canonical: https://jentic.com/apis/monodesk.com/monodesk

# MonoDesk API

The MonoDesk API publishes the discovery surface for MonoDesk's Model Context Protocol transport at api.monodesk.com. Its streamable HTTP endpoint accepts authenticated requests for MonoDesk tools, resources, and prompts, and a companion status check confirms the endpoint is reachable. Access runs through an OAuth 2.0 authorization code flow hosted on Supabase, requesting the openid, profile, email, and phone scopes.

## For AI agents

Reach MonoDesk's tools, resources, and prompts over its authenticated streamable HTTP endpoint, and check that the endpoint is reachable before sending requests.

## Scope

Does not document MonoDesk's individual tools, offer REST resources beyond the transport endpoint, or manage user accounts. Use for reaching MonoDesk tools, resources, and prompts over its streamable HTTP endpoint only.

## Capabilities

- Send authenticated tool, resource, and prompt requests to the MonoDesk streamable HTTP endpoint
- Check that the MonoDesk endpoint is reachable and the bearer token is accepted before a session starts
- Authorize a MonoDesk user through the OAuth 2.0 authorization code flow with the openid, profile, email, and phone scopes

## Use cases

### Agent access to MonoDesk tools through Jentic

An AI agent that needs MonoDesk's tools can reach them through Jentic without a separate client install. The agent searches for 'call a MonoDesk tool', loads the POST `/api/mcp/mcp` operation with its schema, and sends the request with the OAuth bearer token injected at call time. A 401 response signals a missing or invalid token, so the agent knows to stop rather than retry blindly.

Example prompt: Send a tool-list request to POST `/api/mcp/mcp` and report the names of the MonoDesk tools returned

### Pre-flight reachability check

Before a long agent session, a workflow confirms the MonoDesk endpoint is up and that the current OAuth token is accepted. GET `/api/mcp/mcp` returns 200 when the endpoint is reachable and 401 when authentication is required, which makes it a cheap health probe ahead of real requests.

Example prompt: Call GET `/api/mcp/mcp` and, if it returns 401, prompt the user to re-authorize MonoDesk before continuing

### Delegated user sign-in for MonoDesk

Every MonoDesk request acts for a signed-in user. The spec declares an OAuth 2.0 authorization code flow whose authorize and token URLs sit on a Supabase auth host, with scopes openid, profile, email, and phone, so a client obtains a user token once and attaches it to each call.

Example prompt: Complete the MonoDesk authorization code flow with the openid and profile scopes, then confirm the token with GET `/api/mcp/mcp`

## Key resources

- **Streamable HTTP endpoint** — POST for tool, resource, and prompt access and GET for a reachability status check, both at `/api/mcp/mcp`

## AI readiness

This API is usable in Jentic One now. Its AI-readiness score against Jentic's framework shows where it stands today and where improvements would make it even easier for agents to use.

- **Score:** 55 / 100
- **Maturity:** Foundational
- **Dimensions:**
  - Foundational Compliance: 100 / 100
  - Developer Experience & Jentic Compatibility: 88 / 100
  - AI-Readiness & Agent Experience: 28 / 100
  - Agent Usability: 94 / 100
  - Security: 90 / 100
  - AI Discoverability: 44 / 100
- **View full report:** https://jentic.com/apis/monodesk.com/monodesk/scorecard
- **How the score is calculated:** https://docs.jentic.com/reference/api-readiness-framework/overview/
- **More about the dimensions:** https://docs.jentic.com/reference/api-readiness-framework/specification/#dimensional-model-overview

### Score it yourself

Every API in the directory is allowlisted, so you can re-score it with no key required.

- **Score your own API:** https://jentic.com/scorecard.md
- **Scoring CLI agent skill:** https://github.com/jentic/jentic-api-scorecard/blob/main/skills/jentic-api-scorecard/SKILL.md

```sh
npx @jentic/api-scorecard-cli score <openapi-url>
```

## Why Jentic

- **Setup:** Wiring MonoDesk by hand means running its OAuth 2.0 authorization code flow against a Supabase auth host, keeping the token fresh, and framing streamable HTTP requests yourself. Through Jentic you install once, import MonoDesk from the API Directory, store the credential once, and your agent calls it.
- **Permission scoping:** MonoDesk has two operations on a single path, so a rule bounds your agent by method: the GET status check, the POST request endpoint, or both. The tool being called is named in the request body, so rules bound which operations the agent may call, not which MonoDesk tool.
- **Credential handling:** Your MonoDesk OAuth token is stored once, encrypted, by your own Jentic One instance and injected at execution time. It never enters the agent's prompt, logs, or context.
- **Discovery method:** Agents search Jentic by intent such as 'call a MonoDesk tool' or 'check MonoDesk status', and Jentic returns the matching operation with its input schema so the agent reaches the right method on the transport path.

## Related APIs

- **Composio** — Tool platform that exposes many third-party actions to agents
- **Pipedream** — Workflow platform with hosted connected-account actions
- **Supabase** — Platform API for the Supabase projects that host auth and data

## FAQ

### What authentication does the MonoDesk API use?

The MonoDesk API declares an OAuth 2.0 authorization code flow in its OpenAPI spec, with authorize and token URLs on a Supabase auth host and the scopes openid, profile, email, and phone. Both operations list that scheme, and the resulting token is sent as a bearer token. Through Jentic the token is held by your own instance and attached at call time.

### Is there a MonoDesk MCP server?

Yes. The MonoDesk spec itself describes a streamable HTTP endpoint at `/api/mcp/mcp` for tool, resource, and prompt access. You can also connect it directly through Jentic: your OAuth token is injected at call time by your self-hosted instance instead of living in a client config file, your rules decide which operations the agent may call, and adding the next API is an import rather than another install.

### How do I check that MonoDesk is reachable through Jentic?

Search Jentic for 'check the MonoDesk endpoint status', load the GET `/api/mcp/mcp` operation, and execute it. A 200 response means the endpoint is reachable and the token is accepted, and a 401 means authentication is required. To run it on your own infrastructure, install Jentic One from its GitHub repo.

### What are the rate limits for the MonoDesk API?

The OpenAPI spec does not specify rate limits. Check the MonoDesk site at https://www.monodesk.com for current limits before running high-volume agent sessions.

### Can I limit what my agent is allowed to do with the MonoDesk API?

Partly. A rule can allow only GET `/api/mcp/mcp` so your agent can probe reachability without sending tool requests, or allow POST as well when it should act. Which tool a request invokes travels in the request body, so a rule cannot narrow it to one tool, and every call the agent makes is logged.
