# Dare (mcpb · dare-mcp-server-0.2.0.mcpb) Generate AI video and images on Dare (Seedance, Veo, Kling, Hailuo), billed to your own Dare credits - Trust score: 51/100 (low) - Change this week: +4 - Registry status: active - Liveness: live - Owner verified: no - Last scored: 2026-10-24 ## Components - mcpb · `dare-mcp-server-0.2.0.mcpb`: 51/100 (this document), [markdown](https://verifymcp.io/servers/avi-aggarwal14-dare-mcp-server/dare-mcp-server.md), [page](https://verifymcp.io/servers/avi-aggarwal14-dare-mcp-server/dare-mcp-server) ## Channel facts - Registry: `mcpb` - Package: `https://github.com/avi-aggarwal14/dare-mcp-server/releases/download/mcpb-0.2.0/dare-mcp-server-0.2.0.mcpb` - Version: `0.2.0` - Transport: `stdio` - SHA-256: `02504e640acb0d66d765dfc70aee143e5a1be3b3ea9d6375edf11844dfef8710` ## Trust breakdown 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. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog) Scored 2026-10-24. - **Supply Chain Security**: 23/100 - No malware scan is available for this kind of package: the supply-chain vendors we use do not cover it. This is a permanent gap in our coverage, not a finding about the package. - Known CVEs were checked across the 93 of 93 dependencies we could resolve, so this covers what we could see, not the whole tree. - No install/post-install scripts declared. - 30 of 93 dependencies flagged as unhealthy. - **Provenance & Transparency**: 48/100 - Source repository is publicly reachable at the declared URL. - Provenance check failed: no build-provenance attestation is published. - Clear OSI-approved license (MIT). - Actively maintained (last published 8 days ago). - Publishes a security disclosure policy (SECURITY.md). - **Schema Quality & AI Usability**: 72/100 - AI-judged instruction clarity (excellent). - Context-footprint check failed: tool/resource definitions use about 1846 tokens (~142/item across 13 items; 13 tools + 0 resources), over budget; trim descriptions and params. - Usage-examples check failed: none of the tools include examples. - **Stability & Change Management**: 27/100 - Stability observed for 8 of 30 days with no destabilising changes; credit accrues until the full window elapses. - **Tool Coverage**: 100/100 - 100% of tools have a non-trivial description (not blank, and not just the tool's name). - 100% of tool parameters carry a description. - **Tool Safety**: 100/100 - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured. - All 2 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation. - An AI judge read all 14 captured unit(s) of tool text and found none that tries to manipulate the model reading it. - **Capabilities**: 100/100 - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28. ## Install ### How do I install the Dare MCP server? Dare ships as an MCPB bundle, a single file you download and open in an MCP host that supports MCPB bundles, such as Claude Desktop. The host reads the launch command from the bundle's own manifest, so there is no command to copy. Before opening it, check the file's SHA-256 matches the one the MCP registry declares for it, 02504e640acb0d66d765dfc70aee143e5a1be3b3ea9d6375edf11844dfef8710; the commands to do that are on this page. If it does not match, do not open it. - Download bundle: `https://github.com/avi-aggarwal14/dare-mcp-server/releases/download/mcpb-0.2.0/dare-mcp-server-0.2.0.mcpb` - SHA-256: `02504e640acb0d66d765dfc70aee143e5a1be3b3ea9d6375edf11844dfef8710` ### Verify on macOS / Linux ```bash echo "02504e640acb0d66d765dfc70aee143e5a1be3b3ea9d6375edf11844dfef8710 dare-mcp-server-0.2.0.mcpb" | shasum -a 256 -c ``` ### Verify on Windows (PowerShell) ```powershell (Get-FileHash -Algorithm SHA256 .\dare-mcp-server-0.2.0.mcpb).Hash -eq "02504e640acb0d66d765dfc70aee143e5a1be3b3ea9d6375edf11844dfef8710" ``` ## Changelog Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims. ### 2026-10-23 (score 51, +4) - [functional improvement] Stability: unverified → 0.23 ### 2026-10-16 (score 47) First indexed and scored. ## MCP tools (13) ### `dare_list_models` (~97 tokens) List Dare models List the video and image models available on Dare with their supported durations, aspect ratios, quality tiers and reference limits. Call this before generating so parameters are valid for the chosen model, and dare_estimate_cost for prices. Makes no network request and spends no credits. Input parameters: - `kind` (string): Which model family to list. - `response_format` (string): `markdown` for a readable summary, `json` for the raw payload. ### `dare_estimate_cost` (~258 tokens) Estimate Dare credit cost Estimate the credit cost of a generation before running it, using Dare's own pricing table. Purely local arithmetic: no network request, no credits spent. Use this to check affordability, compare quality tiers, or size a batch. Input parameters: - `aspect_ratio` (string): Aspect ratio; affects cost on `gpt-image-2` only. - `audio_enabled` (boolean): Whether audio is generated (affects Veo and Kling). - `count` (integer): How many variations to generate. - `duration_seconds` (integer): Clip length in seconds (video). - `kind` (string): What is being generated. - `model` (string, required): Model id, e.g. `seedance-2-5`. - `quality` (string): Quality tier, e.g. `720p` for video or `2k` for image. - `reference_count` (integer): Number of reference assets attached (images count toward image-model surcharges). - `reference_video_seconds` (number): Total seconds of video references attached; billed in addition on Seedance 2.5. - `video_reference_count` (integer): How many of the references are video clips. Only video references earn Seedance's 0.6x discount. ### `dare_get_credit_balance` (~60 tokens) Get Dare credit balance Fetch the signed-in Dare account's current credit balance. Read-only. Use before a large batch to confirm there is enough headroom. Input parameters: - `response_format` (string): `markdown` for a readable summary, `json` for the raw payload. ### `dare_generate_video` (~448 tokens) Generate a video on Dare Generate a video from a text prompt on Dare, defaulting to Seedance 2.5. SPENDS CREDITS from the signed-in Dare account (a 10s 720p Seedance 2.5 clip is ~110 credits; call dare_estimate_cost first). Returns generation ids immediately. Rendering is slow — Seedance 2.5 jobs commonly take 5–15 minutes — so leave wait_seconds at 0 and poll with dare_get_generation, or set it only if your client tolerates long tool calls. Attach reference images, clips or audio by uploading them first with dare_upload_media and passing the storage keys. Input parameters: - `aspect_ratio` (string): Aspect ratio such as `16:9`, `9:16` or `auto`. - `audio_enabled` (boolean): Generate synchronised audio where the model supports it. - `count` (integer): Number of variations. Each one costs credits. - `dry_run` (boolean): Validate the request, resolve references and price it, but do not submit. Spends nothing. Returns the exact spec that would be sent. - `duration_seconds` (integer): Clip length in seconds. Seedance 2.5: 4–30; Seedance 2.0: 4–15; Kling: 3–15; Veo: 4/6/8 (8 with a reference); Hailuo: fixed. Ignored when a Seedance 2.5 video reference sets it. - `model` (string): Video model id. Seedance 2.5 supports up to 30 seconds. - `project_id` (string): Optional Dare project to file the generation under. - `prompt` (string, required): What the video should show. Be specific about subject, action, camera and style. - `quality` (string): Quality tier, e.g. `480p` or `720p` for Seedance 2.5. - `reference_storage_keys` (array): Storage keys from dare_upload_media to use as reference images, clips or audio. - `wait_seconds` (integer): Block up to this many seconds waiting for the result. 0 returns immediately. ### `dare_generate_image` (~189 tokens) Generate an image on Dare Generate a still image on Dare with Nano Banana 2, GPT Image 2 or Seedream 5 Pro. SPENDS CREDITS. Useful for producing a reference frame to feed into dare_generate_video. Input parameters: - `aspect_ratio` (string): Aspect ratio such as `16:9` or `1:1`. - `count` (integer): Number of variations. - `dry_run` (boolean): Validate and price without submitting. Spends nothing. - `model` (string): Image model id. - `project_id` (string): Optional Dare project id. - `prompt` (string, required): What the image should show. - `quality` (string): Quality tier, e.g. `1k`, `2k`, `4k`. - `reference_storage_keys` (array): Storage keys to use as references. - `wait_seconds` (integer): Block up to this long for the result. ### `dare_get_generation` (~167 tokens) Get a Dare generation Fetch one generation by id: its status (queued, processing, succeeded, failed), credits charged, and — once finished — the output asset URL. Read-only. Poll this after dare_generate_video; video jobs commonly take 5–15 minutes. Use wait_seconds to block for up to that long per call, sized to what your client's tool timeout allows (e.g. 45 for desktop apps, 300+ for Claude Code), and call again until status is terminal. Input parameters: - `generation_id` (string, required): Generation id returned by a dare_generate_* tool. - `response_format` (string): `markdown` for a readable summary, `json` for the raw payload. - `wait_seconds` (integer): Poll until the generation leaves a pending state, up to this many seconds. ### `dare_list_generations` (~95 tokens) List Dare library items List recent items in the Dare library — generations and uploads, newest first — with cursor pagination. Read-only. Use it to find an earlier video's id or an upload's storage key. Input parameters: - `cursor` (string): `next_cursor` from a previous call. - `limit` (integer): Items per page. - `response_format` (string): `markdown` for a readable summary, `json` for the raw payload. ### `dare_cancel_generation` (~42 tokens) Cancel a Dare generation Cancel an in-flight generation. Use when a job was started by mistake, to stop it consuming credits. Input parameters: - `generation_id` (string, required): Generation id to cancel. ### `dare_delete_generation` (~50 tokens) Delete a Dare generation Permanently delete a generation and its output from the Dare library. Destructive and irreversible — confirm with the user first. Does not refund credits. Input parameters: - `generation_id` (string, required): Generation id to delete. ### `dare_upload_media` (~152 tokens) Upload reference media to Dare Upload an image, video or audio file to Dare and return its storage key, for use as a reference in dare_generate_video or dare_generate_image. Accepts a local file path, a public URL, or base64 bytes. Spends no credits. Input parameters: - `base64` (string): Base64-encoded file bytes. - `content_type` (string): MIME type, e.g. `image/png`. Inferred when omitted. - `file_path` (string): Absolute path to a local file this server can read. - `name` (string): Display name in the Dare library. - `project_id` (string): Optional Dare project id. - `url` (string): Public URL to download and upload. ### `dare_list_uploads` (~76 tokens) List Dare uploads List previously uploaded reference media with their storage keys. Read-only, cursor-paginated. Input parameters: - `cursor` (string): `next_cursor` from a previous call. - `limit` (integer): Items per page. - `response_format` (string): `markdown` for a readable summary, `json` for the raw payload. ### `dare_delete_upload` (~60 tokens) Delete a Dare upload Permanently delete an uploaded reference asset from the Dare library. Destructive and irreversible — confirm with the user first. Generations that already used it are unaffected. Input parameters: - `upload_id` (string, required): Upload id from dare_upload_media or dare_list_uploads. ### `dare_list_projects` (~50 tokens) List Dare projects List the account's Dare projects, for filing generations under a project id. Read-only. Input parameters: - `response_format` (string): `markdown` for a readable summary, `json` for the raw payload. ## Diagnostics Captured diagnostic sections: Provenance, Dependencies. The full working is on the page: https://verifymcp.io/servers/avi-aggarwal14-dare-mcp-server/dare-mcp-server#diagnostics ## Score history - 2026-10-24: 51 - 2026-10-23: 51 - 2026-10-22: 47 - 2026-10-21: 47 - 2026-10-20: 47 - 2026-10-19: 47 - 2026-10-18: 47 - 2026-10-17: 47 - 2026-10-16: 47 ## Common questions ### What is the Dare MCP server? Dare is an MCP server listed in the public MCP registry as io.github.avi-aggarwal14/dare-mcp-server. Generate AI video and images on Dare (Seedance, Veo, Kling, Hailuo), billed to your own Dare credits. This page covers its MCPB bundle (https://github.com/avi-aggarwal14/dare-mcp-server/releases/download/mcpb-0.2.0/dare-mcp-server-0.2.0.mcpb). ### Is the Dare MCP server safe to use? Dare scores 51 out of 100 on VerifyMCP. It declares no install or post-install scripts. 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 Dare MCP server expose? Dare exposes 13 tools: dare_list_models, dare_estimate_cost, dare_get_credit_balance, dare_generate_video, dare_generate_image, and 8 more. Their descriptions and schemas cost roughly 1,744 tokens of context every time the server is loaded. ### What licence is the Dare MCP server under? Dare declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls. ## Links - Repository: https://github.com/avi-aggarwal14/dare-mcp-server - Website: https://avi-aggarwal.com/ - Changelog RSS feed: https://verifymcp.io/servers/avi-aggarwal14-dare-mcp-server/dare-mcp-server.xml - Changelog JSON feed: https://verifymcp.io/servers/avi-aggarwal14-dare-mcp-server/dare-mcp-server.json - HTML version of this page: https://verifymcp.io/servers/avi-aggarwal14-dare-mcp-server/dare-mcp-server