_ratio | string | – | e.g. 1:1, 16:9, 9:16, 4:3, 3:4, 21:9, 9:21. The closest ratio the model supports is used; a note says when. If omitted: text-to-image is 1:1; with input images it is determined automatically from the… |
| estimate_only | boolean | – | true: only return the price estimate and the request that would run. Nothing is submitted or charged. |
| images | array | yes | The images to edit, in order: public URLs, or "@./path" for local files (uploaded automatically). |
| model | string | – | Only when the user names a model; default is the first (Seedream 5 Pro). |
| prompt | string | yes | Complete visual prompt: subject, composition, style, lighting, mood. |
| resolution | string | – | Only when the user asks for a size. The closest size the model supports is used (a tie goes to the smaller one); a note says when. |
| wait_seconds | integer | – | Max seconds to wait for the result in this call (default 0: return the prediction id right away) |
No output schema declared.
No examples provided.
edit_video ~442
Edit an existing video with the same models as the WaveSpeed /chat page. Name the video and any references in the prompt (e.g. "replace the cat in @video 1 with the lion from @image 1"). In the prompt, name input media as @image 1, @image 2, @video 1, @audio 1 (counted in the order the lists are given); they are renamed to what the model expects.
| Name | Type | Req | Description |
|---|---|---|---|
| estimate_only | boolean | – | true: only return the price estimate and the request that would run. Nothing is submitted or charged. |
| model | string | – | Only when the user names a model (seedance-2.5, seedance-2.5-turbo, seedance-2.0, seedance-2.0-turbo, seedance-2.0-fast, seedance-2.0-fast-turbo, seedance-2.0-mini, wan-3.0, wan-3.0-prime, kling-4.0,… |
| prompt | string | yes | What to change in the video and what must stay. |
| reference_audios | array | – | Optional audio for voice, music or sound: public URLs, or "@./path" for local files (uploaded automatically). |
| reference_images | array | – | Optional images to use as references: public URLs, or "@./path" for local files (uploaded automatically). |
| resolution | string | – | Only when the user asks for a resolution, or 480p for a cheaper draft; otherwise omit. The closest resolution the model supports is used (a tie goes to the lower one); a note says when. MiniMax H3 de… |
| video | string | yes | The video to edit (URL or "@./path"). |
| wait_seconds | integer | – | Max seconds to wait for the result in this call (default 0: return the prediction id right away) |
No output schema declared.
No examples provided.
extend_video ~405
Continue an existing video with new footage after its end, with the same models as the WaveSpeed /chat page. Turbo models cannot extend. In the prompt, name input media as @image 1, @image 2, @video 1, @audio 1 (counted in the order the lists are given); they are renamed to what the model expects.
| Name | Type | Req | Description |
|---|---|---|---|
| duration | integer | – | Seconds of new footage; omit to use the model default. A length outside the model's range is moved into it; a note says when. |
| estimate_only | boolean | – | true: only return the price estimate and the request that would run. Nothing is submitted or charged. |
| last_frame | string | – | Optional image the continuation should end on. |
| model | string | – | Only when the user names a model (seedance-2.5, seedance-2.5-turbo, seedance-2.0, seedance-2.0-turbo, seedance-2.0-fast, seedance-2.0-fast-turbo, seedance-2.0-mini, wan-3.0, wan-3.0-prime, kling-4.0,… |
| prompt | string | yes | What happens next. |
| resolution | string | – | Only when the user asks for a resolution, or 480p for a cheaper draft; otherwise omit. The closest resolution the model supports is used (a tie goes to the lower one); a note says when. MiniMax H3 de… |
| video | string | yes | The video to continue (URL or "@./path"). |
| wait_seconds | integer | – | Max seconds to wait for the result in this call (default 0: return the prediction id right away) |
No output schema declared.
No examples provided.
generate_image ~411
Create an image from a text description with the same models as the WaveSpeed /chat page (seedream-5-pro, nano-banana-2.1, nano-banana-2, nano-banana-pro, gpt-image-2.5, gpt-image-2; default seedream-5-pro). Give reference_images to use existing images as subject, product, face or style (the model's edit endpoint is used). To change existing images use edit_image. In the prompt, name input media as @image 1, @image 2, @video 1, @audio 1 (counted in the order the lists are given); they are renamed to what the model expects.
| Name | Type | Req | Description |
|---|---|---|---|
| aspect_ratio | string | – | e.g. 1:1, 16:9, 9:16, 4:3, 3:4, 21:9, 9:21. The closest ratio the model supports is used; a note says when. If omitted: text-to-image is 1:1; with input images it is determined automatically from the… |
| estimate_only | boolean | – | true: only return the price estimate and the request that would run. Nothing is submitted or charged. |
| model | string | – | Only when the user names a model; default is the first (Seedream 5 Pro). |
| prompt | string | yes | Complete visual prompt: subject, composition, style, lighting, mood. |
| reference_images | array | – | Optional images whose subject, product, face or style the new image should use: public URLs, or "@./path" for local files (uploaded automatically). |
| resolution | string | – | Only when the user asks for a size. The closest size the model supports is used (a tie goes to the smaller one); a note says when. |
| wait_seconds | integer | – | Max seconds to wait for the result in this call (default 0: return the prediction id right away) |
No output schema declared.
No examples provided.
generate_video ~675
Create a video with the same models as the WaveSpeed /chat page (default seedance-2.5). Give first_frame to animate an image; give reference_images / reference_videos / reference_audios to keep characters, products, motion, voice or music. The right mode (text, image or reference to video) is picked from what you give. Videos can cost dollars: use estimate_only first when unsure. In the prompt, name input media as @image 1, @image 2, @video 1, @audio 1 (counted in the order the lists are given); they are renamed to what the model expects.
| Name | Type | Req | Description |
|---|---|---|---|
| aspect_ratio | string | – | e.g. 16:9, 9:16, 1:1, 4:3, 3:4, 21:9, 9:21. The closest ratio the model supports is used; a note says when. If omitted, the model's default ratio is used; with first_frame the video follows that imag… |
| duration | integer | – | Seconds, only when the user asks for a length; omit to use the model default. A length outside the model's range is moved into it; a note says when. |
| estimate_only | boolean | – | true: only return the price estimate and the request that would run. Nothing is submitted or charged. |
| first_frame | string | – | Image to start the video from (URL or "@./path"). |
| last_frame | string | – | Optional image to end on (needs first_frame). |
| model | string | – | Only when the user names a model (seedance-2.5, seedance-2.5-turbo, seedance-2.0, seedance-2.0-turbo, seedance-2.0-fast, seedance-2.0-fast-turbo, seedance-2.0-mini, wan-3.0, wan-3.0-prime, kling-4.0,… |
| prompt | string | yes | Shot description: subject, action, camera movement, style, sound. |
| reference_audios | array | – | Optional audio for voice, music or sound to use: public URLs, or "@./path" for local files (uploaded automatically). |
| reference_images | array | – | Optional images for characters, products or style to keep (not a first frame): public URLs, or "@./path" for local files (uploaded automatically). |
| reference_videos | array | – | Optional videos for motion, camera or a character to follow: public URLs, or "@./path" for local files (uploaded automatically). |
| resolution | string | – | Only when the user asks for a resolution, or 480p for a cheaper draft; otherwise omit. The closest resolution the model supports is used (a tie goes to the lower one); a note says when. MiniMax H3 de… |
| wait_seconds | integer | – | Max seconds to wait for the result in this call (default 0: return the prediction id right away) |
No output schema declared.
No examples provided.
get_balance ~23
Show the WaveSpeed account credit balance, with the link to top up.
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
get_model_schema ~65
Get a model's real input schema (required fields, properties, defaults). Call this before run_model so inputs match what the model actually accepts.
| Name | Type | Req | Description |
|---|---|---|---|
| model | string | yes | Model ID from list_models, e.g. bytedance/seedream-v5.0-pro |
No output schema declared.
No examples provided.
get_prediction ~83
Fetch the status and outputs of a past or in-flight prediction by id — use to pick up a run that returned done=false. Pass wait_seconds to keep waiting for it to finish.
| Name | Type | Req | Description |
|---|---|---|---|
| id | string | yes | Prediction id returned by run_model |
| wait_seconds | integer | – | Max seconds to wait for a terminal status; 0 = return the current status now |
No output schema declared.
No examples provided.
get_price ~81
Estimate the cost of a run before executing it (no charge). Provide the same input you would pass to run_model — pricing often depends on inputs like duration or resolution, and a quote made without them can be lower than the real charge.
| Name | Type | Req | Description |
|---|---|---|---|
| input | object | – | Inputs the quote should account for |
| model | string | yes | Model ID from list_models |
No output schema declared.
No examples provided.
get_usage ~107
Usage statistics: spend, request counts, daily series and per-model breakdown. Defaults to the last 7 days. Requires an API key with Billing access.
| Name | Type | Req | Description |
|---|---|---|---|
| model | string | – | Filter by model ID as list_models returns it, e.g. bytedance/seedream-v5.0-pro |
| since | string | – | Start (ISO or YYYY-MM-DD); default 7 days ago |
| until | string | – | End (ISO or YYYY-MM-DD); default now |
No output schema declared.
No examples provided.
list_billings ~132
List itemized charges and refunds (billing records). Requires an API key with Billing access.
| Name | Type | Req | Description |
|---|---|---|---|
| key | string | – | Filter by the API key uuid that generated the charge |
| limit | integer | – | Page size |
| model | string | – | Filter by model ID as list_models returns it, e.g. bytedance/seedream-v5.0-pro |
| page | integer | – | – |
| since | string | – | Records after this time (ISO or YYYY-MM-DD) |
| type | string | – | – |
| until | string | – | Records before this time (ISO or YYYY-MM-DD) |
No output schema declared.
No examples provided.
list_models ~109
Search the live WaveSpeed model catalog (image, video, audio, 3D). Returns model IDs usable with run_model. Do not invent model IDs — always pick one returned by this tool.
| Name | Type | Req | Description |
|---|---|---|---|
| limit | integer | – | Max results |
| query | string | – | Free-text filter on id/name/description |
| refresh | boolean | – | Bypass the 1h catalog cache |
| type | string | – | Filter by modality type, e.g. text-to-image, image-to-video |
No output schema declared.
No examples provided.
list_predictions ~122
List past predictions (run history), newest window first. Defaults to the last 24 hours; pass since/until (ISO or YYYY-MM-DD) for other ranges. Use get_prediction with an id for one task in full.
| Name | Type | Req | Description |
|---|---|---|---|
| limit | integer | – | Page size |
| model | string | – | Filter by model ID |
| page | integer | – | – |
| since | string | – | Created after this time (ISO or YYYY-MM-DD) |
| status | string | – | – |
| until | string | – | Created before this time (ISO or YYYY-MM-DD) |
No output schema declared.
No examples provided.
run_model ~190
Run any WaveSpeed model. input keys come from get_model_schema; unknown keys are rejected before submission. Local files: pass "@./path" in a media field (image, images, video, audio, mask …) — it is uploaded and replaced with hosted URLs (bare paths are NOT uploaded). Returns the prediction id right away (done=false); call get_prediction with that id and wait_seconds until done=true to get the output URLs. The task keeps running on the server. Pass wait_seconds here to wait for a quick model in the same call.
| Name | Type | Req | Description |
|---|---|---|---|
| input | object | yes | Model inputs per its schema (e.g. {"prompt": "...", "aspect_ratio": "16:9"}) |
| model | string | yes | Model ID from list_models |
| wait_seconds | integer | – | Max seconds to wait for the result in this call (default 0: return the prediction id right away) |
No output schema declared.
No examples provided.
upload_file ~56
Upload a local file to WaveSpeed and get its hosted URL (identical bytes reuse the same upload for 24h). Usually unnecessary — run_model handles "@./path" inputs itself.
| Name | Type | Req | Description |
|---|---|---|---|
| path | string | yes | Local file path |
No output schema declared.
No examples provided.
How do I install the WaveSpeed MCP server?
WaveSpeed runs locally as an npm package, launched with npx -y @wavespeed/mcp. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.
npm · @wavespeed/mcp
claude mcp add ai-wavespeed-mcp -- npx -y @wavespeed/mcp
What is the WaveSpeed MCP server?
WaveSpeed is an MCP server listed in the public MCP registry as ai.wavespeed/mcp. Run any model on the live WaveSpeed catalog: image, video, audio, 3D. This page covers its npm package (@wavespeed/mcp).
Is the WaveSpeed MCP server safe to use?
WaveSpeed scores 89 out of 100 on VerifyMCP. We recorded 1 known advisory against it as of 5 November 2026. 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 WaveSpeed MCP server expose?
WaveSpeed exposes 16 tools: list_models, get_model_schema, run_model, generate_image, edit_image, and 11 more. Their descriptions and schemas cost roughly 3,379 tokens of context every time the server is loaded.
Is the WaveSpeed MCP server still maintained?
WaveSpeed is still listed as active in the MCP registry. We last reached this channel on 5 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 WaveSpeed MCP server under?
WaveSpeed declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.