videovector
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@videovectorsearch for videos about ocean waves"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
VideoVector MCP Server
Official Model Context Protocol (MCP) server for VectorMethods VideoVector.
This package lets MCP clients such as Claude Desktop, Cursor, Claude Code, and custom agent runtimes search, inspect, and operate VideoVector media intelligence workflows through the public VideoVector API.
Status
Primary transport:
stdioSelf-hostable transport: Streamable HTTP at
/mcpRuntime: Node.js 18+
Package:
@vectormethods/videovector-mcp-serverCommand:
videovector-mcpServer name:
videovectorMCP Registry name:
io.github.VectorMethods/videovector-mcp-server
This repository is the public source of truth for VideoVector MCP server code, tool contracts, examples, and release metadata. Private VectorMethods backend deployment wiring, service accounts, project IDs, billing internals, and website source are intentionally not part of this repository.
Related MCP server: Gemini Omni MCP Server
Install
Use npx from your MCP client:
npx -y @vectormethods/videovector-mcp-serverOr install globally:
npm install -g @vectormethods/videovector-mcp-serverStdio Usage
VIDEOVECTOR_API_KEY=<your-videovector-api-key> videovector-mcpEnvironment variables:
Variable | Required | Default | Description |
| Yes for stdio | none | VideoVector API key. |
| No |
| API base URL. |
| No |
| Request timeout in milliseconds. |
| No |
| Retry count for retryable API failures. |
| No |
|
|
| No | current directory | Comma-separated directories from which local stdio |
| No |
|
|
Client Examples
Claude Desktop: examples/claude-desktop.json
Cursor: examples/cursor.json
Generic stdio: examples/custom-stdio.json
Simplified workflow stdio: examples/simple-stdio.json
Local Streamable HTTP: examples/streamable-http-local.json
Self-Hosted HTTP
HTTP mode is intended for self-hosted or private network deployments.
npm run build
MCP_TRANSPORT_MODE=http \
VIDEOVECTOR_BASE_URL=https://api.vectormethods.com/api/v2 \
node dist/index.jsEndpoints:
GET /healthPOST /mcp
The /mcp endpoint is stateless. Each POST is independent and may be routed
to any healthy instance. GET /mcp and DELETE /mcp return 405; clients
must not send or persist MCP-Session-Id.
HTTP requests must include either:
Authorization: Bearer <your-videovector-api-key>X-API-Key: <your-videovector-api-key>
HTTP hardening variables:
Variable | Default | Description |
|
| HTTP port. |
|
| Bind host. |
| empty | Optional comma-separated host allowlist. |
| empty | Optional comma-separated browser origin allowlist. |
|
| SDK JSON response mode. |
|
| Maximum graceful drain before active request contexts are closed. |
Both stdio and HTTP modes accept canonical production keys only (sk_live_ followed by
exactly 48 lowercase hexadecimal characters). Invalid candidates are rejected
before normal API use. In HTTP mode, validation uses the side-effect-free
GET /auth/validate API operation. Successful keys are cached for 60 seconds,
confirmed invalid keys for 10 minutes, and transient failures for five
seconds. Same-key checks are singleflighted and backend validation is bounded
to 16 concurrent calls plus a 64-request queue with a five-second timeout.
Plaintext keys are never written to caches or logs. When both supported HTTP
headers are present, X-API-Key takes precedence, matching the VideoVector
API.
Do not advertise a public hosted remote MCP endpoint until OAuth and MCP protected-resource metadata are enabled for that deployment.
Tools
For the lowest-friction agent workflow, set VIDEOVECTOR_TOOL_PROFILE=simple.
It exposes:
upload_media: stream a local media file to Playground or a named/index-ID destinationdefine_prompt: generate and, by default, save a Prompt Lab promptprocess_media: process Playground, an index, or selected media withsmart,content_aware, orfixedsegmentationsearch_media: vector or conditional search over Playground, an index, selected media, or prompt runs with stable cursor pagination
The default full profile preserves those tools plus the complete advanced
surface below. upload_media is local-stdio-only and is never advertised by
the Streamable HTTP transport. Its path must resolve inside
VIDEOVECTOR_UPLOAD_ROOTS (or the process working directory by default), and
the server streams and reopens the file for safe idempotent retries instead of
buffering it in memory.
The server exposes tools for:
semantic, image, multimodal, and structured metadata search
index, video, segment, and prompt discovery
prompt-run estimation, execution, status, results, retries, and cancellation
prompt management and schema testing
cloud connectors, import jobs, exports, and webhooks
The machine-readable tool contract is generated at artifacts/tool-contract.json. Private backend and website releases should vendor this artifact for MCP helper endpoints and documentation updates.
get_export_status is side-effect free: its download_url is only the
authenticated API endpoint and it never mints a bearer credential. Use the
separate get_export_download_url tool only when a header-free client
explicitly needs a short-lived bounded URL. Connector-delivered, processing,
failed, and otherwise unavailable exports return download_url: null. Treat
any non-null minted URL as a credential and do not log or persist it.
Development
npm ci
npm run verifyUseful scripts:
npm run typechecknpm run lintnpm run buildnpm testnpm run generate:contractnpm run check:contractnpm run check:examples
Use the MCP Inspector for local manual checks:
npx @modelcontextprotocol/inspectorFor stdio, point the Inspector to npx -y @vectormethods/videovector-mcp-server and set VIDEOVECTOR_API_KEY.
Security
Never commit API keys, cloud credentials, connector credentials, webhook secrets, service-account JSON, or .env files.
See SECURITY.md for supported versions, disclosure instructions, and operational guidance.
This server cannot be deployed
Maintenance
Related MCP Connectors
Plan, compare, price, generate, and recover AI video from compatible MCP clients.
Inspect and edit media canvases, run existing Flows, and retrieve results. Vyrl MCP token required.
Build, run, schedule, and publish AI video pipelines to YouTube and TikTok from any MCP client.
OAuth-protected ImagineVid MCP for image, video, and music generation.
Related MCP Servers
- AlicenseNot gradedqualityCmaintenanceEnables document ingestion, semantic search, and retrieval-augmented generation via MCP tools and REST API, using vector embeddings and intelligent chunking.MIT
- AlicenseNot gradedqualityCmaintenanceExposes video generation and editing tools to MCP-capable clients, enabling text-to-video, image-to-video, video editing, reusable voice and character profiles, and task status queries through natural language.4MIT
- FlicenseNot gradedqualityBmaintenanceEnables searching and retrieving full transcripts and metadata from YouTube and podcast content, including mentions, momentum, sponsors, and coverage, through a remote MCP endpoint with OAuth or trial key access.1-
- AlicenseNot gradedqualityBmaintenanceEnables MCP clients to search documents stored in OpenSQL/PostgreSQL using vector similarity, with support for version history and changelog retrieval.MIT