Skip to content

For agents, and the people who run them

Built to be set up by an agent

Most video APIs assume a person will click through a dashboard, read a guide and then check by eye that it works. Synento assumes an agent might do all three, and gives it the means to check its own work.

Why agents struggle with video

Three ways agent-written video fails

  • Failure is silent

    Traditional video services

    The code compiles, the WebSocket opens, the call "connects", and no media ever arrives. Nothing throws, so the agent reports success.

    Synento

    Every session is its own recording. The agent reads the manifest back, and a track with a non-null start_ts is proof that real frames arrived.

  • State lives in a dashboard

    Traditional video services

    Rooms, recordings and egress are set up in a console the agent cannot see. It guesses at settings and hopes.

    Synento

    Sessions, recordings and exports are REST calls, described by an OpenAPI spec. There is no recording to switch on, because recording is not a setting.

  • Retries make duplicates

    Traditional video services

    Agents retry. On most APIs a retried create makes a second room, or a second recording, or a second bill.

    Synento

    Session creation takes an Idempotency-Key. Send the same key again within 24 hours and you get the same session back.

Resources

Point your agent here

Public, credential-free and CORS-enabled, so any agent or tool can fetch them.

Try it

Paste this into your coding agent

Connecting the MCP server above is the fastest route. For an agent that can only fetch URLs and run commands, paste this instead.

Live callsprompt.md
Add live video calls to this app using Synento.

1. Read https://synento.com/llms.txt and follow the quickstart it links to.
2. Keep the API key server-side: add one route that creates a session and mints a connection token.
3. Join from the browser with @synento/client and publish camera and microphone.
4. Send an Idempotency-Key when you create the session.
5. Prove it works: after a two-participant test call, GET /v1/sessions/{sessionId}/manifest and confirm both participants have a cam and a mic track with a non-null start_ts. A track only appears once media reached it, so a missing track is a failure. Do not report success until both do.
Recorded 1:1 callsprompt-recorded-1-1.md
Add recorded 1:1 video calls to my app using Synento: create a project, a session, connection tokens, embed the call, and show the replay and MP4 export after the call.

Use the Synento MCP server. Read https://synento.com/llms.txt and https://synento.com/docs/guides/mcp.md. Keep the API key on the server (SYNENTO_API_KEY). The browser only receives a short-lived connection token. After a two-person test call, verify_session must pass before you say it works. A worked example is https://synento.com/docs/examples/ai-interview-recorder.

Safe by construction

Guardrails an agent can't forget

  • Keys stay on the server

    API keys are server secrets, stored only as peppered hashes. Browsers get connection tokens scoped to one session and one user, which expire after an hour.

  • Idempotent writes

    Session and replay-link creation accept an Idempotency-Key, so a retried request returns the original result.

  • Fair rate limits

    Limits apply per API key and per client, and the headers say when to back off. One noisy caller cannot lock anyone else out.

  • One response shape

    Every JSON response is { data, error } with a stable error code, so an agent can branch on errors without parsing prose.

Available in the beta

The Synento MCP server

Connect your agent once. It sets up the project, writes the integration, then reads the recording back to confirm camera and microphone media arrived. You approve access in the browser and choose the projects it can touch.

  • Remote MCP over Streamable HTTP, with nothing to install
  • OAuth 2.1 with PKCE: you approve each agent in the browser, per project, and can see its recent tool calls and disconnect it from the dashboard
  • The keys an agent writes into your app are restricted: they can only create sessions, mint connection tokens and read session manifests. Never an owner key
  • verify_session reads the recording back, says exactly which tracks are missing, and suggests the likely cause

Create a free account first. The agent signs in through your browser the first time it connects, and it needs an account to approve against.

Add to CursorAdd to Cursor
Claude Code
claude mcp add --transport http synento https://api.synento.com/mcp
Cursor and most other clients
{
  "mcpServers": {
    "synento": { "url": "https://api.synento.com/mcp" }
  }
}

Add this to .vscode/mcp.json. type http is Streamable HTTP.

VS Code
{
  "servers": {
    "synento": { "type": "http", "url": "https://api.synento.com/mcp" }
  }
}

Add this to ~/.codex/config.toml. A url is Streamable HTTP. Codex uses OAuth unless you set a bearer token.

Codex
[mcp_servers.synento]
url = "https://api.synento.com/mcp"

Name the environment variable that holds an agent token. The file stores the variable name, not the token. Create the token in the dashboard under Agents.

Codex, no browser
[mcp_servers.synento]
url = "https://api.synento.com/mcp"
bearer_token_env_var = "SYNENTO_AGENT_TOKEN"

Send an agent token instead of opening a browser. It starts with sat_, lasts 90 days unless you pick another lifetime (up to a year), and must not be committed.

Claude Code, no browser
claude mcp add --transport http synento https://api.synento.com/mcp \
  --header "Authorization: Bearer sat_…"

Example

AI interview recorder

A small Next.js app in the repository. The interviewer creates a link, the candidate joins a recorded 1:1 call in the browser, and after the call the app plays the recording and can export an MP4. The AI step is one function you replace. The app does not call a model and does not include an AI API key.

Read the example

Your agent is ready. Is your video platform?

Sign up, then hand your agent one URL.